2018-03-21T13:15:06Z http://www.intechopen.com/oai/index.php
oai:intechopen.com:129 2007-02-01 3-86611-283-102007-02-01
Robot Egomotion from the Deformation of Active Contours Guillem Alenya Carme Torras Mobile Robots: Perception & Navigation This work is partially funded by the EU PACO-PLUS project FP6-2004-IST-4-27657. The authors thank the brewer company DAMM in El Prat de Llobregat, Barcelona, and the robotics company Robosoft in Bidart, France, for their help in performing the experiments. InTech 2007-02-01 1 http://www.intechopen.com/articles/show/title/robot_egomotion_from_the_deformation_of_active_contours en ISBN:3-86611-283-1 http://www.intechopen.com/download/pdf/pdfs_id/129
oai:intechopen.com:130 2007-02-01 3-86611-283-102007-02-01
Visually Guided Robotics Using Conformal Geometric Computing Eduardo Bayro-Corrochano Luis Eduardo Falcon-Morales Julio Zamora-Esquivel Mobile Robots: Perception & Navigation In this chapter the authors have used a single non?standard mathematical framework, the Conformal Geometric Algebra, in order to simplify the set of data structures that we usually use with the traditional methods. The key idea is to define and use a set of products in CGA that will be enough to generate conformal transformations, manifolds as ruled surfaces and develop incidence algebra operations, as well as solve equations and obtain directed distances between different kinds of geometric primitives. Thus, within this approach, all those different mathematical entities and tasks can be done simultaneously, without the necessity of abandoning the system. Using conformal geometric algebra we even show that it is possible to find three grasping points for each kind of object, based on the intrinsic information of the object. The hand`s kinematic and the object structure can be easily related to each other in order to manage a natural and feasible grasping where force equilibrium is always guaranteed. These are only some applications that could show to the robotic and computer vision communities the useful insights and advantages of the CGA, and we invite them to adopt, explore and implement new tasks with this novel framework, expanding its horizon to new possibilities for robots equipped with stereo systems, range data, laser, omnidirectional and odometry. InTech 2007-02-01 2 http://www.intechopen.com/articles/show/title/visually_guided_robotics_using_conformal_geometric_computing en ISBN:3-86611-283-1 http://www.intechopen.com/download/pdf/pdfs_id/130
oai:intechopen.com:131 2007-02-01 3-86611-283-102007-02-01
One Approach to the Fusion of Inertial Navigation and Dynamic Vision Stevica Graovac Mobile Robots: Perception & Navigation The algorithm of fusion of data originating from the strap-down inertial navigation system (INS) and the dynamic vision based visual navigation system (VNS) has been suggested for the general case when the appropriate landmarks are in the field of a TV camera's view. The procedure is of weighted averaging type, allowing the adjustment of weighting factors having in mind the physical nature of errors characterizing both systems and according to the self-evaluation of some intermediate estimates made inside the VNS. The overall procedure could be reasonably reduced according to the particular application and to some InTech 2007-02-01 3 http://www.intechopen.com/articles/show/title/one_approach_to_the_fusion_of_inertial_navigation_and_dynamic_vision en ISBN:3-86611-283-1 http://www.intechopen.com/download/pdf/pdfs_id/131
oai:intechopen.com:132 2007-02-01 3-86611-283-102007-02-01
Sonar Sensor Interpretation and Infrared Image Fusion for Mobile Robotics Mark Hinders Wen Gao William Fehlman Mobile Robots: Perception & Navigation We have developed a set of automatic algorithms that use sonar backscattering data to distinguish extended objects in the campus environment by taking a sequence of scans of each object, plotting the corresponding backscatter vs. scan angle, extracting abstract feature vectors and then categorizing them in various phase spaces. We have chosen to perform the analysis with multiple scans per object as a balance between data processing requirements and robustness of the results. Although our current robotic scanner is parked for each scan and then moves to the next scan location before scanning again, it is not difficult to envision a similar mobile robotic platform that scans continuously while moving. It could then take ten or even a hundred scans while approaching a tree or while moving along a unit of a fence, for example. Based on our experience with such scans, however, we would typically expect only the characteristic variations in backscattering behavior described above. Hence, we would envision scans taken continuously as the robot moves towards or along an object, and once the dominant features are identified, the necessary backscatter plots could be processed in the manner described in the previous sections, with the rest of the data safely purged from memory. Our reason for performing this level of detailed processing is a scenario where an autonomous robot is trying to identify particular landmark objects, presumably under low- InTech 2007-02-01 4 http://www.intechopen.com/articles/show/title/sonar_sensor_interpretation_and_infrared_image_fusion_for_mobile_robotics en ISBN:3-86611-283-1 http://www.intechopen.com/download/pdf/pdfs_id/132
oai:intechopen.com:133 2007-02-01 3-86611-283-102007-02-01
Obstacle Detection Based on Fusion Between Stereovision and 2D Laser Scanner Raphael Labayrade Dominique Gruyer Cyril Royere Mathias Perrollaz Didier Aubert Mobile Robots: Perception & Navigation InTech 2007-02-01 5 http://www.intechopen.com/articles/show/title/obstacle_detection_based_on_fusion_between_stereovision_and_2d_laser_scanner en ISBN:3-86611-283-1 http://www.intechopen.com/download/pdf/pdfs_id/133
oai:intechopen.com:134 2007-02-01 3-86611-283-102007-02-01
Optical Three-Axis Tactile Sensor M. Ohka Mobile Robots: Perception & Navigation In this chapter, mechanism and evaluation of the optical three-axis tactile sensor are described to show sensing characteristics on three components of force vector applied to the sensing element. Then, recognition method for subtle convex portions of flat plate is presented to show effective of the present method using a series of experiments. In future work, the author plans to mount the present three-axis tactile sensors on a micro and robotic fingers to perform verification experiments and will perform edge tracing of an object and object manipulation. In these experiments, the presented recognition method will be effective to determine subtle concave and convex portions located on any surfaces. InTech 2007-02-01 6 http://www.intechopen.com/articles/show/title/optical_three-axis_tactile_sensor en ISBN:3-86611-283-1 http://www.intechopen.com/download/pdf/pdfs_id/134
oai:intechopen.com:135 2007-02-01 3-86611-283-102007-02-01
Vision Based Tactile Sensor Using Transparent Elastic Fingertip for Dexterous Handling Goro Obinata Ashish Dutta Norinao Watanabe Nobuhiko Moriyama Mobile Robots: Perception & Navigation We have explained on a new tactile sensor for measuring multi-dimensional force and moment of contact. The structure of sensor is simple because the method is vision-based. The method to obtain the values of force and moment has been confirmed by several experiments. It is shown that the accurate estimation of contact force and moment is possible with the proposed sensor although there is a trade-off between the resolution and the computational time. There exist small interpositions between the tangential force, the moment and the normal force while measuring. Clear understanding the interposition between applied forces and moments will be required in further research. We defined the stick ratio as an index for indicating the degree of slippage. We have also proposed a new method to estimate the stick ratio for preventing from slippage of manipulated object. The exact relation of the defined stick ratio or the estimated stick ratio to the exact friction coefficient is an important problem to be solved. We demonstrated the control system for keeping the estimated stick ratio around a set point. Moreover, we have given a comparison with a piezoelectric sensor because it may be another candidate to cope with several practical requirements. The purpose-built integrated circuit for the image processing of this vision-based sensor may be required to achieve high speed control against disturbances in high frequency band. It is shown that the proposed sensor has the potential for dexterous handling like human. InTech 2007-02-01 7 http://www.intechopen.com/articles/show/title/vision_based_tactile_sensor_using_transparent_elastic_fingertip_for_dexterous_handling en ISBN:3-86611-283-1 http://www.intechopen.com/download/pdf/pdfs_id/135
oai:intechopen.com:136 2007-02-01 3-86611-283-102007-02-01
Accurate Color Classification and Segmentation for Mobile Robots Raziel Alvarez Erik Millan Alejandro Aceves-Lopez Ricardo Swain-Oropeza Mobile Robots: Perception & Navigation The presented color classification technique shows a good approximation for color subspaces without the need of transforming the color signal of pixels. The produced implicit surface binds tightly the cloud of color samples, reducing possible overlapping problems with other color classes. The use of a look-up table was an efficient method that allows the classification of a single pixel with a single lookup on a 3D array. In addition, evaluation of this algorithm under varying lighting conditions showed a better color classification than that produced by other color classification methods. The main reason behind this benefit is the tight approximation of the color class to the cloud of InTech 2007-02-01 8 http://www.intechopen.com/articles/show/title/accurate_color_classification_and_segmentation_for_mobile_robots en ISBN:3-86611-283-1 http://www.intechopen.com/download/pdf/pdfs_id/136
oai:intechopen.com:137 2007-02-01 3-86611-283-102007-02-01
Intelligent Global Vision for Teams of Mobile Robots Jacky Baltes John Anderson Mobile Robots: Perception & Navigation This chapter has reviewed some of the issues involved in creating pragmatic global vision systems. We have discussed the assumptions on which traditional systems are based, pointed out how these differ with the observed abilities of human vision, and described how these assumptions limit the applicability and generality of existing systems. We then described techniques that allow some of these assumptions to be discarded, and the embodiment of these techniques in our production global vision systems, Doraemon and Ergo. Both Doraemon and Ergo are used in a number of ways. Doraemon has been in use every year by a number of teams from around the world in the F-180 (small-size) league at RoboCup. Ergo is the current global vision system in use in our own laboratories, and is currently being employed in a number of projects, such as imitation learning in groups of robots (Allen, 2007). We have also described some of our recent work toward creating much more general global vision systems that take advantage of additional knowledge or adaptability in order to avoid the need for any type of predefined markings on objects. The latter work is very preliminary, but shows the potential for improved techniques to eventually be the basis for more general vision systems. In working toward such generality today, there are a number of very important areas of immediate future work. Existing approaches to global vision are well-understood and immediately deployable. The fact that they rely heavily on elements such as the ability to recognize colour patches, for example, means that anything that can be done to improve these abilities will serve to improve existing systems. While systems such as Doraemon are already exploiting much in terms of maximizing flexibility while still assuming colours can be defined and matched, future work may still improve this further. Any small steps that can be performed to wean existing systems away from their traditional assumptions will serve as a backbone for further future work. While Ergo is a significant improvement over the abilities of Doraemon, for example, it still conforms to some traditional assumptions in terms of relying on predefined patterns, and instead exploits different mechanisms to be more flexible and offer a better performance in a wider array of domains. There will be many similar steps as we move to more general vision systems. Any single tracking or identification technique has its limitations, and just as neither Ergo nor Doraemon use a single mechanism to identify and track objects, future systems will require a synergy of techniques. Attempting to leverage the strengths of techniques off of one another will always be an important part of future work in this area. In our own work, we are currently attempting to employ the addition of control knowledge to the subsymbolic orientation recognition described in Section 4.2. For example, if we are uncertain of a robot's location and orientation at the current time, we can start with the robot's last known location/orientation at previous time, and constrain the potential solution set by the likely outcome of the most recent command sent to the robot. The iterative steps taken in improving global vision are in turn a useful source of future work in improving application areas as well. For example, the work on recognizing orientation without markers described in Section 4.2 was undertaken as convenient subproblem of the overall vision task useful in robotic soccer, in order to track a teamâ€™s own players for control purposes. The ability to infer robots' orientation without prior InTech 2007-02-01 9 http://www.intechopen.com/articles/show/title/intelligent_global_vision_for_teams_of_mobile_robots en ISBN:3-86611-283-1 http://www.intechopen.com/download/pdf/pdfs_id/137
oai:intechopen.com:138 2007-02-01 3-86611-283-102007-02-01
Contour Extraction and Compression-Selected Topics Andrzej Dziech Mobile Robots: Perception & Navigation 1 InTech 2007-02-01 10 http://www.intechopen.com/articles/show/title/contour_extraction_and_compression-selected_topics en ISBN:3-86611-283-1 http://www.intechopen.com/download/pdf/pdfs_id/138
oai:intechopen.com:139 2007-02-01 3-86611-283-102007-02-01
Comparative Analysis of Mobile Robot Localization Methods Based on Proprioceptive and Exteroceptive Sensors Gianluca Ippoliti Leopoldo Jetto Sauro Longhi Andrea Monteriu Mobile Robots: Perception & Navigation 1 InTech 2007-02-01 11 http://www.intechopen.com/articles/show/title/comparative_analysis_of_mobile_robot_localization_methods_based_on_proprioceptive_and_exteroceptive_ en ISBN:3-86611-283-1 http://www.intechopen.com/download/pdf/pdfs_id/139
oai:intechopen.com:140 2007-02-01 3-86611-283-102007-02-01
Composite Models for Mobile Robot Offline Path Planning Ellips Masehian M. R. Amin-Naseri Mobile Robots: Perception & Navigation This chapter introduces two new offline path planning models which are based on the Roadmap and Potential Fields classic motion planning approaches. It is shown that how some relatively old methods can combine and yield new models. The first path planning model is established based on two traditional methods: the Voronoi Diagrams and Potential Fields, and so is called V-P Hybrid model. The model integrates the advantages of Voronoi diagram's safest distance and Potential Fields' search simplicity properties. After constructing the Generalized Voronoi Graph roadmap for the workspace, it is reduced to the Pruned Generalized Voronoi Graph (PGVG) through a pruning procedure. The PGVG decreases the search time effectively. An attractive potential is then applied to the resulting roadmap, which yields a new version of Potential Fields method, since it implicitly models the obstacles by attractive potentials rather than repulsive ones. The search technique developed for finding the trajectory is a bidirectional steepest descent ? mildest ascent stage-by-stage method, which is complete, and performs much faster than the classical Potential Fields or Dijkstra's methods. InTech 2007-02-01 12 http://www.intechopen.com/articles/show/title/composite_models_for_mobile_robot_offline_path_planning en ISBN:3-86611-283-1 http://www.intechopen.com/download/pdf/pdfs_id/140
oai:intechopen.com:141 2007-02-01 3-86611-283-102007-02-01
Global Navigation of Assistant Robots using Partially Observable Markov Decision Processes Maria Elena Lopez Rafael Barea Luis Miguel Bergasa Manuel Ocana Maria Soledad Escudero Mobile Robots: Perception & Navigation The proposed navigation system, based on a topological representation of the world, allows the robot to robustly navigate in corridor and structured environments. This is a very practical issue in assistance applications, in which robots must perform guidance missions from room to room in environments typically structured in corridors and rooms, such as hospitals or nursing homes. Although the topological map consists of very simple and reduced information about the environment, a set of robust local navigation behaviors (the actions of the model) allow the robot to locally move in corridors, reacting to sensor information and avoiding collisions, without any previous metric information. Another important subject in robot navigation is robustness in dynamic environments. It is demonstrated that topological representations are more robust to dynamic changes of the environment (people, obstacles, doors state, etc.) because they are not modelled in the map. In this case, in which local navigation is also based on an extracted local model of the corridor, the system is quite robust to people traversing the corridor. People are another source of uncertainty in actions and observations, which is successfully treated by the probabilistic transition and observation models. Regarding doors state, the learning module adapts the probabilities to its real state, making the system more robust to this dynamic aspect of the environment. In order to improve the navigation capabilities of the proposed system, we are working on several future work lines. The first one is to enlarge the action and observation sets to navigate in more complex or generic environments. For example, to traverse large halls or unstructured areas, a "wall-following" or "trajectory-following" action would be useful. Besides, we are also working on the incorporation of new observations from new sensors, such as a compass (to discriminate the four orientations of the graph) and a wireless signal strength sensor. Enlarging the model doesn't affect the proposed global navigation algorithms. Regarding the learning system, future work is focused on automatically learning the POMDP structure from real data, making even easier the installation process. Another current research lines are the extension of localization, planning and learning probabilistic algorithms to multi-robot cooperative systems (SIMCA project) and the use of hierarchical topological models to expand the navigation system to larger structured environments. InTech 2007-02-01 13 http://www.intechopen.com/articles/show/title/global_navigation_of_assistant_robots_using_partially_observable_markov_decision_processes en ISBN:3-86611-283-1 http://www.intechopen.com/download/pdf/pdfs_id/141
