Abstract
This paper discusses the emergence of sensorimotor coordination for ESCHeR, a 4DOF redundant foveated robot-head, by interaction with its environment. A feedback-error-learning (FEL)-based distributed control provides the system with explorative abilities with reflexes constraining the learning space. A Kohonen network, trained at run-time, categorizes the sensorimotor patterns obtained over ESCHeR's interaction with its environment, enables the reinforcement of frequently executed actions, thus stabilizing the learning activity over time. We explain how the development of ESCHeR's visual abilities (e.g., gaze fixation and saccadic motion), from a context-free reflex-based control process to a context-dependent, pattern-based sensorimotor coordination can be related to the Piagetian ‘stage theory’.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Bajcsy, R. and Campos, M. 1992. Active and exploratory perception. CVGIP: Image Understanding, 56(1):31-40.
Brown, C. 1988. The Rochester Robot Technical Report TR-257, University of Rochester, Rochester, USA.
Chow, M. and Teeter, J. 1994. An analysis of weight decay as a methodology of reducing three-layer feed-forward artificial neural networks for classification problems. In Proc. IEEE International Conference on Neural Networks, pp. 600-605.
Coombs, D. 1992. Real-time gaze holding in binocular robot vision. Doctoral dissertation (also available as TR-415), Department of Computer Science, University of Rochester, Rochester, USA.
Gomi, H. and Kawato, M. 1993. Neural network control for a closed-loop system using feedback-error-learning. Neural Networks, 6: 933-946.
Jordan, M.I. 1990. Motor learning and the degree of freedom problem. In Attention and Performance, M. Jeannerod (Ed.), vol. 13, pp. 796-836.
Jordan, M.I. 1992. Computational aspects of motor control and motor learning. Technical Report TR-9206. Massachusetts Institute of Technology, Department of Brain and Cognitive Sciences, USA.
Jordan, M.I. and Rosenbaum, D.A. 1989. Action. In Foundations of Cognitive Science, M.I. Posner (Ed.), MIT Press: Cambridge, MA.
Kawato, M., Furukawa, K., and Suzuki, R. 1987. A hierarchical neural-network model for control and learning of voluntary movement. Biological Cybernetics, 57:169-185.
Kawato, M. and Gomi, H. 1992. A computational model of four regions of the cerebellum based on feedback-error learning. Biological Cybernetics, 68:95-103.
Kohonen, T., Hynninen, J., Kangas, J., and Laaksonen, J. 1995. SOM-PAK: The self-organizing map program package. Technical Report, Helsinki University of Technology, Laboratory of Computer and Information Science, Rakentajanaukio 2 C, SF-02150 Espoo, Finland.
Kraaijveld, M.A., Mao, J., and Jain, A.K. 1992. A nonlinear projection method based on kohonen's topology preserving maps. In Proc. International Conference on Pattern Recognition, Los Alamitos, CA, pp. 41-45.
Kuniyoshi, Y. 1994. The science of imitation—Towards physically and socially grounded intelligence. RWC Technical Report, TR-94001.
Kuniyoshi, Y., Kita, N., Sugimoto, K., Nakamura, S., and Suehiro, T. 1995a. A foveated wide angle lens for active vision. In Proc. IEEE International Conference on Robotics and Automation, Japan, pp. 2982-2985.
Kuniyoshi, Y., Kita, N., Rougeaux, S., and Suehiro, T. 1995b. Active stereo vision system with foveated wide angle lenses. In Recent Developments in Computer Vision, S.Z. Li, D.P. Mital, E.K. Teoh, and H. Wang (Eds.), Lecture Notes in Computer Science 1035, Springer-Verlag, pp. 191-200.
Lucas, B. and Kanade, T. 1981. An iterative image registration technique with an application to stereo vision. In Proc. DARPA Image Understanding Workshop, pp. 121-130.
Meltzoff, A.N. and Moore, M.K. 1989. Imitation in newborn infants: Exploring the range of gestures imitated and the underlying mechanisms. Developmental Psychology, 25(6):954- 962.
Murray, D.W., Bradshaw, K.J., McLauchlan, P.F., Reid, I.D., and Sharkey, P.M. 1995. Driving saccade to pursuit using image motion. International Journal of Computer Vision.
Nordlund P. and Uhlin, T. 1995. Closing the loop: Detection and pursuit of a moving object by a moving observer. Technical Report CVAP-175-95-7-173, Computational Vision and Active Perception Laboratory, Royal Institute of Technology, S-100 44 Stockholm, Sweden.
Piaget, J. 1962. Play, Dreams and Imitation in Childhood, W.W.Norton: New York.
Rougeaux, S., Kita, N., Kuniyoshi, S., Sakane, S., and Chavand, F. 1994. Binocular tracking based on virtual horopters. IEEE Proc. International Conference on Intelligent Robots and Systems, Munich, Germany, pp. 2052-2057.
Rougeaux, S. and Kuniyoshi, Y. 1997. Velocity and disparity cues for robust real-time binocular tracking. IEEE Proc. Computer Vision and Pattern Recognition, Puerto-Rico, pp. 1-6.
Rumelhart, D.E., Hinton, G.E., and Williams, R.J. 1986. Learning representations by back-propagating errors. Nature, 323:533- 536.
Sandini, G. and Tagliaso, V. 1980. An anthropomorphic retina-like structure for scene analysis. Computer Graphics and Image Processing, 14(3):365-372.
Smagt, P. and Krose, B.J.A. 1991. A real-time learning neural robot controller. In Proc. International Conference on Neural Networks, Espoo, Finland, pp. 351-356.
Thelen, E. and Smith, L. 1994. A Dynamic Systems Approach to the Development of Cognition and Action, MIT Press: Cambridge, MA, Bradford Books.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Berthouze, L., Kuniyoshi, Y. Emergence and Categorization of Coordinated Visual Behavior Through Embodied Interaction. Autonomous Robots 5, 369–379 (1998). https://doi.org/10.1023/A:1008818608164
Issue Date:
DOI: https://doi.org/10.1023/A:1008818608164