Loading [MathJax]/extensions/TeX/ieeemacros.js
Quadruped robot obstacle negotiation via reinforcement learning | IEEE Conference Publication | IEEE Xplore

Quadruped robot obstacle negotiation via reinforcement learning


Abstract:

Legged robots can, in principle, traverse a large variety of obstacles and terrains. In this paper, we describe a successful application of reinforcement learning to the ...Show More

Abstract:

Legged robots can, in principle, traverse a large variety of obstacles and terrains. In this paper, we describe a successful application of reinforcement learning to the problem of negotiating obstacles with a quadruped robot. Our algorithm is based on a two-level hierarchical decomposition of the task, in which the high-level controller selects the sequence of foot-placement positions, and the low-level controller generates the continuous motions to move each foot to the specified positions. The high-level controller uses an estimate of the value function to guide its search; this estimate is learned partially from supervised data. The low-level controller is obtained via policy search. We demonstrate that our robot can successfully climb over a variety of obstacles which were not seen at training time
Date of Conference: 15-19 May 2006
Date Added to IEEE Xplore: 26 June 2006
Print ISBN:0-7803-9505-0
Print ISSN: 1050-4729
Conference Location: Orlando, FL

References

References is not available for this document.