oai:intechopen.com:142 2007-02-01 3-86611-283-102007-02-01
Robust Autonomous Navigation and World Representation in Outdoor Environments Favio Masson Juan Nieto Jose Guivant Eduardo Nebot Mobile Robots: Perception & Navigation A solution to the SLAM problem is necessary to make a robot truly autonomous. For this reason, SLAM has been one of the main research topics in robotics, especially during the last fifteen years. While the structure of the problem is today well known, there are still many open problems, particularly when working in outdoor environments. We presented here some of the latest SLAM algorithms that address the problem of localisation and mapping in large outdoor areas. InTech 2007-02-01 14 http://www.intechopen.com/articles/show/title/robust_autonomous_navigation_and_world_representation_in_outdoor_environments en ISBN:3-86611-283-1 http://www.intechopen.com/download/pdf/pdfs_id/142
oai:intechopen.com:143 2007-02-01 3-86611-283-102007-02-01
Unified Dynamics-based Motion Planning Algorithm for Autonomous Underwater Vehicle-Manipulator Systems (UVMS) Tarun K. Podder Nilanjan Sarkar Mobile Robots: Perception & Navigation We have proposed a new unified dynamics-based motion planning algorithm that can generate both kinematically admissible and dynamically feasible joint-space trajectories for systems composed of heterogeneous dynamics. We have then extended this algorithm for an autonomous underwater vehicle-manipulator system, where the dynamic response of the vehicle is much slower than that of the manipulator. We have also exploited the kinemetic redundancy to accommodate the thruster/actuator faults and saturation and also to minimize hydrodynamic drag. We have incorporated thruster dynamics when modeling the UVMS. Although, some researchers have exploited kinematic redundancy for optimizing various criteria, but those work have mainly addressed to problems with land-based robotics or space-robotics. Hardly any motion planning algorithm has been developed for autonomous underwater vehiclemanipulator system. In this research, work we have formulated a new unified motion planning algorithm for a heterogeneous underwater robotic system that has a vastly different dynamic bandwidth. The results from computer simulation demonstrate the effectiveness of the proposed method. It shows that the proposed algorithm not only improves the trajectory tracking performance but also significantly reduce the energy consumption and the power requirements for the operation of an autonomous UVMS. We have not presented results from Case II (Total Decomposition) because of the length of the paper. However, these results are comparable to the conventional motion planning approach. In future, instead of Fourier decomposition, one can try to use wavelet approach to decompose the task-space trajectory into system's sub-component compatible segments. There are a few drawbacks of this paper as well. We used a model-based control technique to evaluate our planning algorithm. However, the underwater environment is uncertain and we need to use adaptive control techniques in future. Although the fault-tolerant control algorithm has been experimentally verified, the other proposed algorithms need to be validated by experiments. InTech 2007-02-01 15 http://www.intechopen.com/articles/show/title/unified_dynamics-based_motion_planning_algorithm_for_autonomous_underwater_vehicle-manipulator_syste en ISBN:3-86611-283-1 http://www.intechopen.com/download/pdf/pdfs_id/143
oai:intechopen.com:144 2007-02-01 3-86611-283-102007-02-01
Optimal Velocity Planning of Wheeled Mobile Robots on Specific Paths in Static and Dynamic Environments Maria Prado Mobile Robots: Perception & Navigation A method to compute velocity, acceleration and deceleration upper boundary functions for WMRs is described in this chapter. These functions confine the operating variables into safety regions in order to generate trajectories that are feasible, safe and with low tracking errors. The method first deals with issues related to the performances of steering, tractive and braking subsystems of wheeled robots, as well as mechanical properties of wheelground contact. Next, the motion capabilities of the robot's guide point are calculated as functions of the previous results, attending to the kinematics and dynamics of the complete robot system. Operational constraints caused by the need for fitting and synchronising the robot's motion with its environment are also defined. The upper limits for velocity based on robot dynamics are fixed not only to avoid total vehicle slippage, as was previously done by other authors, but also to bound the spatial and temporal errors of a trajectory in which the space path generator and the trajectory tracker work under the kinematic problem solution. The definition of these boundary functions depends on either simulation outcomes of a sufficiently accurate dynamic model of the WMR, as complex as needed since it works offline, or on an appropriate number of experimental tests. Topics involving navigation over 3D terrains and vehicles with very high velocities, such as the presence of ground irregularities, transients for non-stationary manoeuvres, aerodynamic effects, gyroscope torques, etc., are not dealt with in this chapter, though they should be taken into account for robots used in tasks such as outdoor exploration or vehicles developed to run on roads without a driver. The resulting bounds are included in an algorithm to plan time optimal velocity profiles for a WMR on specific paths. Dealing with PP and VP simultaneously may make it possible to plan faster trajectories in some situations, but such methodologies involve more complex algorithms where it is very difficult to include a significant number of velocity and acceleration constraints that include nonintegrable functions. The velocity planner proposed in this chapter is able to generate a trajectory with favorable tracking conditions, since: -It confines the velocity and its first derivative into safety zones limited by functions that can consider any velocity, acceleration and deceleration constraint which can be expressed as a InTech 2007-02-01 16 http://www.intechopen.com/articles/show/title/optimal_velocity_planning_of_wheeled_mobile_robots_on_specific_paths_in_static_and_dynamic_environme en ISBN:3-86611-283-1 http://www.intechopen.com/download/pdf/pdfs_id/144
oai:intechopen.com:145 2007-02-01 3-86611-283-102007-02-01
Autonomous Navigation of Indoor Mobile Robot Using Global Ultrasonic System Soo-Yeong Yi Byoung-Wook Choi Mobile Robots: Perception & Navigation In this chapter, the global ultrasonic system with an EKF algorithm is presented for the selflocalization of an indoor mobile robot. Also, the performance of the autonomous navigation based on the self-localization system is thus verified through various experiments. The global ultrasonic system consists of four or more ultrasonic generators fixed at known positions in the workspace, two receivers mounted on the mobile robot, and RF modules added to the ultrasonic sensors. By controlling the ultrasonic signal generation through the RF channel, the robot can synchronize and measure the distance between the ultrasonic generators and receivers, thereby estimating its own position and heading angle. It is shown InTech 2007-02-01 17 http://www.intechopen.com/articles/show/title/autonomous_navigation_of_indoor_mobile_robot_using_global_ultrasonic_system en ISBN:3-86611-283-1 http://www.intechopen.com/download/pdf/pdfs_id/145
oai:intechopen.com:146 2007-02-01 3-86611-283-102007-02-01
Distance Feedback Travel Aid Haptic Display Design Hideyasu Sumiya Mobile Robots: Perception & Navigation This chapter aims at the user-friendly ETA design. As a preliminary information, several tactile characteristics including sensing range, sensitivity, dynamic factors are introduced, which are critical to design tactile/haptic device. In the latter half of this chapter, an example model of recent ETA design is introduced along the user-friendly real-time operation. Current ETA system are still on the process to gives satisfactory level of environmental reconstruction for user. Even under restriction of tactile charcterists, this design concept will give some hint to create new device to activate human's sensitivity. (e.g. magnification of sensing resolution, extending human sense). Recent studies of sensory substitution system has another aspect to extend human original sense. These approach would be called as `Hyper sense'. Currently, the most popular user of ETA is the visually impaired. But this applicable area is more extensive. ETA technique will take the certain role in `Hyper Sense' technique. InTech 2007-02-01 18 http://www.intechopen.com/articles/show/title/distance_feedback_travel_aid_haptic_display_design en ISBN:3-86611-283-1 http://www.intechopen.com/download/pdf/pdfs_id/146
oai:intechopen.com:147 2007-02-01 3-86611-283-102007-02-01
Efficient Data Association Approach to Simultaneous Localization and Map Building Sen Zhang Lihua Xie Martin David Adams Mobile Robots: Perception & Navigation This chapter presented a data association algorithm for SLAM which offers a good trade-off between accuracy and computational requirements. We first formulated the data association problem in SLAM as a two dimensional assignment problem. In our work, only 1 frame of scan data is considered. The data association problem in SLAM is formulated as a two dimensional assignment problem rather than a three dimensional one which is an NP hard problem and is computationally more efficient. Further, since only one step prediction is involved, the effect of the vehicle model uncertainty is smaller as compared to the data association methods using two frame scan data. In order to obtain a fast solution, the 0-1 IP problem was firstly relaxed to an LP problem. Then we proposed to use the IHGR procedure in conjunction with basic LP algorithms to obtain a feasible solution of the data association problem. Both the simulation and experiment results demonstrated that the proposed algorithm is implementable and gives a better performance (higher successful rate) than the commonly used NN algorithm for complex (outdoor) environments with high density of features. Compared to the optimal JCBB algorithm, the proposed algorithm has lower computational complexity and is more suitable for real-time implementation. InTech 2007-02-01 19 http://www.intechopen.com/articles/show/title/efficient_data_association_approach_to_simultaneous_localization_and_map_building en ISBN:3-86611-283-1 http://www.intechopen.com/download/pdf/pdfs_id/147
oai:intechopen.com:148 2007-02-01 3-86611-283-102007-02-01
A Generalized Robot Path Planning Approach Without The Cspace Calculation Yongji Wang Matthew Cartmell QingWang Qiuming Tao Mobile Robots: Perception & Navigation InTech 2007-02-01 20 http://www.intechopen.com/articles/show/title/a_generalized_robot_path_planning_approach_without_the_cspace_calculation en ISBN:3-86611-283-1 http://www.intechopen.com/download/pdf/pdfs_id/148
oai:intechopen.com:149 2007-02-01 3-86611-283-102007-02-01
A Pursuit-Rendezvous Approach for Robotic Tracking Fethi Belkhouche Boumediene Belkhouche Mobile Robots: Perception & Navigation We presented a method for robotic navigation and tracking of an unpredictably moving object. Our method is kinematics-based, and combines the pursuit law with the rendezvous law. First a kinematics model is derived. This kinematics model gives the motion of the goal with respect to the robot. The first equation gives the range rate between the robot and its goal. The second equation gives the turning rate of the goal with respect to the robot. The control law is then derived based on this kinematics model. This law is controlled by a real variable, which may be constant or time-varying. The most important properties of the control law are discussed. The dynamic coverage of the target is also discussed, where a second law for the robot's linear velocities is derived. InTech 2007-02-01 21 http://www.intechopen.com/articles/show/title/a_pursuit-rendezvous_approach_for_robotic_tracking en ISBN:3-86611-283-1 http://www.intechopen.com/download/pdf/pdfs_id/149
oai:intechopen.com:150 2007-02-01 3-86611-283-102007-02-01
Sensor-based Global Planning for Mobile Manipulators Navigation Using Voronoi Diagram and Fast Marching S. Garrido D. Blanco M.L. Munoz L. Moreno M. Abderrahim Mobile Robots: Perception & Navigation We present here a discussion regarding alternative planning approaches, the limitations of the proposed method, and the potential effect on mobile robot's control architecture. 8.1. Comparison with existing methods The common limitation of all the reactive navigation methods analyzed in this section is that they cannot guarantee global convergence to the goal location, because they use only a fraction of the information available (the local sensory information). Some researchers have worked on introducing global information into the reactive collision avoidance methods to avoid local traps situations. This approach has been adopted in (Ulrich & Borenstein, 2000) which utilizes a look-ahead verification in order to analyze the consequences of a given motion a few steps ahead avoiding trap situations. Other authors exploit the information about global environment connectivity to avoid trap situations (Minguez & Montano, 2001). Such solutions still maintain the classical twolevel approach, and require additional complexity at the obstacle avoidance level to improve the reliability. InTech 2007-02-01 22 http://www.intechopen.com/articles/show/title/sensor-based_global_planning_for_mobile_manipulators_navigation_using_voronoi_diagram_and_fast_march en ISBN:3-86611-283-1 http://www.intechopen.com/download/pdf/pdfs_id/150
oai:intechopen.com:151 2007-02-01 3-86611-283-102007-02-01
Effective Method for Autonomous Simultaneous Localization and Map Building in Unknown Indoor Environments Y.L. Ip A.B. Rad Y.K. Wong Mobile Robots: Perception & Navigation In this chapter, a new autonomous exploration strategy for mobile robot was presented and extensively tested via simulation and experimental trials. The essential mechanisms used included a HFFS reactive navigation scheme, EAFC map extraction algorithm, SLAM process, an open space evaluation system cooperating with probability theory and Bayesian update rule and a novel navigation point generation system. The proposed autonomous exploration algorithm is a version of combination of a robust reactive navigation scheme and approaching the unknown strategy which ensure that the mobile robot to explore the entire region in an unknown environment automatically. InTech 2007-02-01 23 http://www.intechopen.com/articles/show/title/effective_method_for_autonomous_simultaneous_localization_and_map_building_in_unknown_indoor_environ en ISBN:3-86611-283-1 http://www.intechopen.com/download/pdf/pdfs_id/151
oai:intechopen.com:152 2007-02-01 3-86611-283-102007-02-01
Motion Planning and Reconfiguration for Systems of Multiple Objects Adrian Dumitrescu Mobile Robots: Perception & Navigation The different reconfiguration models discussed in this survey have raised new interesting mathematical questions and revealed surprising connections with other older ones. For instance the key ideas in the reconfiguration algorithm in [18] were derived from the properties of a system of maximal cycles, similar to those of the block decomposition of graphs [16]. The lower bound configuration with unit disks for the sliding model in [5] uses "rigidity" considerations and properties of stable packings of disks studied a long time ago by B?r?czky [7]; in particular, he showed that there exist stable systems of unit disks with arbitrarily small density. A suitable modification of his construction yields our lower bound. The study of the lifting model offered other interesting connections: the algorithm for unit disks given in [6] is intimately related to the notion of center point of a finite point set, and to the following fact derived from it: Given two sets each with n pairwise disjoint unit disks, there exists a binary space partition of the plane into polygonal regions each containing of disks and such that the total number of disks roughly the same small number InTech 2007-02-01 24 http://www.intechopen.com/articles/show/title/motion_planning_and_reconfiguration_for_systems_of_multiple_objects en ISBN:3-86611-283-1 http://www.intechopen.com/download/pdf/pdfs_id/152
oai:intechopen.com:153 2007-02-01 3-86611-283-102007-02-01
Symbolic Trajectory Description in Mobile Robotics Pradel Gilbert Caleanu Catalin Daniel Mobile Robots: Perception & Navigation InTech 2007-02-01 25 http://www.intechopen.com/articles/show/title/symbolic_trajectory_description_in_mobile_robotics en ISBN:3-86611-283-1 http://www.intechopen.com/download/pdf/pdfs_id/153
oai:intechopen.com:154 2007-02-01 3-86611-283-102007-02-01
Robot Mapping and Navigation by Fusing Sensory Information Maki K. Habib Mobile Robots: Perception & Navigation This chapter presented the state of the art, the complexity, and the challenges facing simultaneous and real-time mapping, obstacle avoidance, and dynamic navigation for mobile robots. The development of an autonomous map building and maintenance method with focus on incremental map building technique that is suitable for real-time obstacle detection and avoidance has been presented. The chapter introduced a modified histogram grid based navigation techniques that is integrated with the concept of vector field histogram to support real-time obstacle avoidance in parallel with the incremental map building. Through the integrated implementation, the mobile robot was able to map the environment, avoid obstacles and move towards its target successfully. The results are important for simultaneous localization and map building applications, and can facilitate the use of additional natural landmarks to improve the accuracy of the localization algorithm. 5.1 Future work The future expansion can include the following: 1. As the grid based mapping in general and the histogram grids require fixed-size environment, it is important to consider a technique that helps to deal with dynamic size of robot's environment, i.e. building variable-sized maps without imposing size or shape constraints on the grid map. Dynamically expanding occupancy grids seek to remove dependency on an array for representing a histogram or occupancy grid. Dynamically expanding occupancy grids tackle the issues related to the efficient use of available memory and the requirements for real time searching and actions. Such techniques help to increase the size of map dynamically when new area is detected. 2. Integrate heterogeneous sensor modules, such as ultrasonic range data and an InTech 2007-02-01 26 http://www.intechopen.com/articles/show/title/robot_mapping_and_navigation_by_fusing_sensory_information en ISBN:3-86611-283-1 http://www.intechopen.com/download/pdf/pdfs_id/154
