%0 Conference Paper %B AAAI Workshops %D 2012 %T Augmenting the Reachable Space in the NAO Humanoid Robot %A Marco Antonelli %A Beata J. Grzyb %A Vicente Castelló %A Angel P. del Pobil %K autonomous learning %K cues integration %K humanoid robot %K radial basis functions %K recursive least square %X

Reaching for a target requires estimating the spatial position of the target and to convert such a position in a suitable arm-motor command. In the proposed framework, the location of the target is represented implicitly by the gaze direction of the robot and by the distance of the target. The NAO robot is provided with two cameras, one to look ahead and one to look down, which constitute two independent head-centered coordinate systems. These head-centered frames of reference are converted into reaching commands by two neural networks. The weights of networks are learned by moving the arm while gazing the hand, using an on-line learning algorithm that maintains the covariance matrix of weights. This work adapts a previously proposed model that worked on a full humanoid robot torso, to work with the NAO and is a step toward a more generic framework for the implicit representation of the peripersonal space in humanoid robots.

%B AAAI Workshops %G eng %U http://www.aaai.org/ocs/index.php/WS/AAAIW12/paper/view/5231 %0 Book Section %B From Animals to Animats 12 %D 2012 %T How Walking Influences the Development of Absolute Distance Perception %A Beata J. Grzyb %A Angel P. del Pobil %A Linda B. Smith %E Ziemke, Tom %E Balkenius, Christian %E Hallam, John %B From Animals to Animats 12 %S Lecture Notes in Computer Science %I Springer Berlin / Heidelberg %V 7426 %P 65–74 %@ 978-3-642-33092-6 %G eng %0 Book Section %B Artificial Neural Networks and Machine Learning – ICANN 2012 %D 2012 %T Integration of Static and Self-motion-Based Depth Cues for Efficient Reaching and Locomotor Actions %A Beata J. Grzyb %A Vicente Castelló %A Marco Antonelli %A Angel P. del Pobil %E Villa, AlessandroE.P. %E Duch, Włodzisław %E Érdi, Péter %E Masulli, Francesco %E Palm, Günther %K depth cue integration %K distance perception %K embodied perception %K reward-mediated learning %B Artificial Neural Networks and Machine Learning – ICANN 2012 %S Lecture Notes in Computer Science %I Springer Berlin Heidelberg %V 7552 %P 322-329 %@ 978-3-642-33268-5 %G eng %U http://dx.doi.org/10.1007/978-3-642-33269-2_41 %R 10.1007/978-3-642-33269-2_41 %0 Book Section %B From Animals to Animats 12 %D 2012 %T Plastic Representation of the Reachable Space for a Humanoid Robot %A Marco Antonelli %A Beata J. Grzyb %A Vicente Castelló %A Angel P. del Pobil %E Ziemke, Tom %E Balkenius, Christian %E Hallam, John %B From Animals to Animats 12 %S Lecture Notes in Computer Science %I Springer Berlin Heidelberg %V 7426 %P 167-176 %@ 978-3-642-33092-6 %G eng %U http://dx.doi.org/10.1007/978-3-642-33093-3_17 %R 10.1007/978-3-642-33093-3_17 %0 Journal Article %J Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on %D 2012 %T Pose Estimation Through Cue Integration: A Neuroscience-Inspired Approach %A Eris Chinellato %A Beata J. Grzyb %A Angel P. del Pobil %K binocular cue integration %K Biological system modeling %K Cameras %K Computational modeling %K Computer Simulation %K Computer-Assisted %K Cybernetics %K Depth Perception %K Estimation %K Grasping %K grippers %K Humans %K Image Processing %K Intelligent robots %K Models %K monocular cue integration %K Neurological %K neuropsychological effects %K neuroscience-inspired model %K object estimation %K perspective orientation estimator %K pose estimation %K Reliability %K Reproducibility of Results %K robot sensory systems %K robot vision %K robot vision systems %K Robotics %K Robots %K stereo image processing %K stereo vision %K stereoptic orientation estimator %K Task Performance and Analysis %K visual estimation %K visual perception %K Visualization %X

The aim of this paper is to improve the skills of robotic systems in their interaction with nearby objects. The basic idea is to enhance visual estimation of objects in the world through the merging of different visual estimators of the same stimuli. A neuroscience-inspired model of stereoptic and perspective orientation estimators, merged according to different criteria, is implemented on a robotic setup and tested in different conditions. Experimental results suggest that the integration of multiple monocular and binocular cues can make robot sensory systems more reliable and versatile. The same results, compared with simulations and data from human studies, show that the model is able to reproduce some well-recognized neuropsychological effects.

