Abstract
We propose our scenario towards the first few stages of understanding the basic principles of human-robot interface. A problem that is applicable across many tasks. We view the problem as the structure of coupling between interaction dynamics of agents. Through a case study of a full body dynamic motion of a simulated humanoid, we point out that there is a sparse global structure, defined as boundaries of dynamics. We propose that an intervention to the current interaction dynamics, as well as information extraction is best made on such boundaries. Then, through learning experiments with mobile robot navigation, and an active vision system, we show non-physical forms of an emergent global structure. They emerged from interferences between multiple sensory-motor flows. A neural network for spatio-temporal correlation learning is presented as a candidate mechanism for capturing and retrieving the global structure. Lastly, an experiment with our humanoid robot on visual mimicking of human motion is briefly presented as an integrating platform.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
K. Ikeuchi and T. Suehiro. Toward an assembly plan from observation. i. task recognition with polyhedral objects. IEEE Trans. Robotics and Automation, 10(3): 368–385, June 1994.
Y. Kuniyoshi, M. Inaba, and H. Inoue. Learning by watching: Extracting reusable task knowledge from visual observation of human performance. IEEE Trans. Robotics and Automation, 10 (5), 1994.
H. Miyamoto, S. Schaal, F. Gandolfo et al. A kendama learning robot based on bi-directional theory. Neural Networks, 9: 1281–1302, 1996.
I. Eguchi, T. Sato, and T. Mori. Visual behavior understanding as a care function of computerized description of medical care. In Proc. 1996 IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS96), pages 1573–1578, November 1996.
H. Kobayashi and F. Hara. Dynamic recognition of basic facial expressions by discrete-time recurrent neural network. In Proc. Int. Joint Conf. on Neural Networks (IJCNN), pages 155–158, 1993.
Y. Kuniyoshi and A. Nagakubo. Humanoid as a research vehicle into flexible complex interaction. In Proc. IEEE Int. Conf. Intelligent Robots and Systems, pages 811–819, 1997.
T. Sato and S. Hirai. Language-aidedrobotic teleoperation system (tails) for advanced teleoperation. IEEE J. Robotics and Automation, 3 (5): 476–481, October 1987.
S. Lee. Intelligent sensing and control for advanced teleoperation. IEEE Control Systems Magazine, 13 (3): 19–28, June 1993.
B. Brunner, K. Arbter, and G. Hirzinger. Task directed programming of sensor based robots. In Proc. IEEFJRSJ/GI Int. Conf. Intelligent Robots and Systems (IROS), pages 1080–1087, 1994.
T. Mao. From Gestures to Language. Shin’yosha, 1992. (In Japanese).
Y. Kuniyoshi. Behavior matching by observation for multi-robot cooperation. In G. Giralt and G. Hirzinger, editors, Robotics Research — The Seventh International Symposium, pages 343–352. Springer, 1996.
G. Taga, Y. Yamaguchi, and H. Shimizu. Self-organized control of bipedal locomotion in unpredictable environment. Biol. Cybern, 65: 147–159, 1991.
A. A. Rizzi and D. E. Koditschek. Further progress in robot juggling: The spatial two-juggle. In Proc. IEEE Int. Conf. Robotics and Automation, pages 919–924, 1993.
S. Miyakoshi, G. Taga, Y. Kuniyoshi et al. Three dimensional bipedal step** motion using neural oscillators — towards humanoid motion in the real world. In Proc. IEEE Int. Conf. Intelligent Robots and Systems, 1998.
A. Zelinsky and Y. Kuniyoshi. Learning to coordinate behaviours for robot navigation. Advanced Robotics, 10(2): 143–159, 1996.
Y. Kuniyoshi and L. Berthouze. Neural learning of embodied interaction dynamics. Neural Networks, 11 (7–8): 1259–1276, 1998.
Y. Kuniyoshi, N. Kita, S. Rougeaux et al. Active stereo vision system with foveated wide angle lenses. In S.Z. Li, D.P. Mital, E.K. Teoh, and H. Wang, editors, Recent Developments in Computer Vision, Lecture Notes in Computer Science 1035. Springer–Verlag, 1995. ISBN 3–540–60793–5.
Y. Kuniyoshi, N. Kita, K. Sugimoto et al. A foveated wide angle lens for active vision. In Proc. IEEE Int. Conf. Robotics and Automation, 1995.
S. Rougeaux and Y. Kuniyoshi. Robust real-time tracking on an active vision head. In Proc. IEEE Int. Conf. Intelligent Robot and Systems (IROS), pages 873–879, 1997.
L. Berthouze and Y. Kuniyoshi. Emergence and categorization of coordinated visual behavior through embodied interaction. Autonomous Robots, 5: 369–379, 1998. to appear.
M. Kawato. Feedback-error-learning neural network for supervised motor learning. In R. Eckmiller, editor, Advanced Neural Computers, pages 365–372. Elsevier, Amsterdam, 1990.
R. A. Jacobs, M. I. Jordan, S. J. Nowlan et al. Adaptive mixtures of local experts. Neural Computation, 3: 79–87, 1991.
J. Tani and S. Nolfi. Learning to perceive the world as articulated: an approach for hierarchical learning in sensory-motor systems. In R. Pfeifer, B. Blumberg, J.A. Meyer, and S.W. Wilson, editors, Proc. Int. Conf. on Society of Adaptive Behavior (SAB), pages 270–279. MIT Press, 1998.
Y. Shigematsu, G. Matsumoto, and M. Ichikawa. Temporal learning rule and dynamic neural networks model. International Conference on Brain Processes, Theories and Models, pages 164–172, 1995.
J. Piaget. Play, Dreams and Imitation in Childhood. W. W. Norton, New York, 1962. (Original work published 1945).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag London
About this paper
Cite this paper
Kuniyoshil, Y., Nagakubo, A., Berthouze, L., Cheng, G. (2000). Interfacing Agents through Boundaries of Interaction Dynamics. In: Hollerbach, J.M., Koditschek, D.E. (eds) Robotics Research. Springer, London. https://doi.org/10.1007/978-1-4471-0765-1_35
Download citation
DOI: https://doi.org/10.1007/978-1-4471-0765-1_35
Publisher Name: Springer, London
Print ISBN: 978-1-4471-1254-9
Online ISBN: 978-1-4471-0765-1
eBook Packages: Springer Book Archive