oai:intechopen.com:155 2007-02-01 3-86611-283-102007-02-01
Intelligent Control of AC Induction Motors Hosein Marzi Mobile Robots: Perception & Navigation The simulation consists of four main components, the fuzzy controller, AC motor, the cart and the inverted pendulum, Figure 5. The cart passes the fuzzy controller four parameters , , X, V. Based on these four parameters the fuzzy controller outputs a voltage to the motor. The motor in turn calculates the force that will be exerted on the cart. The system then calculates the new values for parameters , , X, V and the cycle will be repeated. InTech 2007-02-01 27 http://www.intechopen.com/articles/show/title/intelligent_control_of_ac_induction_motors en ISBN:3-86611-283-1 http://www.intechopen.com/download/pdf/pdfs_id/155
oai:intechopen.com:156 2007-02-01 3-86611-283-102007-02-01
Optimal Path Planning of Multiple Mobile Robots for Sample Collection on a Planetary Surface J.C. Cardema P.K.C. Wang Mobile Robots: Perception & Navigation In this work, we gave mathematical formulations of the sample collection problem for single and multiple robots as optimization problems. These problems are more complex than the well-known NP-hard Traveling Salesman Problem. In order to gain some insight on the nature of the solutions, algorithms are developed for solving simplified versions of these problems. This study has been devoted to centralized operation. If communication between the rovers is considered, as in autonomous operation, the nature of the result will be different. The problem posed here is simplified to facilitate mathematical formulation. To determine whether the strategies and algorithms discussed in this paper InTech 2007-02-01 28 http://www.intechopen.com/articles/show/title/optimal_path_planning_of_multiple_mobile_robots_for_sample_collection_on_a_planetary_surface en ISBN:3-86611-283-1 http://www.intechopen.com/download/pdf/pdfs_id/156
oai:intechopen.com:157 2007-02-01 3-86611-283-102007-02-01
Multi Robotic Conflict Resolution by Cooperative Velocity and Direction Control Satish Pedduri K. Madhava Krishna Mobile Robots: Perception & Navigation A method by which the velocity and orientation axis of the robot can be dissected into various portions and these portions labeled as conflict free or conflicting with a particular set of robots, unreachable and reachable is presented. The conflict free intervals along the axis that are also represent the solution space for the robot. When the entire reachable space is conflicting with one or more robots it points to the need for cooperation between robots. For a pair of robots that are in conflict with one another and either of them unable to resolve the conflict individually plot of the joint solution space demarcates area where cooperative change of velocities or directions can result in collision freeness. For a pair of robots the entire solution space need not be searched, if a solution is not possible at the corners of the rectangular portions demarcated there is no possibility to resolve the conflict by mutual cooperation. Often a velocity or direction control strategy that solves a conflict with one robot results in conflict with others there by bringing in more robots into the resolution scheme. In such situations the space to be searched for finding a solution increases exponentially. However a method by which requests are passed between robots to resolve the conflicts drastically reduces the space to be searched. We call this as a three-tiered strategy of individual, mutual and tertiary levels. Simulation results confirm the efficacy of the method. Existential and inevitable nature of cooperation is also presented and analyzed in detail InTech 2007-02-01 29 http://www.intechopen.com/articles/show/title/multi_robotic_conflict_resolution_by_cooperative_velocity_and_direction_control en ISBN:3-86611-283-1 http://www.intechopen.com/download/pdf/pdfs_id/157
oai:intechopen.com:158 2007-02-01 3-86611-283-102007-02-01
Robot Collaboration for Simultaneous Map Building and Localization M. Oussalah D. Wilson Mobile Robots: Perception & Navigation This chapter investigated the state of the art of SLAM system whose aim is to simultaneously map the environment and provide accurate positioning of the vehicle where the state of both vehicle and landmarks are brought into a single estimation process. The estimation process supplies estimation of vehicle and landmarks in terms of mean and variance-covariance estimate of the state vector conditional on the whole set of measurements. The construction of the map involves appropriate initialization step in which some prior knowledge regarding the environment is reported, which allows us to ensure geometrical validation test later on, and an alignment stage in which the observations are turned into landmark Cartesian coordinates. Next, a data association stage is required to map the observations to the already identified landmark or initiate new landmarks. For this purpose, one uses Mahanalobis distance to match the observation to possible landmarks. If none of the landmarks matches the current observation and both the geometrical and statistical tests were positive, then a new landmark is initiated and the state vector is therefore augmented. Note that, in order to balance the cost effectiveness and optimality requirement, the reasoning is carried out only within a submap of the environment, where it is most likely to find the matching given the sensor limitations. At later stage, the obtained landmarks are also used to extract feature landmark consisting of segments and corners. The methodology has been validated in a platform using two Khepera robots, one of which is equipped with vision turret while both are equipped with range infrared sensors and encoders. A virtual interface showing the robot trajectory as well as environment is developed using OpenGL platform for 3D visualization. The use of both robots also allowed us to test and validate collaboration scenarios in which multi-robot localization technique is used in conjunction with SLAM algorithm. The tests carried out demonstrated the validation of the developed algorithm and the consistency of the outcomes when looking at the 95% confidence bound limits. This open a new area of research where more advanced collaboration scenarios can be used in more complex environments where the features can be constituted of either geometrical or non-geometrical features. On the other hand, inspired by the overall intelligent behaviour of large biological insect communities, together with the rapid development of the field of distributed artificial intelligence, through, for instance, the concrete RoboCup robot soccer initiative, this offers new motivation grounds for further developments of multiple robot systems at different research communities. InTech 2007-02-01 30 http://www.intechopen.com/articles/show/title/robot_collaboration_for_simultaneous_map_building_and_localization en ISBN:3-86611-283-1 http://www.intechopen.com/download/pdf/pdfs_id/158
oai:intechopen.com:4204 2007-03-01 01729-88062007-03-01
Guest Editorial Kerstin Dautenhahn Chrystopher L. Nehaniv International Journal of Advanced Robotic Systems Volume 4 InTech 2007-03-01 18 http://www.intechopen.com/articles/show/title/guest_editorial_vol4_num1_international_journal_of_advanced_robotic_systems en ISSN:1729-8806 http://www.intechopen.com/download/pdf/pdfs_id/4204
oai:intechopen.com:4205 2007-03-01 01729-88062007-03-01
Operator Engagement Detection for Robot Behavior Adaptation Pramila Rani Nilanjan Sarkar International Journal of Advanced Robotic Systems Volume 4 It has been shown that in human-robot interaction, the effectiveness of a robot varies inversely with the operator engagement in the task. Given the importance of maintaining optimal task engagement when working with a robot, it would be immensely useful to have a robotic system that can detect the level of operator engagement and modify its behavior if required. This paper presents a framework for human-robot interaction that allows inference of operator?s engagement level through the analysis of his/her physiological signals, and adaptation of robot behavior as a function of the operator?s engagement level. Peripheral physiological signals were measured through wearable biofeedback sensors and a control architecture inspired by Riley?s original information-flow model was developed to implement such human-robot interaction. The results from affect- elicitation tasks for human participants showed that it was possible to detect engagement through physiological sensing in real-time. An open-loop teleoperation-based robotic experiment was also conducted where the recorded physiological signals were transmitted to the robot in real-time speed to demonstrate that the presented control architecture allowed the robot to adapt its behavior based on operator engagement level. InTech 2007-03-01 1 http://www.intechopen.com/articles/show/title/operator_engagement_detection_for_robot_behavior_adaptation en ISSN:1729-8806 http://www.intechopen.com/download/pdf/pdfs_id/4205
oai:intechopen.com:4206 2007-03-01 01729-88062007-03-01
Optical Flow based Robot Obstacle Avoidance Kahlouche Souhila Achour Karim International Journal of Advanced Robotic Systems Volume 4 In this paper we try to develop an algorithm for visual obstacle avoidance of autonomous mobile robot. The input of the algorithm is an image sequence grabbed by an embedded camera on the B21r robot in motion. Then, the optical flow information is extracted from the image sequence in order to be used in the navigation algorithm. The optical flow provides very important information about the robot environment, like: the obstacles disposition, the robot heading, the time to collision and the depth. The strategy consists in balancing the amount of left and right side flow to avoid obstacles, this technique allows robot navigation without any collision with obstacles. The robustness of the algorithm will be showed by some examples. InTech 2007-03-01 2 http://www.intechopen.com/articles/show/title/optical_flow_based_robot_obstacle_avoidance en ISSN:1729-8806 http://www.intechopen.com/download/pdf/pdfs_id/4206
oai:intechopen.com:4207 2007-03-01 01729-88062007-03-01
Path Planning of Free-Floating Robot in Cartesian Space Using Direct Kinematics Wenfu Xu Bin Liang Cheng Li Yangsheng Xu Wenyi Qiang International Journal of Advanced Robotic Systems Volume 4 Dynamic singularities make it difficult to plan the Cartesian path of freefloating robot. In order to avoid its effect, the direct kinematic equations are used for path planning in the paper. Here, the joint position, rate and acceleration are bounded. Firstly, the joint trajectories are parameterized by polynomial or sinusoidal functions. And the two parametric functions are compared in details. It is the first contribution of the paper that polynomial functions can be used when the joint angles are limited(In the similar work of other researchers, only sinusoidla functions could be used). Secondly, the joint functions are normalized and the system of equations about the parameters is established by integrating the differential kinematics equations. Normalization is another contribution of the paper. After normalization, the boundary of the parameters is determined beforehand, and the general criterion to assign the initial guess of the unknown parameters is supplied. The criterion is independent on the planning conditions such as the total time tf. Finally, the parametes are solved by the iterative Newtonian method. Modification of tf may not result in the recalculation of the parameters. Simulation results verify the path planning method. InTech 2007-03-01 4 http://www.intechopen.com/articles/show/title/path_planning_of_free-floating_robot_in_cartesian_space_using_direct_kinematics en ISSN:1729-8806 http://www.intechopen.com/download/pdf/pdfs_id/4207
oai:intechopen.com:4208 2007-03-01 01729-88062007-03-01
Development and Control of Compliant Hybrid Joints for Human-Symbiotic Mobile Manipulators Zhijun Li Jun Luo Ning Xi Aiguo Ming International Journal of Advanced Robotic Systems Volume 4 In this paper, we develop a robot with the ability to secure human safety in humanrobot collisions arising in our living and working environments. The humansymbiotic service robot using compliant hybrid joints realizes human safety, absorbs impact force, and fulfills task. In unexpected or expected collisions with human, the arising impulse force is attenuated effectively by the proposed physical model. Owing to the displacement of the links, several recovery controls have been developed for the endeffector to maintain its desired task position after the collision. The force attenuation property has been verified through collision simulations and experiments in that the capability of the proposed passive arm in overcoming the limitations of active compliance control has been demonstrated. InTech 2007-03-01 3 http://www.intechopen.com/articles/show/title/development_and_control_of_compliant_hybrid_joints_for_human-symbiotic_mobile_manipulators en ISSN:1729-8806 http://www.intechopen.com/download/pdf/pdfs_id/4208
oai:intechopen.com:4209 2007-03-01 01729-88062007-03-01
Combined Intelligent Control (CIC): An Intelligent decision making algorithm Moteaal Asadi Shirzi M. R. Hairi Yazdi Caro Lucas International Journal of Advanced Robotic Systems Volume 4 The focus of this research is to introduce the concept of combined intelligent control (CIC) as an effective architecture for decision making and control of intelligent agents and multi robot sets. Basically, the CIC is a combination of various architectures and methods from fields such as artificial intelligence, Distributed Artificial Intelligence (DAI), control and biological computing. Although any intelligent architecture may be very effective for some specific applications, it could be less for others. Therefore, CIC combines and arranges them in a way that the strengths of any approach cover the weaknesses of others. In this paper first, we introduce some intelligent architectures from a new aspect. Afterward, we offer the CIC by combining them. CIC has been executed in a multi agent set. In this set, robots must cooperate to perform some various tasks in a complex and nondeterministic environment with a low sensory feedback and relationship. In order to investigate, improve, and correct the combined intelligent control method, simulation software has been designed which will be presented and considered. To show the ability of the CIC algorithm as a distributed architecture, a central algorithm is designed and compared with the CIC. InTech 2007-03-01 6 http://www.intechopen.com/articles/show/title/combined_intelligent_control__cic___an_intelligent_decision_making_algorithm en ISSN:1729-8806 http://www.intechopen.com/download/pdf/pdfs_id/4209
oai:intechopen.com:4210 2007-03-01 01729-88062007-03-01
A Novel Robot of Manufacturing Space Solar Cell Arrays Wu Yuexin Fu Zhuang Zhao Yanzheng Zhao Hui International Journal of Advanced Robotic Systems Volume 4 This paper presents a novel robot employed to manufacture space solar cell arrays. First of all including the mechanical configuration and control system, the architecture of the robot is described. Then the flow velocity field of adhesive in the dispensing needles is acquired based on hydrodynamics. The accurate section form model of adhesive dispensed on the solar cells is obtained, which is essential for the robot to control the uniformity of dispensing adhesive. Finally the experiment validates the feasibility and reliability of the robot system. The application of robots instead of manual work in manufacturing space solar cell arrays will enhance the development of space industry. InTech 2007-03-01 5 http://www.intechopen.com/articles/show/title/a_novel_robot_of_manufacturing_space_solar_cell_arrays en ISSN:1729-8806 http://www.intechopen.com/download/pdf/pdfs_id/4210
oai:intechopen.com:4211 2007-03-01 01729-88062007-03-01
3D Vision Based Landing Control of a Small Scale Autonomous Helicopter Zhenyu Yu Kenzo Nonami Jinok Shin Demian Celestino International Journal of Advanced Robotic Systems Volume 4 Autonomous landing is a challenging but important task for Unmanned Aerial Vehicles (UAV) to achieve high level of autonomy. The fundamental requirement for landing is the knowledge of the height above the ground, and a properly designed controller to govern the process. This paper presents our research results in the study of landing an autonomous helicopter. The abovetheground height sensing is based on a 3D vision system. We have designed a simple planefitting method for estimating the height over the ground. The method enables vibration free measurement with the camera rigidly attached on the helicopter without using complicated gimbal or active vision mechanism. The estimated height is used by the landing control loop. Considering the ground effect during landing, we have proposed a twostage landing procedure. Two controllers are designed for the two landing stages respectively. The sensing approach and control strategy has been verified in field flight test and has demonstrated satisfactory performance. InTech 2007-03-01 7 http://www.intechopen.com/articles/show/title/3d_vision_based_landing_control_of_a_small_scale_autonomous_helicopter en ISSN:1729-8806 http://www.intechopen.com/download/pdf/pdfs_id/4211
oai:intechopen.com:4212 2007-03-01 01729-88062007-03-01
Segmentation and Location Computation of Bin Objects C.R. Hema M.P. Paulraj R. Nagarajan Sazali Yaacob International Journal of Advanced Robotic Systems Volume 4 In this paper we present a stereo vision based system for segmentation and location computation of partially occluded objects in bin picking environments. Algorithms to segment partially occluded objects and to find the object location [midpoint,x, y and z coordinates] with respect to the bin area are proposed. The z co ordinate is computed using stereo images and neural networks. The proposed algorithms is tested using two neural network architectures namely the Radial Basis Function nets and Simple Feedforward nets. The training results fo feedforward nets are found to be more suitable for the current application.The proposed stereo vision system is interfaced with an Adept SCARA Robot to perform bin picking operations. The vision system is found to be effective for partially occluded objects, in the absence of albedo effects. The results are validated through real time bin picking experiments on the Adept Robot. InTech 2007-03-01 9 http://www.intechopen.com/articles/show/title/segmentation_and_location_computation_of_bin_objects en ISSN:1729-8806 http://www.intechopen.com/download/pdf/pdfs_id/4212
