论文信息 - Representing robot/environment interactions using probabilities: the "beam in the bin" experiment

Representing robot/environment interactions using probabilities: the "beam in the bin" experiment

The paper presents a very simple robotic experiment to illustrate how probabilistic reasoning may be used for sensory motor systems. We show how our robot may learn internal representations of its interactions with the environment, how it may predict the sensory result of a given action, how it may generate motor command to reach a wished sensory situation, how it may recognize different status and novel conditions and finally how it may behave consistently to simultaneously explore and exploit its environment.

E. Mazer | P. Bessiere | E. Dedieu

[1] R. T. Cox. The Algebra of Probable Inference , 1962 .

[2] E. Jaynes. On the rationale of maximum-entropy methods , 1982, Proceedings of the IEEE.

[3] Jan M. Van Campenhout,et al. Maximum entropy and conditional probability , 1981, IEEE Trans. Inf. Theory.

[4] Shinji Maeda. Improved articulatory models , 1988 .

[5] R. T. Cox. Probability, frequency and reasonable expectation , 1990 .

[6] Rodney W. Johnson,et al. Axiomatic derivation of the principle of maximum entropy and the principle of minimum cross-entropy , 1980, IEEE Trans. Inf. Theory.

[7] Claudine Robert. AN ENTROPY CONCENTRATION THEOREM: APPLICATIONS IN ARTIFICIAL INTELLIGENCE AND DESCRIPTIVE STATISTICS , 1990 .

[8] Pierre Bessière. Towards a synthetic cognitive paradigm: probabilistic inference , 1991 .

[9] David Miller. Review: Richard T. Cox, Probability, Frequency and Reasonable Expectation; Richard T. Cox, The Algebra of Probable Inference , 1972 .

[10] R. Johnson,et al. Properties of cross-entropy minimization , 1981, IEEE Trans. Inf. Theory.

[11] John E. Shore,et al. Relative Entropy, Probabilistic Inference, and AI , 1985, UAI.