The automatic generation of walking policies for a four-legged robot in a non-deterministic space


Abstract eng:
Both the automatic policies generation and its analysis for four legged walking robot is given in this contribution. Policies generation is based on state space search which is represented by a tree. The set of elementary production rules is used for tree generation, chosen with respect to obtain suitable tree complexity and algorithm response. Further the selection of tasks operators are discussed. Those operators represent the performance of basic movements of walking robot. Policy generation is made through the Antos-251-PT.txt.txt algorithm. The policies are continuously generated as short-time plans of robot movements.

Contributors:
Publisher:
Institute of Theoretical and Applied Mechanics, AS CR, v.v.i., Prague
Conference Title:
Conference Title:
ENGINEERING MECHANICS 2006
Conference Venue:
Svratka (CZ)
Conference Dates:
2006-05-15 / 2006-05-18
Rights:
Text je chráněný podle autorského zákona č. 121/2000 Sb.



Record appears in:



 Record created 2014-11-12, last modified 2014-11-18


Original version of the author's contribution as presented on CD, , paper No. 329. :
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)