oai:intechopen.com:4213 2007-03-01 01729-88062007-03-01
New Jacobian Matrix and Equations of Motion for a 6 DOF Cable-driven Robot Ali Afshari Ali Meghdari International Journal of Advanced Robotic Systems Volume 4 In this paper, we introduce a new method and new motion variables to study kinematics and dynamics of a 6 d.o.f cabledriven robot. Using these new variables and Lagrange equations, we achieve new equations of motion which are different in appearance and several aspects from conventional equations usually used to study 6 d.o.f cable robots. Then, we introduce a new Jacobian matrix which expresses kinematical relations of the robot via a new approach and is basically different from the conventional Jacobian matrix. One of the important characteristics of the new method is computational efficiency in comparison with the conventional method. It is demonstrated that using the new method instead of the conventional one, significantly reduces the computation time required to determine workspace of the robot as well as the time required to solve the equations of motion. InTech 2007-03-01 8 http://www.intechopen.com/articles/show/title/new_jacobian_matrix_and_equations_of_motion_for_a_6_dof_cable-driven_robot en ISSN:1729-8806 http://www.intechopen.com/download/pdf/pdfs_id/4213
oai:intechopen.com:4214 2007-03-01 01729-88062007-03-01
Network Distributed Monitoring System Based on Robot Technology Middleware Songmin Jia Kunikatsu Takase International Journal of Advanced Robotic Systems Volume 4 In this paper, a network distributed monitoring system for human assistance robot system was developed to improve the interaction among the users and local service robotic system and enable a remote user to get a better understanding of what is going on in the local environment. Home integration robot system and network monitoring system using QuickCam Orbit cameras were developed and demonstrated from June 9 to June 19 at the 2005 World Exposition, Aichi, Japan. Improvements of network distributed monitoring system using IEEE1394 cameras with high performance and high resolution have been done in order to extend the application of system. Robot Technology Middleware (RTM) was used in the developed system. By using RTM, we can develop cameras functional elements as RT software components that can be implemented by different programming languages, run in different operating system, or connected in different networks to interoperate.It is also easy to create comprehensive robot system application by reusing existing modules thus facilitating networkdistributed software sharing and improving the cost of writing and maintaining software. InTech 2007-03-01 11 http://www.intechopen.com/articles/show/title/network_distributed_monitoring_system_based_on_robot_technology_middleware en ISSN:1729-8806 http://www.intechopen.com/download/pdf/pdfs_id/4214
oai:intechopen.com:4215 2007-03-01 01729-88062007-03-01
Simulation of Intelligent Single Wheel Mobile Robot Maki K. Rashid International Journal of Advanced Robotic Systems Volume 4 Stabilization of a single wheel mobile robot attracted researcher attentions in robotic area. However, the budget requirements for building experimental setups capable in investigating isolated parameters and implementing others encouraged the development of new simulation methods and techniques that beat such limitations. In this work we have developed a simulation platform for testing different control tactics to stabilize a single wheel mobile robot. The graphic representation of the robot, the dynamic solution, and, the control scheme are all integrated on common computer platform using Visual Basic. Simulation indicates that we can control such robot without knowing the detail of it's internal structure or dynamics behaviour just by looking at it and using manual operation tactics. Twenty five rules are extracted and implemented using Takagi-Sugeno's fuzzy controller with significant achievement in controlling robot motion during the dynamic simulation. The resulted data from the successful implementation of the fuzzy model are used to utilize and train a neurofuzzy controller using ANFIS scheme to produce further improvement in robot performance InTech 2007-03-01 10 http://www.intechopen.com/articles/show/title/simulation_of_intelligent_single_wheel_mobile_robot en ISSN:1729-8806 http://www.intechopen.com/download/pdf/pdfs_id/4215
oai:intechopen.com:4216 2007-03-01 01729-88062007-03-01
Environmental-Interaction Robotic Systems: Compliant Actuation Approach Reza Ghorbani Qiong Wu International Journal of Advanced Robotic Systems Volume 4 Many successful designs of compliant actuators have been recently proposed. However, the challenge of providing passive and active motion in one actuator has remained. In this paper, a novel mechanism for changing the stiffness of the series elastic actuator over a wide range is presented. An accurate force source is provided by introducing the force control using velocity control of the DC motor. Performance and behaviour of the system and controller is investigated through simulation. InTech 2007-03-01 12 http://www.intechopen.com/articles/show/title/environmental-interaction_robotic_systems__compliant_actuation_approach en ISSN:1729-8806 http://www.intechopen.com/download/pdf/pdfs_id/4216
oai:intechopen.com:4217 2007-03-01 01729-88062007-03-01
A Novel Action Selection Architecture in Soccer Simulation Environment Using Neuro-Fuzzy and Bidirectional Neural Networks Reza Zafarani Mohammad Reza Yazdchi International Journal of Advanced Robotic Systems Volume 4 MultiAgent systems have generated lots of excitement in recent years because of its promise as a new paradigm for conceptualizing, designing, and implementing software systems. One of the most important aspects of agent design in AI is the way agent acts or responds to the environment that the agent is acting upon. An effective action selection and behavioral method gives a powerful advantage in overall agent performance. We define a new method of action selection based on probability/priority models, we thereby introduce two efficient ways to determine probabilities using neurofuzzy systems and bidirectional neural networks and a new priority based system which maps the human knowledge to the action selection method. Furthermore, a behavior model is introduced to make the model more flexible. InTech 2007-03-01 13 http://www.intechopen.com/articles/show/title/a_novel_action_selection_architecture_in_soccer_simulation_environment_using_neuro-fuzzy_and_bidirec en ISSN:1729-8806 http://www.intechopen.com/download/pdf/pdfs_id/4217
oai:intechopen.com:4218 2007-03-01 01729-88062007-03-01
Methodology &amp; Themes of Human-Robot Interaction: A Growing Research Field Kerstin Dautenhahn International Journal of Advanced Robotic Systems Volume 4 This article discusses challenges of Human-Robot Interaction, which is a highly inter- and multidisciplinary area. Themes that are important in current research in this lively and growing field are identified and selected work relevant to these themes is discussed. InTech 2007-03-01 15 http://www.intechopen.com/articles/show/title/methodology__amp__themes_of_human-robot_interaction__a_growing_research_field en ISSN:1729-8806 http://www.intechopen.com/download/pdf/pdfs_id/4218
oai:intechopen.com:4219 2007-03-01 01729-88062007-03-01
Self-imitation and Environmental Scaffolding for Robot Teaching Joe Saunders Chrystopher L. Nehaniv Kerstin Dautenhahn Aris Alissandrakis International Journal of Advanced Robotic Systems Volume 4 Imitative learning and learning by observation are social mechanisms that allow a robot to acquire knowledge from a human or another robot. However to be able to obtain skills in this way the robot faces many complex issues, one of which is that of finding solutions to the correspondence problem. Evolutionary predecessors to observational imitation may have been self-imitation where an agent avoids the complexities of the correspondence problem by learning and replicating actions it has experienced through the manipulation of its body. We investigate how a robotic control and teaching system using self-imitation can be constructed with reference to psychological models of motor control and ideas from social scaffolding seen in animals. Within these scaffolded environments sets of competencies can be built by constructing hierarchical state/action memory maps of the robot's interaction within that environment. The scaffolding process provides a mechanism to enable learning to be scaled up. The resulting system allows a human trainer to teach a robot new skills and modify skills that the robot may possess. Additionally the system allows the robot to notify the trainer when it is being taught skills it already has in its repertoire and to direct and focus its attention and sensor resources to relevant parts of the skill being executed. We argue that these mechanisms may be a first step towards the transformation from self-imitation to observational imitation. The system is validated on a physical pioneer robot that is taught using self-imitation to track, follow and point to a patterned object. InTech 2007-03-01 14 http://www.intechopen.com/articles/show/title/self-imitation_and_environmental_scaffolding_for_robot_teaching en ISSN:1729-8806 http://www.intechopen.com/download/pdf/pdfs_id/4219
oai:intechopen.com:4220 2007-03-01 01729-88062007-03-01
Situated Dialogue and Spatial Organization: What, Where and Why? Geert-Jan M. Kruijff Hendrik Zender Patric Jensfelt Henrik I. Christensen International Journal of Advanced Robotic Systems Volume 4 The paper presents an HRI architecture for human-augmented mapping, which has been implemented and tested on an autonomous mobile robotic platform. Through interaction with a human, the robot can augment its autonomously acquired metric map with qualitative information about locations and objects in the environ- ment. The system implements various interaction strategies observed in independently performed Wizard-of-Oz studies. The paper discusses an ontology-based approach to multi-layered conceptual spatial mapping that pro- vides a common ground for human-robot dialogue. This is achieved by combining acquired knowledge with innate conceptual commonsense knowledge in order to infer new knowledge. The architecture bridges the gap between the rich semantic representations of the meaning expressed by verbal utterances on the one hand and the robot?s internal sensor-based world representation on the other. It is thus possible to establish references to spatial areas in a situated dialogue between a human and a robot about their environment. The resulting conceptual descrip- tions represent qualitative knowledge about locations in the environment that can serve as a basis for achieving a notion of situational awareness. InTech 2007-03-01 16 http://www.intechopen.com/articles/show/title/situated_dialogue_and_spatial_organization__what__where_and_why en ISSN:1729-8806 http://www.intechopen.com/download/pdf/pdfs_id/4220
oai:intechopen.com:4221 2007-03-01 01729-88062007-03-01
A Monocular Pointing Pose Estimator for Gestural Instruction of a Mobile Robot Jan Richarz Andrea Scheidig Christian Martin Steffen Mueler Horst-Michael Gross International Journal of Advanced Robotic Systems Volume 4 We present an important aspect of our human-robot communication interface which is being developed in the context of our long-term research framework PERSES dealing with highly interactive mobile companion robots. Based on a multi-modal people detection and tracking system, we present a hierarchical neural architec- ture that estimates a target point at the floor indicated by a pointing pose, thus enabling a user to navigate a mo- bile robot to a specific target position in his local surroundings by means of pointing. In this context, we were especially interested in determining whether it is possible to accomplish such a target point estimator using only monocular images of low-cost cameras. The estimator has been implemented and experimentally investigated on our mobile robotic assistant HOROS. Although only monocular image data of relatively poor quality were util- ized, the estimator accomplishes a good estimation performance, achieving an accuracy better than that of a hu- man viewer on the same data. The achieved recognition results demonstrate that it is in fact possible to realize a user-independent pointing direction estimation using monocular images only, but further efforts are necessary to improve the robustness of this approach for everyday application. InTech 2007-03-01 17 http://www.intechopen.com/articles/show/title/a_monocular_pointing_pose_estimator_for_gestural_instruction_of_a_mobile_robot en ISSN:1729-8806 http://www.intechopen.com/download/pdf/pdfs_id/4221
oai:intechopen.com:104 2007-06-01 978-3-902613-08-002007-06-01
Voice Activity Detection. Fundamentals and Speech Recognition System Robustness J. Ramirez J. M. Gorriz J. C. Segura Robust Speech Recognition and Understanding This chapter has shown an overview of the main challenges in robust speech detection and a review of the state of the art and applications. VADs are frequently used in a number of applications including speech coding, speech enhancement and speech recognition. A precise VAD extracts a set of discriminative speech features from the noisy speech and formulates the decision in terms of well defined rule. The chapter has summarized three robust VAD methods that yield high speech/non-speech discrimination accuracy and improve the performance of speech recognition systems working in noisy environments. The evaluation of these methods showed the experiments most commonly conducted to compare VADs: i) speech/non-speech discrimination analysis, ii) the receiver operating characteristic curves, and iii) speech recognition system tests. InTech 2007-06-01 1 http://www.intechopen.com/articles/show/title/voice_activity_detection__fundamentals_and_speech_recognition_system_robustness en ISBN:978-3-902613-08-0 http://www.intechopen.com/download/pdf/pdfs_id/104
oai:intechopen.com:105 2007-06-01 978-3-902613-08-002007-06-01
Novel Approaches to Speech Detection in the Processing of Continuous Audio Streams Janez Zibert Bostjan Vesnicer France Mihelic Robust Speech Recognition and Understanding This chapter addresses the problem of speech detection in continuous audio streams and explores the impact of speech/non-speech segmentation on speech-processing applications. We proposed a novel approach for deriving speech-detection features based on phoneme transcriptions from generic speech-recognition systems. The proposed phoneme-recognition features were designed to be recognizer and language independent and could be applied in different speech/non-speech segmentation-classification frameworks. In our evaluation experiments two segmentation-classification frameworks were tested, one based on the Viterbi decoding of hidden Markov models, where speech/non-speech segmentation and detection were performed simultaneously, and the other framework, where segments were initially produced on the basis of acoustic information by using the Bayesian information criterion and then speech/non-speech classification was performed by applying Gaussian mixture models. InTech 2007-06-01 2 http://www.intechopen.com/articles/show/title/novel_approaches_to_speech_detection_in_the_processing_of_continuous_audio_streams en ISBN:978-3-902613-08-0 http://www.intechopen.com/download/pdf/pdfs_id/105
oai:intechopen.com:106 2007-06-01 978-3-902613-08-002007-06-01
New Advances in Voice Activity Detection using HOS and Optimization Strategies J.M. Gorriz J. Ramirez C.G. Puntonet Robust Speech Recognition and Understanding This paper showed three different schemes for improving speech detection robustness and the performance of speech recognition systems working in noisy environments. These methods are based on: i) statistical likelihood ratio tests (LRTs) formulated in terms of the integrated bispectrum of the noisy signal. The integrated bispectrum is defined as a cross spectrum between the signal and its square, and therefore a function of a single frequency variable. It inherits the ability of higher order statistics to detect signals in noise with many other additional advantages; ii) Hard decision clustering approach where a set of prototypes is used to characterize the noisy channel. Detecting the presence of speech is enabled by a decision rule formulated in terms of an averaged distance between the observation vector and a cluster-based noise model; and iii) an effective method employing support vector machines (SVM) , a paradigm of learning from examples based in Vapkik-Chervonenkis theory. The use of kernels in SVM enables to map the data, via a nonlinear transformation, into some other dot product space (called feature space) in which the classification task is settled. The proposed methods incorporate contextual information to the decision rule, a strategy that has reported significant improvements in speech detection accuracy and robust speech recognition applications. The optimal window size was determined by analyzing the overlap between the distributions of the decision variable and the error rate. The experimental analysis conducted on the well-known AURORA databases has reported significant improvements over standardized techniques such as ITU G.729, AMR1, AMR2 and ESTI AFE VADs, as well as over recently published VADs. The analysis assessed: i) the speech/non-speech detection accuracy by means of the ROC curves, with the proposed VADs yielding improved hit-rates and reduced false alarms when compared to all the reference algorithms, and ii) the recognition rate when the VADs are considered as part of a complete speech recognition system, showing a sustained advantage in speech recognition performance. InTech 2007-06-01 3 http://www.intechopen.com/articles/show/title/new_advances_in_voice_activity_detection_using_hos_and_optimization_strategies en ISBN:978-3-902613-08-0 http://www.intechopen.com/download/pdf/pdfs_id/106
oai:intechopen.com:107 2007-06-01 978-3-902613-08-002007-06-01