%B Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on %V 42 %P 530-538 %G eng %R 10.1109/TSMCB.2011.2168952 %0 Journal Article %J IEEE Transactions on Systems, Man, and Cybernetics, Part B %D 2012 %T Pose Estimation Through Cue Integration: A Neuroscience-Inspired Approach %A Eris Chinellato %A Beata J. Grzyb %A Angel P. del Pobil %B IEEE Transactions on Systems, Man, and Cybernetics, Part B %V 42(2) %P 530–538 %G eng %0 Conference Paper %B Proceedings of Post-Graduate Conference on Robotics and Development of Cognition (A satellite Event of the International Conference on Artificial Neural Networks - ICANN 2012). %D 2012 %T Reachable by walking: inappropriate integration of near and far space may lead to distance errors %A Beata J. Grzyb %A Vicente Castelló %A Angel P. del Pobil %B Proceedings of Post-Graduate Conference on Robotics and Development of Cognition (A satellite Event of the International Conference on Artificial Neural Networks - ICANN 2012). %G eng %0 Conference Paper %B AAAI Workshop on Lifelong learning %D 2011 %T Between frustration and elation: sense of control regulates the intrinsic motivation for motor learning %A Beata J. Grzyb %A J. Boedecker %A M. Asada %A Angel P. del Pobil %A Linda B. Smith %B AAAI Workshop on Lifelong learning %G eng %0 Journal Article %J Neurocomputing %D 2011 %T The Dorso-medial visual stream: From neural activation to sensorimotor interaction %A Eris Chinellato %A Beata J. Grzyb %A Nicoletta Marzocchi %A A. Bosco %A Patrizia Fattori %A Angel P. del Pobil %K Bio-inspired systems %X

The posterior parietal cortex of primates, and more exactly areas of the dorso-medial visual stream, are able to encode the peripersonal space of a subject in a way suitable for gathering visual information and contextually performing purposeful gazing and arm reaching movements. Such sensorimotor knowledge of the environment is not explicit, but rather emerges through the interaction of the subject with nearby objects. In this work, single-cell data regarding the activation of primate dorso-medial stream neurons during gazing and reaching movements is studied, with the purpose of discovering meaningful pattern useful for modeling purposes. The outline of a model of the mechanisms which allow humans and other primates to build dynamical representations of their peripersonal space through active interaction with nearby objects is proposed, and a detailed description of how to employ the results of the data analysis in the model is offered. The application of the model to robotic systems will allow artificial agents to improve their skills in exploring the nearby space, and will at the same time constitute a way to validate modeling assumptions.

%B Neurocomputing %V 74 %P 1203 - 1212 %G eng %U http://www.sciencedirect.com/science/article/pii/S0925231210004212 %R 10.1016/j.neucom.2010.07.029 %0 Conference Paper %B IROS 2011 Workshop on Cognitive Neuroscience Robotics %D 2011 %T Elevated activation of dopaminergic brain areas facilitates behavioral state transition %A Beata J. Grzyb %A J. Boedecker %A M. Asada %A Angel P. del Pobil %B IROS 2011 Workshop on Cognitive Neuroscience Robotics %G eng %0 Conference Paper %B Computational Intelligence for Visual Intelligence (CIVI), 2011 IEEE Workshop on %D 2011 %T Hierarchical object recognition inspired by primate brain mechanisms %A Eris Chinellato %A Javier Felip %A Beata J. Grzyb %A Antonio Morales %A Angel P. del Pobil %K brain %K Estimation %K Grasping %K hierarchical object recognition %K Image color analysis %K multimodal integration %K mutual projection %K neurophysiology %K neuroscience hypothesis %K object recognition %K object weight estimation %K primate brain mechanism %K real robot %K robot vision %K Robots %K Shape %K visual processing %K Visualization %K visuomotor behavior %B Computational Intelligence for Visual Intelligence (CIVI), 2011 IEEE Workshop on %G eng %R 10.1109/CIVI.2011.5955017 %0 Journal Article %J Autonomous Mental Development, IEEE Transactions on %D 2011 %T Implicit Sensorimotor Mapping of the Peripersonal Space by Gazing and Reaching %A Eris Chinellato %A Marco Antonelli %A Beata J. Grzyb %A Angel P. del Pobil %K arm motor control %K arm movement control %K artificial agent %K control engineering computing %K eye movement control %K Eye–arm coordination %K gazing action %K humanoid robot %K implicit sensorimotor mapping %K implicit visuomotor representation %K joint-space representation %K motion control %K oculomotor control %K peripersonal space %K radial basis function framework %K radial basis function networks %K reaching actions %K Robotics %K self-supervised learning %K shared sensorimotor map %K spatial awareness %K stereo vision %X

