Abstract
This paper studies the essential dynamical structure that arises in two different classes of learning of the sensory-based navigation, namely skill-based learning and model-based learning. In skill-based learning a robot learns navigational skills for a fixed navigational task such as homing, while in model-based learning a robot learns a model of the environment, then conducts planning on the model to reach an arbitrary goal. We formulated that the former is achieved by learning the state-action map, and the latter does by learning the forward model of the environment, using recurrent neural learning scheme. The analysis of the dynamical structure from the coupling of the internal neural dynamics and the environment showed that generation of the global attractor is crucial for both learning cases. Experiments were conducted using a mobile robot with a laser range sensor, which verified our assertions in a simple obstacle environment.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
R.D. Beer. A Dynamical System's Perspective on Agent-Environment Interaction. Artificial Intelligence, in press.
A. Elfes. Sonar-based Real-world Mapping and Navigation. IEEE Journal of Robotics and Automation, Vol. 3, pp. 249–265, 1987.
S. Harnad. The Symbol Grounding Problem. Physica D, Vol. 42, pp. 335–346, 1990.
M.I. Jordan and D. E. Rumelhart. Forward models: Supervised Learning with a Distal Teacher. Cognitive Science, Vol. 16, pp. 307–354, 1992.
O. Khatib. Real-time Obstacle Avoidance for Manipulators and Mobile Robots. The International Journal of Robotics Research, Vol. 5, No. 1, pp. 90–98, 1986.
Long-Ji Lin and T.M. Mitchell. Reinforcement Learning with Hidden States. In proc. of the Second International Conference on Simulation of Adaptive Behavior, 1992.
M. Mataric. Integration of Representation into Goal-driven Behavior-based Robot. IEEE Trans. Robotics and Automation, Vol. 8, pp. 304–312, 1992.
J.B. Pollack. The Induction of Dynamical Recognizers. Machine Learning, Vol. 7, pp. 227–252, 1991.
D.E. Rumelhart, G.E. Hinton, and R.J. Williams. Learning Internal Representations by Error Propagation. In D.E. Rumelhart and J.L. Mclelland, editors, Parallel Distributed Processing. MIT Press, Cambridge, MA, 1986.
L. Steels. Mathematical Analysis of Behavior Systems. In proc. of From Perception TO Action, 1994.
J. Tani and N. Fukumura. Learning Goal-directed Sensory-based Navigation of a Mobile Robot. Neural Networks, Vol. 7, No. 3, pp. 553–563, 1994.
J. Tani and N. Fukumura. Embedding a grammatical description in deterministic chaos: an experiment in recurrent neural learning. Biological Cybernetics, in press.
B. M. Yamauchi and R. D. Beer. Spatial Learning for Navigation in Dynamic Environment. IEEE Trans, on Systems, Man, and Cybernetics, in press.
S. Yuta and J. Iijima. State Information Panel for Inter-Processor Communication in an Autonomous Mobile Robot Controller. In proc. of the IEEE International Workshop on Intelligent Robots and Systems (IROS'90), 1990.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tani, J. (1995). Essential dynamical structure in learnable autonomous robots. In: Morán, F., Moreno, A., Merelo, J.J., Chacón, P. (eds) Advances in Artificial Life. ECAL 1995. Lecture Notes in Computer Science, vol 929. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-59496-5_338
Download citation
DOI: https://doi.org/10.1007/3-540-59496-5_338
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-59496-3
Online ISBN: 978-3-540-49286-3
eBook Packages: Springer Book Archive