Voice and Noise Detection with AdaBoost T. Takiguchi N. Miyake H. Matsuda Y. Ariki Robust Speech Recognition and Understanding We proposed the sudden-noise detection and classification with Boosting. Experimental results show that the performance using AdaBoost is better than that of the conventional GMM-based method, especially at a high SNR (meaning, under low-power noise conditions). The reason is that Boosting could make a complex non-linear boundary fitting training data, while the GMM approach could not express the complex boundary because the GMM-based method calculates the mean and covariance of the training data only. Future research will include combining the noise detection and classification with noise reduction. InTech 2007-06-01 4 http://www.intechopen.com/articles/show/title/voice_and_noise_detection_with_adaboost en ISBN:978-3-902613-08-0 http://www.intechopen.com/download/pdf/pdfs_id/107
oai:intechopen.com:108 2007-06-01 978-3-902613-08-002007-06-01
Evolutionary Speech Recognition Anne Spalanzani Robust Speech Recognition and Understanding InTech 2007-06-01 5 http://www.intechopen.com/articles/show/title/evolutionary_speech_recognition en ISBN:978-3-902613-08-0 http://www.intechopen.com/download/pdf/pdfs_id/108
oai:intechopen.com:109 2007-06-01 978-3-902613-08-002007-06-01
Using Genetic Algorithm to Improve the Performance of Speech Recognition Based on Artificial Neural Network Shing-Tai Pan Chih-Chin Lai Robust Speech Recognition and Understanding In this chapter, we have seen that the recognition rate through the SDM in BPNN is up to 91% under the MFCC feature. This recognition rate is not the optimum because that the SDM can always get local optimum. To solve this problem, GA was adopted and following SDM to improve MSE. By this two stage (SDM then GA) training scheme, the recognition rate can be increasing up to 95%. However, under the condition of adopting only MFCC parameters, speech recognition rate still has room for improvement. For the future, other InTech 2007-06-01 6 http://www.intechopen.com/articles/show/title/using_genetic_algorithm_to_improve_the_performance_of_speech_recognition_based_on_artificial_neural_ en ISBN:978-3-902613-08-0 http://www.intechopen.com/download/pdf/pdfs_id/109
oai:intechopen.com:110 2007-06-01 978-3-902613-08-002007-06-01
A General Approximation-Optimization Approach to Large Margin Estimation of HMMs Hui Jiang Xinwei Li Robust Speech Recognition and Understanding In this paper, we have proposed a general Approximation-optiMization (AM) approach for large margin estimation (LME) of Gaussian mixture HMMs in speech recognition. Each iteration of the AM method consists of A-step and M-step. In A-step, the original LME problem is approximated by a simple convex optimization problem in a close proximity of initial model parameters. In M-step, the approximate convex optimization problem is solved by using efficient convex optimization algorithms. The AM method is a general approach which can be easily applied for discriminative training of statistical models with hidden variables. In this paper, we introduce two examples to apply the AM approach to LME of Gaussian mixture HMMs. The first method uses V-approx and is applicable for isolated word recognition and continuous speech recognition based on N-Best lists. The second method uses E-approx and can be applied to large vocabulary continuous speech recognition when competing hypotheses are given as word graphs or word lattices. Due to space limit, we can not report experimental results in this paper. Readers can refer to Li, 2005 and Li & Jiang, 2006a, Li & Jiang, 2006b for details about ASR experiments. InTech 2007-06-01 7 http://www.intechopen.com/articles/show/title/a_general_approximation-optimization_approach_to_large_margin_estimation_of_hmms en ISBN:978-3-902613-08-0 http://www.intechopen.com/download/pdf/pdfs_id/110
oai:intechopen.com:111 2007-06-01 978-3-902613-08-002007-06-01
Double Layer Architectures for Automatic Speech Recognition Using HMM Marta Casar Jose A. R. Fonollosa Robust Speech Recognition and Understanding The future of speech-related technologies is connected to the improvement of speech recognition quality. Until recently, speech recognition technologies and applications had assumed that there were certain limitations regarding vocabulary length, speaker independence, and environmental noise or acoustic events. In the future, however, ASR must deal with these restrictions and it must also be able to introduce other speech-related non-acoustic information that is available in speech signals. Furthermore, HMM-based statistical modelling--the standard state-of-the-art ASR--has several time-domain limitations that are known to affect recognition performance. Context is usually represented by means of spectral dynamic features (namely, its first and second derivatives). However, they are generally limited to a few subsequent feature vectors and do not represent long-term variations. To overcome all these drawbacks and to achieve a qualitative improvement in speech recognition, a change of paradigm from conventional speech recognizers has been proposed by several authors. Although some authors propose a move away from HMM-based recognition (or, at the very least, introducing hybrid solutions), we are adhering to Markovbased acoustic modelling as we believe its approach is still unbeatable. However, to overcome HMM-related limitations certain innovative solutions are required. Throughout this chapter we have pointed out different approaches for improving standard HMM-based ASR systems. The main solutions for modelling temporal evolution and speech trajectory have been introduced, together with some ideas on how second-order HMMs deal with the same problems. These models provide an improvement in most cases, but they also require major modifications in the decoding of algorithms. Generally, there is also a considerable increase in complexity, even if this is compensated for by a moderate gain. Layered architectures have been presented, and special attention has been paid to the implementation of the second layer using extended HMMs. Two implementations for this second layer have been described in detail. The first relies on modelling the temporal evolution of acoustic HMM state scores. In the second one, the evolution of the acoustic HMM is modelled by the speech utterance as a new way of modelling state transitions. This can be done in two ways, namely, by taking into account or ignoring the context of each active state while the "path" followed by the speech signal through the HMM states is being modelled. Again, speech recognition performance improves that of a conventional HMMbased speech recognition system, but at the cost of increased complexity. Although current research solutions should not be unduly concerned by the computational cost (due to the constant increase in the processing capacity of computers), it is important to keep their implementation in commercial applications in mind. Therefore, a great deal of work remains if layered architectures are to be generalized for large vocabulary applications that keep complexity down to a moderate level. Efforts should be made in the field of research for defining and testing innovative approaches to implementing layered architectures. Although keeping an HMM-based scheme for the different layers reduces the overall complexity, a change in paradigm may help to bring about significant improvements. InTech 2007-06-01 8 http://www.intechopen.com/articles/show/title/double_layer_architectures_for_automatic_speech_recognition_using_hmm en ISBN:978-3-902613-08-0 http://www.intechopen.com/download/pdf/pdfs_id/111
oai:intechopen.com:112 2007-06-01 978-3-902613-08-002007-06-01
Audio Visual Speech Recognition and Segmentation Based on DBN Models Dongmei Jiang Guoyun Lv Ilse Ravyse Xiaoyue Jiang Yanning Zhang Hichem Sahli Rongchun Zhao Robust Speech Recognition and Understanding In this chapter, we first implement an audio or visual single stream DBN model proposed in [Bilmes 2005], which we demonstrate that it can break through the limitation of the state-ofthe-art `whole-word-state DBN' models and output phone (viseme) segmentation results. Then we expand this model to an audio-visual multi-stream asynchronous DBN (MSADBN) model. In this MSADBN model, the asynchrony between audio and visual speech is allowed to exceed the timing boundaries of phones/visemes, in opposite to the multi-stream hidden markov models (MSHMM) or product HMM (PHMM) which constrain the audio stream and visual stream to be synchronized at the phone/viseme boundaries. In order to evaluate the performances of the proposed DBN models on word recognition and subunit segmentation, besides the word recognition rate (WRR) criterion, the timing boundaries of the segmented phones in the audio stream are compared to those obtained from the well trained triphone HMMs using HTK. The viseme timing boundaries are compared to manually labeled timing boundaries in the visual stream. Furthermore, suppose for each viseme, one representative image is built and hence a mouth animation is constructed using the segmented viseme sequence, the relative viseme segmentation accuracy (RVSA) is evaluated from the speech intelligibility aspect, by the global image sequence similarity between the mouth animations obtained from the segmented and the reference viseme sequences. Finally, the asynchrony between the segmented audio and visual subunits is also analyzed. Experiment results show: 1) the SDBN model for audio or visual speech recognition has higher word recognition performance than the triphone HMM, and with the increasing noise in the audio stream, the SDBN model shows more robust tendency; 2) in a noisy environment, the MSADBN model has higher WRR than the SDBN model, showing that the visual information increases the intelligibility of speech. 3) compared with the segmentation results by running the SDBN model on audio features and on visual features respectively, the MSADBN model, by integrating the audio features and visual features in one scheme and forcing them to be synchronized on the timing boundaries of words, in most cases, gets more reasonable asynchronous relationship between the speech units in the audio and visual streams. In our future work, we will expand the MSADBN model to the subunits segmentation task of a large vocabulary audio visual continuous speech database, and test its performance in speech recognition, as well as analyze its ability of finding the inherent asynchrony between audio and visual speech. InTech 2007-06-01 9 http://www.intechopen.com/articles/show/title/audio_visual_speech_recognition_and_segmentation_based_on_dbn_models en ISBN:978-3-902613-08-0 http://www.intechopen.com/download/pdf/pdfs_id/112
oai:intechopen.com:113 2007-06-01 978-3-902613-08-002007-06-01
Discrete-Mixture HMMs-based Approach for Noisy Speech Recognition Tetsuo Kosaka Masaharu Katoh Masaki Kohda Robust Speech Recognition and Understanding This chapter introduced a new method of robust speech recognition using discrete-mixture HMMs (DMHMMs) based on maximum a posteriori (MAP) estimation. The aim of this work was to develop robust speech recognition for adverse conditions which contain both stationary and non-stationary noise. In order to achieve the goal, we proposed two methods. InTech 2007-06-01 10 http://www.intechopen.com/articles/show/title/discrete-mixture_hmms-based_approach_for_noisy_speech_recognition en ISBN:978-3-902613-08-0 http://www.intechopen.com/download/pdf/pdfs_id/113
oai:intechopen.com:114 2007-06-01 978-3-902613-08-002007-06-01
Speech Recognition in Unknown Noisy Conditions Ji Ming Baochun Hou Robust Speech Recognition and Understanding This chapter investigated the problem of speech recognition in noisy conditions assuming absence of prior information about the noise. A method, namely universal compensation, was described, which combines multicondition model training and missing-feature theory to model noises with unknown temporal-spectral characteristics. Multicondition training can be conducted using simulated noisy data, to provide a coarse compensation for the noise, and missing-feature theory is applied to refine the compensation by ignoring noise InTech 2007-06-01 11 http://www.intechopen.com/articles/show/title/speech_recognition_in_unknown_noisy_conditions en ISBN:978-3-902613-08-0 http://www.intechopen.com/download/pdf/pdfs_id/114
oai:intechopen.com:115 2007-06-01 978-3-902613-08-002007-06-01
Uncertainty in Signal Estimation and Stochastic Weighted Viterbi Algorithm: A Unified Framework to Address Robustness in Speech Recognition and Speaker Verification N. Becerra Yoma C. Molina C. Garreton F. Huenupan Robust Speech Recognition and Understanding The Stochastic Weighted Viterbi algorithm offers a unified framework to reduce the effect of additive/convolutional noise and low-bit rate coding-decoding distortion. SWV started a new paradigm in speech processing by considering the original speech signal information as a stochastic variable. Consequently, the ordinary HMM observation probability needs to be replaced with its expected value. SWV is interesting from the theoretic and applied points of view: first, it is based on stochastic models of additive noise and low-bit rate codingdecoding distortion; and second, it assumes reasonable hypotheses such as a rough estimation of additive noise and a low number of adaptation utterances. It is worth emphasizing that SWV allows the interaction between the higher layers of language modeling (semantic, syntactic, etcâ€¦) and acoustic models in ASR just like in human perception: the higher layer of the linguistic information should have a higher weight in InTech 2007-06-01 12 http://www.intechopen.com/articles/show/title/uncertainty_in_signal_estimation_and_stochastic_weighted_viterbi_algorithm__a_unified_framework_to_a en ISBN:978-3-902613-08-0 http://www.intechopen.com/download/pdf/pdfs_id/115
oai:intechopen.com:116 2007-06-01 978-3-902613-08-002007-06-01
The Research of Noise-Robust Speech Recognition Based on Frequency Warping Wavelet Xueying Zhang Wenjun Meng Robust Speech Recognition and Understanding The later conculsions can be obtained from the experimental results of the fourth section. 1. The three parts of speech recognition are conjunct one another and exist the relation restricted among themselves. Bark wavelet was used in improving the feature of ZCPA and MFCC the latter effect is obviously better than the former.It illustrates that Bark wavelet and the speech character described by MFCC feature are more closer than Bark wavelet and the speech character described by ZCPA feature. The fact is also as such. Bark wavelet is constructed directly according to the hearing perception of human ear, and MFCC is the cepstrum coefficents on the basis of Mel frequency. While Mel frequency is just the hearing frequency of human ear. Though the frequency bins of ZCPA are divided according to the hearing perception, the zero-crossing rate and peak amplitude are time-domain parameters which are transformed nonlinearly mapping to frequency bin. This kind of nonlinear transform may affect the consistency of ZCPA and hearing frequency, that results in decreasing in function. If the selection of training or recognition network is different, they have different effect on the results. Furthermore, the function of recogntion network has direct relationship with front-end filter and feature extracted. This point can be seen from the experimental results of combination mode1 FIR+ZCPA+HMM and mode 2 FIR+ZCPA+WNN . Comparing the two modes, the former two parts are same and the third part is different from using HMM or WNN the results obtained have much more different.The wavelet neural network has bright foreground for speech recognition.Its training speed is fast, which is good for implementation in real time. Further,it has also good recognition rates under no noise or noise environment and the number of recogintion words is larger. The paper researched some kinds combination modes aiming to the three parts of speech recognition system in Fig. 1. For other combination modes, such as Bark+MFCC+WNN Bark+ZCPA+WNN and so on, we will research them in later work. Which of combination ever is optimal? This needs considering practical application case. We hope the research can be refered by interesting researcher and get to the purpose of communication mutually and progress. InTech 2007-06-01 13 http://www.intechopen.com/articles/show/title/the_research_of_noise-robust_speech_recognition_based_on_frequency_warping_wavelet en ISBN:978-3-902613-08-0 http://www.intechopen.com/download/pdf/pdfs_id/116
oai:intechopen.com:117 2007-06-01 978-3-902613-08-002007-06-01
Autocorrelation-based Methods for Noise-Robust Speech Recognition Gholamreza Farahani Mohammad Ahadi Mohammad Mehdi Homayounpour Robust Speech Recognition and Understanding In this chapter, the importance of autocorrelation domain in robust feature extraction for speech recognition was discussed. To prove the effectiveness of this domain, some recently proposed methods for robust feature extraction against additive noise were discussed. These methods resulted in cepstral feature sets derived from the autocorrelation spectral domain. The DAS algorithm used the differentiated filtered autocorrelation spectrum of the noisy signal to extract cepstral parameters. We noted that similar to RAS and DPS, DAS can better InTech 2007-06-01 14 http://www.intechopen.com/articles/show/title/autocorrelation-based_methods_for_noise-robust_speech_recognition en ISBN:978-3-902613-08-0 http://www.intechopen.com/download/pdf/pdfs_id/117
oai:intechopen.com:118 2007-06-01 978-3-902613-08-002007-06-01
Bimodal Emotion Recognition using Speech and Physiological Changes Jonghwa Kim Robust Speech Recognition and Understanding In this paper, we treated all stages of emotion analysis, from data collection to classification using short-term observations, and evaluated several fusion methods as well as a hybrid decision scheme. We also compared the results from multimodal classification with the unimodal results. As in our earlier work (Kim et al. 2005) where we relied on longer observation phases and a different set of features, the best results were obtained by featurelevel fusion method in combination with feature selection stage. In this case, not only userdependent, but also user-independent emotion classification could be improved compared to the unimodal methods. InTech 2007-06-01 15 http://www.intechopen.com/articles/show/title/bimodal_emotion_recognition_using_speech_and_physiological_changes en ISBN:978-3-902613-08-0 http://www.intechopen.com/download/pdf/pdfs_id/118
oai:intechopen.com:119 2007-06-01 978-3-902613-08-002007-06-01
