LEARNING BASED CONTROL SYSTEM OF FOUR-LEGGED ROBOT

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26210%2F02%3APU30854" target="_blank" >RIV/00216305:26210/02:PU30854 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
čeština
Original language name
LEARNING BASED CONTROL SYSTEM OF FOUR-LEGGED ROBOT
Original language description
Possible discretization technique of the continuous state space of four-legged robot using simultaneous compositions of behaviors is described in this contribution. Compositions are generated by the instances of two basic controllers. The aim is to automatically develop the gait policy. Possible composition strategies are implemented through undeterministic state machine. In the machine design stage the number of both machine states and transitions could be essetially reduced using formal considerationss only. Furthermore machine transitions are evaluated by selected alternative of Q-learning to incrementally improve the estimation of the future benefit from single transitions. This technique results in simultaneous activations of controller compositions instances with the highest estimation of the future benefit.
Czech name
LEARNING BASED CONTROL SYSTEM OF FOUR-LEGGED ROBOT
Czech description
—

Publication year
2002
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Inženýrská mechanika 2002
ISBN
80-214-2109-6
ISSN
—
e-ISSN
—
Number of pages
2
Pages from-to
9-10
Publisher name
Institute of Mechanics of Solids, Faculty of Mechanical Engineering, Brno University of Technology
Place of publication
Brno
Event location
Svratka
Event date
May 13, 2002
Type of event by nationality
CST - Celostátní akce
UT code for WoS article
—

Similar results(10)