Primates often perform coordinated eye and arm movements, contextually fixating and reaching towards nearby objects. This combination of looking and reaching to the same target is used by infants to establish an implicit visuomotor representation of the peripersonal space, useful for both oculomotor and arm motor control. In this work, taking inspiration from such behavior and from primate visuomotor mechanisms, a shared sensorimotor map of the environment, built on a radial basis function framework, is configured and trained by the coordinated control of eye and arm movements. Computational results confirm that the approach seems especially suitable for the problem at hand, and for its implementation on a real humanoid robot. By exploratory gazing and reaching actions, either free or goal-based, the artificial agent learns to perform direct and inverse transformations between stereo vision, oculomotor, and joint-space representations. The integrated sensorimotor map that allows to contextually represent the peripersonal space through different vision and motor parameters is never made explicit, but rather emerges thanks to the interaction of the agent with the environment.

%B Autonomous Mental Development, IEEE Transactions on %V 3 %P 43-53 %G eng %R 10.1109/TAMD.2011.2106781 %0 Conference Paper %B IEEE International Conference on Development and Learning and Epigenetic Robotics %D 2011 %T Trying anyways: how ignoring the errors may help in learning new skills %A Beata J. Grzyb %A J. Boedecker %A M. Asada %A Angel P. del Pobil %A Linda B. Smith %B IEEE International Conference on Development and Learning and Epigenetic Robotics %G eng %0 Journal Article %J Industrial Robot Journal %D 2009 %T A 3D Grasping System Based on Multimodal Visual and Tactile Processing %A Beata J. Grzyb %A Eris Chinellato %A Antonio Morales %A Angel P. del Pobil %B Industrial Robot Journal %V 36 %P 365-369 %G eng %R 10.1108/01439910910957138 %0 Book Section %B Bioinspired Applications in Artificial and Natural Computation, LNCS 5602 %D 2009 %T Eye-Hand Coordination for Reaching in Dorsal Stream Area {V6A}: Computational Lessons %A Eris Chinellato %A Beata J. Grzyb %A Nicoletta Marzocchi %A A. Bosco %A Patrizia Fattori %A Angel P. del Pobil %E J. Mira %E J. M. Ferrandez %E J.R. Alvarez Sánchez %E F. de la Paz %E J. Toledo %B Bioinspired Applications in Artificial and Natural Computation, LNCS 5602 %I Springer %P 304–313 %G eng %R 10.1007/978-3-642-02267-8_33 %0 Conference Paper %B Proc. International Joint Conference on Neural Networks IJCNN 2009 %D 2009 %T Facial expression recognition based on Liquid State Machines built of alternative neuron models %A Beata J. Grzyb %A Eris Chinellato %A Wojcik, G. M. %A Kaminski, W. A. %B Proc. International Joint Conference on Neural Networks IJCNN 2009 %G eng %R 10.1109/IJCNN.2009.5179025 %0 Book Section %B Bioinspired Applications in Artificial and Natural Computation, LNCS 5602 %D 2009 %T Toward an Integrated Visuomotor Representation of the Peripersonal Space %A Eris Chinellato %A Beata J. Grzyb %A Patrizia Fattori %A Angel P. del Pobil %E J. Mira %E J. M. Ferrandez %E J.R. Alvarez Sánchez %E F. de la Paz %E J. Toledo %B Bioinspired Applications in Artificial and Natural Computation, LNCS 5602 %P 314–323 %G eng %R 10.1007/978-3-642-02267-8_34 %0 Conference Paper %B Proc. International Joint Conference on Neural Networks IJCNN 2009 %D 2009 %T Which model to use for the Liquid State Machine? %A Beata J. Grzyb %A Eris Chinellato %A Wojcik, G. M. %A Kaminski, W. A. %B Proc. International Joint Conference on Neural Networks IJCNN 2009 %G eng %R 10.1109/IJCNN.2009.5178822 %0 Conference Paper %D 2008 %T Brain Mechanisms for Robotic Object Pose Estimation %A Eris Chinellato %A Beata J. Grzyb %A Angel P. del Pobil %G eng %R 10.1109/IJCNN.2008.4634262 %0 Conference Paper %B Intl. Conf. on Climbing and Walking Robots, CLAWAR %D 2008 %T Robust grasping of 3{D} objects with stereo vision and tactile feedback %A Beata J. Grzyb %A Eris Chinellato %A Antonio Morales %A Angel P. del Pobil %B Intl. Conf. on Climbing and Walking Robots, CLAWAR %C Coimbra, Portugal %G eng