Emotion Estimation in Speech Using a 3D Emotion Space Concept Michael Grimm Kristian Kroschel Robust Speech Recognition and Understanding In this chapter we discussed the recognition of emotions in spontaneous speech. We used a general framework motivated by emotion psychology to describe emotions by means of three emotion "primitives" (attributes), namely valence, activation, and dominance. With these emotion primitives, we proposed a real-valued three-dimensional emotion space concept to overcome the limitations in the state-of-the-art emotion categorization. We tested the method on the basis of 893 spontaneous emotional utterances recorded on a German TV talk-show. For the acoustic representation of the emotion conveyed in the speech signal, we extracted 137 features. These reflected the prosody and the spectral characteristics of the speech. We tested two methods to reduce the problem of large feature sets, Principal Component Analysis and Sequential Feature Selection. Thus, we selected the 20 most relevant acoustic features that yielded the best recognition results. InTech 2007-06-01 16 http://www.intechopen.com/articles/show/title/emotion_estimation_in_speech_using_a_3d_emotion_space_concept en ISBN:978-3-902613-08-0 http://www.intechopen.com/download/pdf/pdfs_id/119
oai:intechopen.com:120 2007-06-01 978-3-902613-08-002007-06-01
Linearly Interpolated Hierarchical N-gram Language Models for Speech Recognition Engines Imed Zitouni Qiru Zhou Robust Speech Recognition and Understanding We have investigated a new language modeling approach called linearly interpolated ngram language models. We showed in this chapter the effectiveness of this approach to estimate the likelihood of n-gram events: the linearly interpolated n-gram language models outperform the performance of both linearly interpolated n-gram language models and backoff n-gram language models in terms of perplexity and also in terms word error rate when intergrated into a speech recognizer engine. Compared to traditional backoff and linearly interpolated LMs, the originality of this approach is in the use of a class hierarchy that leads to a better estimation of the likelihood of n-gram events. Experiments on the WSJ database show that the linearly interpolated n-gram language models improve the test perplexity over the standard language modeling approaches: 7% improvement when estimating the likelihood of bigram events, and 10% improvement when estimating the likelihood of trigram events. Speech recognition results show to be sensitive to the number of unseen events: up to 12% reduction of the WER is obtained when using the linearly interpolated hierarchical approach, due to the large number of unseen events in the ASR test set. The magnitude of the WER reduction is larger than what we would have expected given the observed reduction of the language model perplexity; this leads us to an interesting assumption that the reduction of unseen event perplexity is more effective for improving ASR accuracy than the perplexity associated with seen events. The probability model for frequently seen events may already be appropriate for the ASR system so that improving the likelihood of such events does not correct any additional ASR errors (although the total perplexity may decrease.) Thus, it may be that similar reductions of the perplexity are not equivalent in terms of WER improvement. The improvement in word accuracy also depends on the errors the recognizer makes: if the acoustic model alone is able to discriminate words under unseen linguistic contexts, then improving the LM probability for those events may not improve the overall WER. Compared to hierarchical class n-gram LMs, we observed that the new hierarchical approach is not sensitive to the depth of the hierarchy. As future work, we may explore this approach with a more accurate technique in building the class word hierarchy. InTech 2007-06-01 17 http://www.intechopen.com/articles/show/title/linearly_interpolated_hierarchical_n-gram_language_models_for_speech_recognition_engines en ISBN:978-3-902613-08-0 http://www.intechopen.com/download/pdf/pdfs_id/120
oai:intechopen.com:121 2007-06-01 978-3-902613-08-002007-06-01
A Factored Language Model for Prosody Dependent Speech Recognition Ken Chen Mark A. Hasegawa-Johnson Jennifer S. Cole Robust Speech Recognition and Understanding In this chapter, we proposed a novel approach that improves the robustness of prosody dependent language modeling by leveraging the dependence between prosody and syntax. In our experiments on Radio News Corpus, a factorial prosody dependent language model estimated using our proposed approach has achieved as much as 31% reduction of the joint perplexity over a prosody dependent language model estimated using the standard Maximum Likelihood approach. In recognition experiments, our approach results in a 1% improvement in word recognition accuracy, 0.7% improvement in accent recognition accuracy and 1.5% improvement in intonational phrase boundary (IPB) recognition accuracy over the baseline prosody dependent recognizer. The study in the chapter shows that InTech 2007-06-01 18 http://www.intechopen.com/articles/show/title/a_factored_language_model_for_prosody_dependent_speech_recognition en ISBN:978-3-902613-08-0 http://www.intechopen.com/download/pdf/pdfs_id/121
oai:intechopen.com:122 2007-06-01 978-3-902613-08-002007-06-01
Early Decision Making in Continuous Speech Odette Scharenborg Louis ten Bosch Lou Boves Robust Speech Recognition and Understanding In the laboratory, listeners are able to reliably identify polysyllabic content words before the end of the acoustic realisation (e.g., Marslen-Wilson, 1987). In real life, listeners not only use acoustic-phonetic information, but also contextual constraints to make a decision about the identity of a word. This makes it possible for listeners to guess the identity of content words even before their uniqueness point. In the research presented here, we investigated an alternative ASR system, called SpeM, that is able to recognise words during the speech recognition process for its ability for recognising words before their acoustic offset ? but after their uniqueness point ? a capability that we dubbed `early recognition'. The restriction to recognition at or after the uniqueness point allowed us to focus on acoustic recognition only, and minimise the impact of contextual constraints. The probability theory underlying SpeM makes it possible for an advanced statistical LM to emulate the context effects that enable humans to recognise words even before their uniqueness point. Such an LM would make SpeM's recognition behaviour even more like human speech recognition behaviour. In our analyses, we investigated the Bayesian word activation as predictor for early recognition. The results in Section 5 indicate that the Bayesian word activation can be used InTech 2007-06-01 19 http://www.intechopen.com/articles/show/title/early_decision_making_in_continuous_speech en ISBN:978-3-902613-08-0 http://www.intechopen.com/download/pdf/pdfs_id/122
oai:intechopen.com:123 2007-06-01 978-3-902613-08-002007-06-01
Analysis and Implementation of an Automated Delimiter of "Quranic" Verses in Audio Files using Speech Recognition Techniques Tabbal Hassan Al-Falou Wassim Monla Bassem Robust Speech Recognition and Understanding The system that we developed showed promising results although it was only tested against small Quranâ€™ chapters. We think that the incorporation of morphological knowledge of the Arabic language with a more sophisticated statistical model deduced from the full scope of InTech 2007-06-01 20 http://www.intechopen.com/articles/show/title/analysis_and_implementation_of_an_automated_delimiter_of__quranic__verses_in_audio_files_using_speec en ISBN:978-3-902613-08-0 http://www.intechopen.com/download/pdf/pdfs_id/123
oai:intechopen.com:124 2007-06-01 978-3-902613-08-002007-06-01
An Improved GA Based Modified Dynamic Neural Network for Cantonese-Digit Speech Recognition S.H. Ling F.H.F. Leung K.F. Leung H.K. Lam H.H.C. Iu Robust Speech Recognition and Understanding A proposed Cantonese-digit speech recognizer by using a GA-based modified dynamic recurrent neural network has been developed. The structure of the modified neural network consists of two parts: a rule-base 3-layer feed-forward neural network and a classifier 3-layer recurrent neural network. The network parameters are trained by an improved GA. With this specific network structure, the dynamic feature of the speech signals can be generalized and the parameter values of the network can adapt to the values of the input data set. Cantonese digits 0 to 10, 12 and 20 have been used to demonstrate the merits of the proposed network. By using the proposed dynamic network, the dynamic and static information of the speech can be modeled effectively. Therefore, both single-syllable and multi-syllable Cantonese digits can be recognized. InTech 2007-06-01 21 http://www.intechopen.com/articles/show/title/an_improved_ga_based_modified_dynamic_neural_network_for_cantonese-digit_speech_recognition en ISBN:978-3-902613-08-0 http://www.intechopen.com/download/pdf/pdfs_id/124
oai:intechopen.com:125 2007-06-01 978-3-902613-08-002007-06-01
Talking Robot and the Autonomous Acquisition of Vocalization and Singing Skill Hideyuki Sawada Robust Speech Recognition and Understanding In this paper a talking and singing robot was introduced, which is constructed mechanically with human-like vocal cords and a vocal tract. By introducing the adaptive learning and controlling of the mechanical model with the auditory feedback, the robot was able to InTech 2007-06-01 22 http://www.intechopen.com/articles/show/title/talking_robot_and_the_autonomous_acquisition_of_vocalization_and_singing_skill en ISBN:978-3-902613-08-0 http://www.intechopen.com/download/pdf/pdfs_id/125
oai:intechopen.com:126 2007-06-01 978-3-902613-08-002007-06-01
Conversation System of an Everyday Robot Robovie-IV Noriaki Mitsunaga Zenta Miyashita Takahiro Miyashita Hiroshi Ishiguro Norihiro Hagita Robust Speech Recognition and Understanding This research was supported by the Ministry of Internal Affairs and Communications. InTech 2007-06-01 23 http://www.intechopen.com/articles/show/title/conversation_system_of_an_everyday_robot_robovie-iv en ISBN:978-3-902613-08-0 http://www.intechopen.com/download/pdf/pdfs_id/126
oai:intechopen.com:127 2007-06-01 978-3-902613-08-002007-06-01
Sound Localization of Elevation using Pinnae for Auditory Robots Tomoko Shimoda Toru Nakashima Makoto Kumon Ryuichi Kohzawa Ikuro Mizumoto Zenta Iwai Robust Speech Recognition and Understanding In this chapter, by using a system consisting of two microphones and one pinna, a method for sound localization using spectral cues was considered. In particular, a robust spectral cue detection method was considered and a method for orientating the robot's head toward a sound source was proposed. In addition, this chapter considers the use of sound source separation in order to attenuate the effect of noise. The conclusions of this present study are summarized as follows: ? Real robotic pinnae were designed and a robot using the pinnae was developed. ? In order to realize sound localization with vertical displacement, an algorithm for detecting spectral cues using the developed pinnae was proposed. ? Spectral cue detection was made robust by considering their frequency continuity with respect to time. A model for determining the sound elevation angle by measuring spectral cues was introduced. InTech 2007-06-01 24 http://www.intechopen.com/articles/show/title/sound_localization_of_elevation_using_pinnae_for_auditory_robots en ISBN:978-3-902613-08-0 http://www.intechopen.com/download/pdf/pdfs_id/127
oai:intechopen.com:128 2007-06-01 978-3-902613-08-002007-06-01
Speech Recognition Under Noise Conditions: Compensation Methods Angel de la Torre Jose C. Segura Carmen Benitez Javier Ramirez Luz Garcia Antonio J. Rubio Robust Speech Recognition and Understanding In this chapter, we have presented an overview of methods for noise robust speech recognition and a detailed description of the mechanism degrading the performance of speech recognizers working under noise conditions. Performance is degraded because of the mismatch between training and recognition and also because of the information loss associated to the randomness of the noise. In the group of compensation methods, we have described the VTS approach (as a representative model-based noise compensation method) and histogram equalization (a nonlinear non-model-based method). We have described the differences and advantages of each one, finding that more accurate compensation can be achieved with model-based methods, while non-model-based ones can deal with noise without a description of the distortion mechanism. The best results are achieved when both methods are combined. InTech 2007-06-01 25 http://www.intechopen.com/articles/show/title/speech_recognition_under_noise_conditions__compensation_methods en ISBN:978-3-902613-08-0 http://www.intechopen.com/download/pdf/pdfs_id/128
oai:intechopen.com:159 2007-06-01 978-3-902613-07-302007-06-01
Design of an Assistive Gait Device for Strength Endurance and Rehabilitation K. H. Low Xiaopeng Liu Haoyong Yu Humanoid Robots, Human-like Machines 8.1 Conclusion This chapter has presented the development and control of a wearable lower exoskeleton system for augmentation of human walking ability, which incorporates human as the integral part of the control system and can relieve humans physical fatigue caused by excessive walking and heavy payloads. In this work, xPC Target, together with other toolboxes from MATLAB have been used so as to provide a real-time operating system and an integrated development environment for controlling the exoskeleton. Real-time control of the exoskeleton is implemented in this environment. At last, walking experiments are performed and demonstrated. 8.2 Future Work The first prototype is only a test bed to verify the control algorithms. It looks bulky and rough. Though it has been verified that it can walk, there are some topics need to improve before one will see a reliable and useful exoskeleton that can effectively enhance humans strength and endurance. Another area of improvement may be the addition of more passive joints to the OLE prototype. These passive joints may be spring loaded such that it allows for passive movements without affecting the structural characteristics of the OLE. Examples of passive joints can be at positions like the feet where the passive joint can allow the bending of the OLE foot when walking. This will pertain to the users extension of the toes while walking. This addition of passive joints at the OLE feet will enable the OLE to be able to reciprocate the human movements better and at the same time, allow the user to have a more natural walking gait while wearing the OLE. Other areas where passive joints can be added are the hip joints and the ankle joints to allow them rotate. Now it is the inner exoskeleton who senses the user movements. However, the inner exoskeleton increases the distance between the user and the OLE. They can be replaced with goniometers (BIOPAC systems. Inc., n.d.), which are more compact and light. Besides, human joints are not simple pin joints but complex joints with a changing instantaneous center of rotation. Compared to the hard linkages of the inner exoskeleton, goniometer has a telescopic end block that compensates for changes in distance between the two mounting points as the limb moves. The gauge mechanism allows for more accurate measurement of polycentric joints. To save energy and consequently reduce the size of the power source (e.g. batteries) carried by the OLE, ways to help decrease the torque required at the OLE joints could be developed. Such torque compensation mechanisms are not easy to construct, especially on the OLE. Issues like the amount of torque that will be reduced versus the weight increased by the addition of such a mechanism are widely debatable. Also, such a mechanism should not hinder the movements of the user or the OLE. With the addition of such torque compensation mechanisms, the controlling of the actuators will become more complicated. This is because of the additional parameters to controlling the torque output of the actuators. Nevertheless, a few torque compensation mechanisms can be a possible solution for the OLE. Firstly, in the development of the Saika-4 by Tohoku University (Shirata, Konno, & Uchiyama, 2004), a method of torque compensation was mentioned. Using a stainless-steel wire and a contrive spring layout, the mechanism is able to compensate without depending on joint angles. This is important as methods that depend on joint angles compensate with changing forces at every joint angle position. This increases the robustness of the control of the system. The mechanism in Saika-4 is reported to be able to reduce the torque requirements of the motors InTech 2007-06-01 1 http://www.intechopen.com/articles/show/title/design_of_an_assistive_gait_device_for_strength_endurance_and_rehabilitation en ISBN:978-3-902613-07-3 http://www.intechopen.com/download/pdf/pdfs_id/159
oai:intechopen.com:160 2007-06-01 978-3-902613-07-302007-06-01
A Novel Anthropomorphic Robot Hand and its Master Slave System Tetsuya Mouri Haruhisa Kawasaki Humanoid Robots, Human-like Machines We have presented the newly developed anthropomorphic robot hand named the KH Hand type S and its master slave system using the bilateral controller. The use of an elastic body has improved the robot hand in terms of weight, the backlash of the transmission, and friction between the gears. We have demonstrated the expression of the Japanese finger alphabet. We have also shown an experiment of a peg-in-hole task controlled by the bilateral controller. These results indicate that the KH Hand type S has a higher potential than previous robot hands in performing not only hand shape display tasks but also in grasping and manipulating objects in a manner like that of the human hand. In our future work, we are planning to study dexterous grasping and manipulation by the robot. InTech 2007-06-01 2 http://www.intechopen.com/articles/show/title/a_novel_anthropomorphic_robot_hand_and_its_master_slave_system en ISBN:978-3-902613-07-3 http://www.intechopen.com/download/pdf/pdfs_id/160
oai:intechopen.com:161 2007-06-01 978-3-902613-07-302007-06-01
Development of Biped Humanoid Robots at the Humanoid Robot Research Center, Korea Advanced Institute of Science and Technology (KAIST) Ill-Woo Park Jung-Yup Kim Jungho Lee Min-Su Kim Baek-Kyu Cho Jun-Ho Oh Humanoid Robots, Human-like Machines In this chapter, The HUBO-series robot platform development is introduced. HUBO, Albert HUBO, and HUBO FX-1 are biped humanoids. Each robot has its own character. HUBO is a biped humanoid robot. The major function of this robot is to walk with its two legs and imitate the human's motions such as hand shaking, bowing, and communicating in sign language. The system components of the control hardware are connected using a CAN communication line. The control system of HUBO is based on the distributed control InTech 2007-06-01 3 http://www.intechopen.com/articles/show/title/development_of_biped_humanoid_robots_at_the_humanoid_robot_research_center__kaist_ en ISBN:978-3-902613-07-3 http://www.intechopen.com/download/pdf/pdfs_id/161
