Bayesian Programming and Hierarchical Learning in Robotics

Abstract : This paper presents a new robotic programming environment based on the probability calculus. We show how reactive behaviours, like obstacle avoidance, contour following, or even light following, can be programmed and learned by a Khepera robot with our system. We further demonstrate that behaviours can be combined either by programmation or learning. A homing behaviour is thus obtained by combining obstacle avoidance and light following.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-00019361
Contributor : Pierre Bessiere <>
Submitted on : Monday, September 11, 2006 - 9:21:35 AM
Last modification on : Thursday, February 7, 2019 - 4:31:10 PM
Long-term archiving on : Monday, September 17, 2012 - 12:10:47 PM

Identifiers

  • HAL Id : hal-00019361, version 1

Collections

IMAG | UGA

Citation

Julien Diard, Olivier Lebeltel. Bayesian Programming and Hierarchical Learning in Robotics. 2000, 10p. ⟨hal-00019361⟩

Share

Metrics

Record views

140

Files downloads

107