A walk supervisor architecture for autonomous four-legged robots embedding real-time decision-making
R. Prajoux, L. de S.F. Martins
- Year
- 2002
- Citations
- 12
Abstract
This paper addresses the problem of walk control for legged robots, especially quadrupeds. The control is intended at locomotion level, i.e. at a rather low level in the overall control structure of the robot. The architecture of the corresponding walk supervisor is designed in view of being as versatile as possible, however the paper concerns more specifically the situations in which a dynamic control with fast adaptation to terrain irregularities is needed. The proposed architecture makes use of conventional closed-loop control, whose operation is supervised by a real-time reasoning system, implemented as a compiled rule-based module.
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002