oai:intechopen.com:162 2007-06-01 978-3-902613-07-302007-06-01
Multipurpose Low-Cost Humanoid Platform and Modular Control Software Development Filipe Silva V&iacute;tor Santos Humanoid Robots, Human-like Machines In this chapter we have described the development and integration of hardware and software components to build a small-size humanoid robot based on off-the-shelf technologies. A modular design is conceived to ensure easy maintenance and faster reproducibility. The most relevant feature of this implementation includes the distributed architecture in which independent and self-contained control units may allow either a cooperative or a standalone operation. The integration in these simpler control units of sensing, processing and acting capabilities play a key role towards localised control based on feedback from several sensors. The adoption of an outer motion control loop to provide accurate trajectory tracking was presented and has been experimentally demonstrated. The strength of this approach lies in its performance, generality and overall simplicity. The humanoid platform reached a point where intermediate and high level control can now flourish. An example has been given for a kind of intermediate level control implemented as a local controller. From there, a forcedriven actuation was successfully applied to demonstrate the possibility of keeping the humanoid robot in upright balance position using the ground reaction forces. Ongoing developments on the humanoid platform cover the remainder hardware components, namely the inclusion of vision and its processing, possibly with a system based on PC104 or similar. A full autonomous humanoid robot for research is being developed that allows testing and evaluation of new ideas and concepts in both hardware and software modules. Future research, which has already started, will cover distributed control, alternative control laws and also deal with issues related to navigation of humanoids and, hopefully, cooperation. Force control techniques and more advanced algorithms such as adaptive and learning strategies will certainly be a key issue for the developments in periods to come in the near future. InTech 2007-06-01 4 http://www.intechopen.com/articles/show/title/multipurpose_low-cost_humanoid_platform_and_modular_control_software_development en ISBN:978-3-902613-07-3 http://www.intechopen.com/download/pdf/pdfs_id/162
oai:intechopen.com:163 2007-06-01 978-3-902613-07-302007-06-01
Artificial Muscles for Humanoid Robots Bertrand Tondu Humanoid Robots, Human-like Machines The functioning of natural skeletal muscle is based on microscopic phenomena that no technology is at present able to reproduce. The notion of artificial muscle is as a consequence mainly founded on a macroscopic model of the skeletal muscle. The mimicking of both tension-length and tension-velocity characteristics is aimed at giving future humanoid robots touch ability which is so fundamental in the `relational life' of human beings. No definitive technology has as yet emerged in the design of artificial muscle. It is, however, interesting to note that the most promising ones are based on the use of polymers whose physical properties (responses to chemical or physical agents, elasticity, etc.) mimic some dynamic properties of animal tissues. In particular pH, temperature or electric field are now currently used to produce and control the shape changes of polymer fibres or polymer-based composite materials. These results are generally obtained on a small scale ? typically a mm2-section scale ? and the application of these technologies to macroscopic skeletal muscle scales ? typically a cm2-section scale ? generally induces a performance loose in power-to-volume and power-to-mass. Today the integration of artificial muscles to anthropomorphic limbs on a human-scale in volume and mass, necessitates power-to-mass and power-to-volume very close to human skeletal muscle.. Pneumatic artificial muscles, in the form of McKibben artificial muscles or alternative types such as pleated artificial muscles, are at present able to mimic these natural muscle dynamic properties. As a consequence, we consider that their use is interesting to test control InTech 2007-06-01 5 http://www.intechopen.com/articles/show/title/artificial_muscles_for_humanoid_robots en ISBN:978-3-902613-07-3 http://www.intechopen.com/download/pdf/pdfs_id/163
oai:intechopen.com:164 2007-06-01 978-3-902613-07-302007-06-01
Development of a CORBA-based Humanoid Robot and its Applications Yasuo Nasu Genci Capi Hanafiah Yussof Mitsuhiro Yamano Masahiro Ohka Humanoid Robots, Human-like Machines We have developed anthropomorphic prototype humanoid robot; Bonten-Maru I and Bonten-Maru II. The Bonten-Maru humanoid robot series are one of few research prototype humanoid robots in the world which can be utilized in various aspects of studies. In this research, we utilized the Bonten-Maru in development of the CORBA-based humanoid robot control architecture, the optimal gait strategy and the teleoperation via internet. 7.1 CORBA-Based Humanoid Robot Control Architecture (HRCA) In this section, we proposed a new robot control architecture called HRCA. The HRCA is developed as a CORBA client/server system and is implemented on the Bonten-Maru I humanoid robot. The HRCA allows easy addition, deletion, and upgrading of new modules. We have carried out simulations and experiments to evaluate the performance of the proposed HRCA. The experimental result shows that the proposed HRCA is able to control the static motion of humanoid robot accurately. By using the proposed HRCA various humanoid robots in the world can share their own modules each other via Internet. InTech 2007-06-01 6 http://www.intechopen.com/articles/show/title/development_of_a_corba-based_humanoid_robot_and_its_applications en ISBN:978-3-902613-07-3 http://www.intechopen.com/download/pdf/pdfs_id/164
oai:intechopen.com:165 2007-06-01 978-3-902613-07-302007-06-01
Stability Analysis of a Simple Active Biped Robot with a Torso on Level Ground Based on Passive Walking Mechanisms Terumasa Narukawa Masaki Takahashi Kazuo Yoshida Humanoid Robots, Human-like Machines We study a simple active biped robot on level ground to walk over a wide range of speed. The use of the torso for energy supply and the swing-leg control for stable waking are introduced. Numerical simulations show that the swing-leg control enables the biped robot on level ground to walk stably over a wide range of speed, and enlarges the stable region. InTech 2007-06-01 7 http://www.intechopen.com/articles/show/title/stability_analysis_of_a_simple_active_biped_robot_with_a_torso_on_level_ground_based_on_passive_walk en ISBN:978-3-902613-07-3 http://www.intechopen.com/download/pdf/pdfs_id/165
oai:intechopen.com:166 2007-06-01 978-3-902613-07-302007-06-01
Inertial Forces Posture Control for Humanoid Robots Locomotion Victor Nunez Nelly Nadjar-Gauthier Kazuhito Yokoi Pierre Blazevic Olivier Stasse Humanoid Robots, Human-like Machines In order to consider a whole body control approach capable of treating different kinds of locomotion modes, the consideration of a motion planing and a the posture controller stages is important. In this paper this approach is presented for the locomotion of a humanoid robot. With the proposed approach motions including aerial phases, can be considered. The inertial force posture controller presented here requires the locomotion to be specified using generalized inertial force, besides the trajectory of the extremities not in contact with the ground. This inertial forces can be planed for having zmp stable motion or desired angular momentum. InTech 2007-06-01 8 http://www.intechopen.com/articles/show/title/inertial_forces_posture_control_for_humanoid_robots_locomotion en ISBN:978-3-902613-07-3 http://www.intechopen.com/download/pdf/pdfs_id/166
oai:intechopen.com:167 2007-06-01 978-3-902613-07-302007-06-01
Towards Adaptive Control Strategy for Biped Robots Christophe Sabourin Kurosh Madan Olivier Bruneau Humanoid Robots, Human-like Machines In this chapter, we have described a control strategy based on both proprioceptive and exteroceptive information for autonomous biped robots. The first presented results, carried out on the basis of computer based simulation techniques, are very promising and prove that the proposed approach is a good way to improve the control strategy of a biped robot. First, we show that, with only five reference gaits, it is possible to generate other gaits. The adjustment of the step length as a function of the average velocity is due to the gait pattern based on the Fuzzy CMAC structure. Moreover, with a fuzzy evaluation of the distance between the robots' feet and an obstacle, our control strategy allows to the biped robot to avoid an obstacle using step over strategy. However, it is important to remind that fuzzy rules are based on pragmatic approach and are constructed on the basis of some pre-defined membership functions shapes. For this reason, the presented control strategy may reach some limitation when biped robot comes InTech 2007-06-01 9 http://www.intechopen.com/articles/show/title/towards_adaptive_control_strategy_for_biped_robots en ISBN:978-3-902613-07-3 http://www.intechopen.com/download/pdf/pdfs_id/167
oai:intechopen.com:168 2007-06-01 978-3-902613-07-302007-06-01
Reinforcement Learning of Stable Trajectory for Quasi-Passive Dynamic Walking of an Unstable Biped Robot Tomohiro Shibata Kentarou Hitomoi Yutaka Nakamura Shin Ishii Humanoid Robots, Human-like Machines In this study, we proposed an on-line RL method suitable for Quasi-PDW by a 2D biped robot, whose possession of knees makes the system unstable. Our study is underlaid by the perspective of low energy consumption and good correspondence to human walking. RL was applied not only for the hip joint but also for the knee joints of the robot, and our learning method was successful in making the unstable robot produce stable walking after as small as 500 training episodes, despite of usage of simple intermittent controllers. Although the controller itself was simple, simulation experiments on downslopes with InTech 2007-06-01 10 http://www.intechopen.com/articles/show/title/reinforcement_learning_of_stable_trajectory_for_quasi-passive_dynamic_walking_of_an_unstable_biped_r en ISBN:978-3-902613-07-3 http://www.intechopen.com/download/pdf/pdfs_id/168
oai:intechopen.com:169 2007-06-01 978-3-902613-07-302007-06-01
An Adaptive Biped Gait Generation Scheme Utilizing Characteristics of Various Gaits Kengo Toda Ken Tomiyama Humanoid Robots, Human-like Machines A Sensor-Based Gait Generation method was introduced and an experimental system was built. Then, the system was implemented onto an original humanoid robot to evaluate operations and to demonstrate effectiveness of the proposed method. Experimental results exhibited successful gait selection corresponding to the road surface condition obtained from sensor information. Additionally, walking velocity and the energy efficiency are both enhanced without reducing the success rate of walking. The design approach for Gait Selector based on both ZMP and the angular momentum adopted in this study is a sufficiently general and valid one. The developed Gait Selector should be applicable to many gaits and humanoids. However, more conditional branchings based not only on ZMP and the angular momentum but also on some combinations of them may be necessary depending on such factors as robot hardware, types of gaits and criteria for robot motion evaluation. The fundamental reason for the lack of a fixed design method is that the selection of gait is inherently rooted in factors such as hardware specifications and characteristics of each gait. At present, therefore, we have to redesign the Gait Selector such as that in Fig.6 according to the procedure described in Section 3. Future studies should be targeted to simplify the design procedure of Gait Selector. The more gait modules and ground conditions are installed into the system, the more complicated parameter tuning must be required. One possibility of avoiding this problem would be to introduce simple learning capability for Gait Selector design. A discrimination method that only utilizes sensor value histories of 3-axis accelerometer to identify several ground conditions (Miyasita2006) was already reported. They employ simple decision tree constructed based on acceleration data that are obtained during several trial motions on each ground condition. There is a possibility of direct acquisition of transition rules by utilizing histories of ZMP and angular momentum with all combinations of a gait module and a ground condition. Apart from the improvement of the design of Gait Selector, there also is a room for improvements by adding new gait generation modules and improving the success rate of walk through the enhancement of the transition scheme for gait module changes. These are more straightforward tasks if the required additional computational power is available. InTech 2007-06-01 11 http://www.intechopen.com/articles/show/title/an_adaptive_biped_gait_generation_scheme_utilizing_characteristics_of_various_gaits en ISBN:978-3-902613-07-3 http://www.intechopen.com/download/pdf/pdfs_id/169
oai:intechopen.com:170 2007-06-01 978-3-902613-07-302007-06-01
Momentum Compensation for the Fast Dynamic Walk of Humanoids Based on the Pelvic Rotation of Contact Sport Athletes Jun Ueda Kenji Shirae Shingo Oda Tsukasa Ogasawara Humanoid Robots, Human-like Machines In this chapter, the trunk-twistless walk of contact sport athletes was investigated from a motion measurement. The antiphase pelvic rotation was applied to the fast walk of humanoid HRP-2.The walking action including the momentum compensation was InTech 2007-06-01 12 http://www.intechopen.com/articles/show/title/momentum_compensation_for_the_fast_dynamic_walk_of_humanoids_based_on_the_pelvic_rotation_of_contact en ISBN:978-3-902613-07-3 http://www.intechopen.com/download/pdf/pdfs_id/170
oai:intechopen.com:171 2007-06-01 978-3-902613-07-302007-06-01
Vision-based Motion Control of a Biped Robot Using 2 DOF Gaze Control Structure Shun Ushida Koichiro Deguchi Humanoid Robots, Human-like Machines In this paper, we discussed both a necessity and importance of gaze control mechanism on vision-based motion control of biped robots. Human eye structure and the eye movements, and brain motor control through a central nervous system were considered as an analogy with robotics. In fact, human has powerful control mechanism with vision in order to realize a various type of motions against uncertain environments. As a result, we showed that gaze control mechanism and integrated hierarchical structure like human motor control are indispensable for a vision system of biped robots. We can conclude that in order to overcome many difficulties of aspects of both a limitation of available hardware resources for a vision and a real-time image processing for motor control, we need not only gaze control mechanism but also use of the image processing technologies as shown in Fig. 15. We proposed a concept of the range of gaze and gaze control system with database structure. The use of both image processing and control theory allows us to realize an integrated hierarchical structure on the biped robot motion control as shown in Fig. 3. Furthermore, using the range of gaze, we can evaluate the gaze control performance from the point of view of the availability of visual information for robot motion control. InTech 2007-06-01 13 http://www.intechopen.com/articles/show/title/vision-based_motion_control_of_a_biped_robot_using_2_dof_gaze_control_structure en ISBN:978-3-902613-07-3 http://www.intechopen.com/download/pdf/pdfs_id/171
oai:intechopen.com:172 2007-06-01 978-3-902613-07-302007-06-01
Limit Cycle Walking Daan G.E. Hobbelen Martijn Wisse Humanoid Robots, Human-like Machines In this chapter we have introduced the paradigm `Limit Cycle Walking'. This paradigm has been used for some time by a group of bipedal robotics researchers, but the concept had not been properly defined before: Limit Cycle Walking is a nominally periodic sequence of steps that is stable as a whole but not locally stable at every instant in time. Limit Cycle Walking releases the unnecessary stability constraint of sustained local stability that is often applied in bipedal robots. It only requires the much less restrictive cyclic InTech 2007-06-01 14 http://www.intechopen.com/articles/show/title/limit_cycle_walking en ISBN:978-3-902613-07-3 http://www.intechopen.com/download/pdf/pdfs_id/172
oai:intechopen.com:173 2007-06-01 978-3-902613-07-302007-06-01
A Human-Like Approach to Footstep Planning Yasar Ayaz Khalid Munawar Mohammad Bilal Malik Atsushi Konno Masaru Uchiyama Humanoid Robots, Human-like Machines Our algorithm successfully demonstrates a novel global reactive footstep planning strategy with a human-like approach. Incremental graph expansion from simpler to more complex paths ensures formation of a simpler and more useful graph as compared to that formed by approaches such as the visibility graph. The trajectory generated is more energy-efficient since the robot does not have to lift its foot to a high location in every step as in case of game theory based approaches. The algorithm is considerably fast and reduces computational complexity by minimizing the number of alternate steps considered after planning each step. However, basing the cost of each step on energy or time optimisation criteria instead of just the complexity level of the stepping motion can further improve the performance of the algorithm. Possibilities for future work include implementation on real humanoid robot and incorporation of measures for dealing with dynamic obstacles in the environment. In addition, identification of alternate paths by considering postural changes also seems interesting e.g. constraints on many obstacles of type-3 can be reduced to those for type-2 if the robot only lifts up its arms. InTech 2007-06-01 15 http://www.intechopen.com/articles/show/title/a_human-like_approach_to_footstep_planning en ISBN:978-3-902613-07-3 http://www.intechopen.com/download/pdf/pdfs_id/173
oai:intechopen.com:174 2007-06-01 978-3-902613-07-302007-06-01
Mixed Logic Dynamical Modeling and On Line Optimal Control of Biped Robot Yingjie Yin Shigeyuki Hosoe Humanoid Robots, Human-like Machines In this study, we proposed a MLD modeling and MPC approach for the on line optimization of biped motion. Such modeling approach possesses advantage that it describes both the continuous dynamics and the impact event within one framework, consequently it provides a unified approach for mathematical, numerical and control investigations. This MLD model allows model predictive control (MPC) and subsequent stability from the numerical analysis viewpoints, by powerful MIQP solver. Hence the biped robot can be on line controlled without pre-defined trajectory. The optimal solution corresponds to the optimal gait for current environment and control requirement. The feasibility of the MLD model based predictive control is shown by simulations. How to effectively decrease the computation time in order to realize the real time implementation is an important research topic left to future. Finally, we mention that a human uses his predictive function based on an internal model together with his feedback function for motion, which is considered as a motor control model of a cerebellum (Kawato, 1999). Stimulated by this, a general theoretical study for motion control of hybrid systems is reported in (Yin & Hosoe, 2004) which is based on the MLD model of a hybrid system. We are further developing this theory to help the biped motion synthesis and control. It will be also useful for the realization of complex motion of other bio-mimetic robots. InTech 2007-06-01 16 http://www.intechopen.com/articles/show/title/mixed_logic_dynamical_modeling_and_on_line_optimal_control_of_biped_robot en ISBN:978-3-902613-07-3 http://www.intechopen.com/download/pdf/pdfs_id/174
oai:intechopen.com:175 2007-06-01 978-3-902613-07-302007-06-01
Bipedal Walking Pattern Design by Synchronizing the Motions in the Sagittal and Lateral Planes Chi Zhu Atsuo Kawamura Humanoid Robots, Human-like Machines In this paper, a new design approach of bipedal walking pattern based on the synchronization of the motions in the sagittal and lateral planes are presented. With the discussion on the motions in these two planes, the fact is clarified that the motions in the sagittal and lateral planes are tightly coupled together. The motion parameters in the sagittal plane such as walking speed, walking time, and phase stride can be easily adjusted by altering the start and finish points of the double support phase in the lateral plane. Therefore, an approach for adjusting the walking speed by controlling the double support phase is naturally developed. Moreover, it is pointed out that a smooth and fast walking can be obtained by shortening the double support phase after a high speed is reached at the end of acceleration phase. Such a walking pattern is very similar to a walker's patter in walking race. The motion planning is also presented and a numerical example is given out. It is expected to apply this theory to a real bipedal robot and extend it to the jumping and running robot. (This paper is originally published in IEEJ Trans. IA, Vol. 126, No. 8, pp. 1069-1078, 2006) InTech 2007-06-01 17 http://www.intechopen.com/articles/show/title/bipedal_walking_pattern_design_by_synchronizing_the_motions_in_the_sagittal_and_lateral_planes en ISBN:978-3-902613-07-3 http://www.intechopen.com/download/pdf/pdfs_id/175
oai:intechopen.com:176 2007-06-01 978-3-902613-07-302007-06-01
Generating Natural Motion in an Android by Mapping Human Motion Daisuke Matsui Takashi Minato Karl F. MacDorman Hiroshi Ishiguro Humanoid Robots, Human-like Machines This paper has proposed a method of implementing humanlike motions by mapping their three-dimensional appearance to the android using a motion capture system. By measuring the android's posture and comparing it to the posture of a human subject, we propose a new method to evaluate motion sequences along bodily surfaces. Unlike other approaches that focus on reducing joint angle errors, we consider how to evaluate differences in the android's apparent motion, that is, motion at its visible surfaces. The experimental results show the effectiveness of the evaluation: the method can transfer human motion. However, the method is restricted by the speed of the motion. We have to introduce a method to deal with the dynamic characteristics (Ben=Amor et al., 2007) and physical limitations of the android. We also have to evaluate the method with different subjects. We would expect to generate the most natural and accurate movements using a female subject who is about the same height as the original woman on which the android is based. Moreover, we have to evaluate the human likeness of the visible motions by the subjective impressions the android gives experimental subjects and the responses it elicits, such as eye contact (Minato et al., 2006; Shimada et al., 2006), autonomic responses, and so on. Research in these areas is in progress. InTech 2007-06-01 18 http://www.intechopen.com/articles/show/title/generating_natural_motion_in_an_android_by_mapping_human_motion en ISBN:978-3-902613-07-3 http://www.intechopen.com/download/pdf/pdfs_id/176
oai:intechopen.com:177 2007-06-01 978-3-902613-07-302007-06-01
Towards an Interactive Humanoid Companion with Visual Tracking Modalities Paulo Menezes Frederic Lerasle Jorge Dias Thierry Germa Humanoid Robots, Human-like Machines This article presents the developments of a set of visual trackers dedicated to the upper human body parts. We have outlined visual trackers a universal humanoid companion should deal with in the future. A brief state-of-art related to tracking highlight that particle filtering is widely used in the literature. The popularity of this framework stems, probably, from its simplicity, ease of implementation, and modelling flexibility, for a wide variety of applications. From these considerations, a first contribution relates to visual data fusion and particle filtering strategies associations with respect to considered interaction modalities. This guiding principle frames all the designed and developed trackers. Practically, the multi-cues associations proved to be more robust than any of the cues individually. All the trackers are applied in quasi-real-time process and have the ability to (re)-initialize automatically. A second contribution concerns especially the 3D tracker dedicated to the upper human body parts. An efficient method (not detailed here, see (Menezes et al., 2005b) has been proposed in order to handle the projection and hidden removal efficiently. In the vein of the depicted 2D trackers, we propose a new model-image matching cost metric combining visual cues but also geometric constraints. We integrate degrees of adaptability into this likelihood function depending on the human limbs appearance and the environmental conditions. Finally, integration, even if in progress, of the developed trackers on two platforms highlights their relevance and complementarity. To our knowledge, quite few mature robotic systems enjoy such advanced capabilities of human perception. Several directions are studied regarding our trackers. Firstly, to achieve gestures/activities interpretation, Hidden Markov Models (Fox et al., 2006) and Dynamic Bayesian Network (Pavlovic et al., 1999) are currently under evaluation and preliminary results are actually available. Secondly, we currently study how to extend our monocular-based approaches to account for stereoscopic data as most humanoid robot embed such exteroceptive sensor. Finally, we will integrate all these visual trackers on our new humanoid companion HRP2. The tracking functionalities will be made much more active; zooming will be used to actively adapt the focal lenght with respect to the H/R distance and the current robot status. InTech 2007-06-01 19 http://www.intechopen.com/articles/show/title/towards_an_interactive_humanoid_companion_with_visual_tracking_modalities en ISBN:978-3-902613-07-3 http://www.intechopen.com/download/pdf/pdfs_id/177
oai:intechopen.com:178 2007-06-01 978-3-902613-07-302007-06-01
Methods for Environment Recognition Based on Active Behaviour Selection and Simple Sensor History Takahiro Miyashita Reo Matsumura Kazuhiko Shinozawa Hiroshi Ishiguro Norihiro Hagita Humanoid Robots, Human-like Machines In this paper, we proposed a method for recognizing environment and selecting appropriate behaviours for humanoid robots based on sensor histories. By using the method, the robot could select effective behaviours to recognize current environment. For ten different environments that are typical in a Japanese family's house, the results of these experiments indicated that the robot successfully recognized them by five basic motions shown in Table 3. However, we should consider the case when number of candidates of current environment does not converge to one. In the case, the robot should acquire new sensor data and rebuild the decision trees, then recognize the environment, again. After these processes, when the number of candidates of the environment becomes one, the robot can decide that the environment is inexperienced. Otherwise, prepared basic motions are not enough for recognizing the environments and an additional basic motion is necessary. In future work, we will clarify dynamical relationships between basic motions and features of environments, and confirm proposed basic motions enough for recognizing the environments. Then, we will extend our method to deal with inexperienced environments. InTech 2007-06-01 20 http://www.intechopen.com/articles/show/title/methods_for_environment_recognition_based_on_active_behaviour_selection_and_simple_sensor_history en ISBN:978-3-902613-07-3 http://www.intechopen.com/download/pdf/pdfs_id/178
oai:intechopen.com:179 2007-06-01 978-3-902613-07-302007-06-01
Simulation Study on Acquisition Process of Locomotion by Using an Infant Robot Katsuyoshi Tsujita Tatsuya Masuda Humanoid Robots, Human-like Machines This chapter presented a simulation method for simulating, and thereby clarifying, the development process of human locomotion that uses a model of an infant robot. The infant robot has many degrees of freedom. By making constraints and coordination for many DOF of using "intensions" such as "want to stay sitting," or "want to move more forward," etc., various motion patterns emerge according to a specific intension. In this study, this type of intension is given as the objective function and development of motion pattern, and is simulated as an optimization or learning problem. Dynamically changing the intension according to the development process changed the motion pattern of the infant robot, and it developed from sitting to crawling, toward locomotion. We investigated the process of this type of development in the infant robot with numerical simulations. InTech 2007-06-01 21 http://www.intechopen.com/articles/show/title/simulation_study_on_acquisition_process_of_locomotion_by_using_an_infant_robot en ISBN:978-3-902613-07-3 http://www.intechopen.com/download/pdf/pdfs_id/179
oai:intechopen.com:180 2007-06-01 978-3-902613-07-302007-06-01
Visual Attention and Distributed Processing of Visual Information for the Control of Humanoid Robots Ales Ude Jan Moren Gordon Cheng Humanoid Robots, Human-like Machines The goals of our work were twofold. On the one hand, we studied how to introduce topdown effects into a bottom-up visual attention system. We have extended the classic system proposed by (Itti et al., 1998) with top-down inhibitory signals to drive attention towards the areas with the expected features while still considering other salient areas in the scene in a bottom-up manner. Our experimental results show that the system can select areas of interest using various features and that the selected areas are quite plausible and most of the time contain potential objects of interest. On the other hand, we studied distributed computer architectures, which are necessary to achieve real-time operation of complex processes such as visual attention. Although some of the previous works mention that parallel implementations would be useful and indeed parallel processing was used in at least one of them (Breazeal and Scasselatti, 1999), this is the first study that focuses on issues arising from such a distributed implementation. We developed a computer architecture that allows for proper distribution of visual processes involved in visual attention. We studied various synchronization schemes that enable the integration of different processes in order to compute the final result. The designed architecture can easily scale to accommodate more complex visual processes and we view it as a step towards a more brain-like processing of visual information on humanoid robots. Our future work will center on the use of visual attention to guide higher-level cognitive tasks. While the possibilities here are practically limitless, we intend to study especially how to guide the focus of attention when learning about various object affordances, such as for example the relationships between the objects and actions that can be applied to objects in different situations. InTech 2007-06-01 22 http://www.intechopen.com/articles/show/title/visual_attention_and_distributed_processing_of_visual_information_for_the_control_of_humanoid_robots en ISBN:978-3-902613-07-3 http://www.intechopen.com/download/pdf/pdfs_id/180
oai:intechopen.com:181 2007-06-01 978-3-902613-07-302007-06-01
Visual Guided Approach-to-Grasp for Humanoid Robots Yang Shen De Xu Min Tan Ze-Min Jiang Humanoid Robots, Human-like Machines Issues concerning with the approach-to-grasp movement of the humanoid robot are investigated in this chapter, including the calibration of the vision system, the visual measurement of rectangle objects and the visual control strategy for grasping. InTech 2007-06-01 23 http://www.intechopen.com/articles/show/title/visual_guided_approach-to-grasp_for_humanoid_robots en ISBN:978-3-902613-07-3 http://www.intechopen.com/download/pdf/pdfs_id/181
oai:intechopen.com:182 2007-06-01 978-3-902613-07-302007-06-01
Dexterous Humanoid Whole-Body Manipulation by Pivoting Eiichi Yoshida Vincent Hugel Pierre Blazevic Kazuhito Yokoi Kensuke Harada Humanoid Robots, Human-like Machines In this paper a pivoting manipulation method has been presented to realize dexterous manipulation that enables precise displacement of heavy or bulky objects. Through this application, we believe that the application area of humanoid robot can be significantly extended. A sequence of pivoting motion composed of two phases has been proposed, manipulation control and robot stepping motion. In the former phase, an impedance control and balancing control framework was introduced to control the required contact force for grasping and to maintain stability during manipulation respectively. Resolved momentum control is adopted for stepping motion in the latter phase. We then showed a sequence of pivoting motion to transport the objects towards the desired direction. We have shown that the proposed pivoting manipulation can be effectively performed by computer simulation and experiments using a humanoid robot platform HRP-2. As a future work, the method will be improved to adapt to various object shapes of transportation in pursuit of wide application in future developments. One of other extension is the manipulation planning for more general trajectories with experimentation of both manipulation and stepping phases. Integration of identification of physical properties of the objects or environments (Yu et al., 1999, Debus et al., 2000) is also an important issue to improve the robot's dexterity. InTech 2007-06-01 24 http://www.intechopen.com/articles/show/title/dexterous_humanoid_whole-body_manipulation_by_pivoting en ISBN:978-3-902613-07-3 http://www.intechopen.com/download/pdf/pdfs_id/182
oai:intechopen.com:183 2007-06-01 978-3-902613-07-302007-06-01
Imitation Learning Based Talking Heads in Humanoid Robotics Enzo Mumolo Massimiliano Nolich Humanoid Robots, Human-like Machines The estimation of articulatory static and dynamic configuration is one of the most difficult problems in voice technology. Several approaches have been attemped during the past years, and most of the difficulties are due to the fact that the articulatory-acoustic relation is not unique: different articulatory configurations can produce the same signal. The problem can be faced with suitable constraints which are needed to avoid the unrealistic configurations. One on the last work in this area has been reported in [60], which estimated articulatory parameters by finding the maximum a posteriori estimate of articulatory parameters for a given speech spectrum and the state sequence of a HMM--based speech production model. This model consists of HMMs of articulatory parameters for each phoneme and an articulatory-to-acoustic mapping that transforms the articulatory parameters into the speech spectrum for each HMM state. The authors constructed the model by using simultaneously observed articulatory and acoustic data for sentence utterances, which was collected by using an electro-magnetic articulo-graphic (EMA) system. Our system does not use EMA at all, trying to get the right articulations with several penalty factors. For this reason, the audio-video result is not always correct and it needs a judgment by the operator. We emphasize the following final remarks. InTech 2007-06-01 25 http://www.intechopen.com/articles/show/title/imitation_learning_based_talking_heads_in_humanoid_robotics en ISBN:978-3-902613-07-3 http://www.intechopen.com/download/pdf/pdfs_id/183
oai:intechopen.com:184 2007-06-01 978-3-902613-07-302007-06-01
Bilinear Time Delay Neural Network System for Humanoid Robot Software Fumio Nagashima Humanoid Robots, Human-like Machines In this chapter, I describe the neural network suitable for building the total humanoid robot software system and show some applications. This method is characterized by â€¢ uniform implementation for wide variety of applications â€¢ simplicity for dynamically structure modification The software system becomes flexible by these characteristics. Now, Iâ€™m working on the general learning technique for this neural network. There is a possibility free from NFL problem (Wolper, 1997). This chapter is originally written for the RSJ paper in Japanese (Nagashima, 2006). InTech 2007-06-01 26 http://www.intechopen.com/articles/show/title/bilinear_time_delay_neural_network_system_for_humanoid_robot_software en ISBN:978-3-902613-07-3 http://www.intechopen.com/download/pdf/pdfs_id/184
oai:intechopen.com:185 2007-06-01 978-3-902613-07-302007-06-01
Robot Learning by Active Imitation Juan Pedro Bandera Rebeca Marfil Luis Molina Tanco Juan Antonio Rodriguez Antonio Bandera Francisco Sandoval Humanoid Robots, Human-like Machines In this chapter, an architecture that endows a robot with the ability to imitate has been described. This architecture has modules that provide action level and program level InTech 2007-06-01 27 http://www.intechopen.com/articles/show/title/robot_learning_by_active_imitation en ISBN:978-3-902613-07-3 http://www.intechopen.com/download/pdf/pdfs_id/185
1521638106987