Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Emergent synthesis of motion patterns for locomotion robots
Autore:
Svinin, MM; Yamada, K; Ueda, K;
Indirizzi:
RIKEN, Bio Mimet Control Res Ctr, Moriyama Ku, Nagoya, Aichi 4630003, Japan RIKEN Nagoya Aichi Japan 4630003 oriyama Ku, Nagoya, Aichi 4630003, Japan Kobe Univ, Dept Mech Engn, Nada Ku, Kobe, Hyogo 6578501, Japan Kobe Univ Kobe Hyogo Japan 6578501 n, Nada Ku, Kobe, Hyogo 6578501, Japan
Titolo Testata:
ARTIFICIAL INTELLIGENCE IN ENGINEERING
fascicolo: 4, volume: 15, anno: 2001,
pagine: 353 - 363
SICI:
0954-1810(200110)15:4<353:ESOMPF>2.0.ZU;2-6
Fonte:
ISI
Lingua:
ENG
Soggetto:
6-LEGGED WALKING; OSCILLATORS; MECHANISMS; NETWORK;
Keywords:
locomotion robots; minimal simulation; gait patterns; emergence; reinforcement learning; classifier systems;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Engineering, Computing & Technology
Citazioni:
31
Recensione:
Indirizzi per estratti:
Indirizzo: Svinin, MM RIKEN, Bio Mimet Control Res Ctr, Moriyama Ku, Nagoya, Aichi 4630003, Japan RIKEN Nagoya Aichi Japan 4630003 Nagoya, Aichi 4630003, Japan
Citazione:
M.M. Svinin et al., "Emergent synthesis of motion patterns for locomotion robots", ARTIF INT E, 15(4), 2001, pp. 353-363

Abstract

Emergence of stable gaits in locomotion robots is studied in this paper. Aclassifier system, implementing an instance-based reinforcement-learning scheme, is used for the sensory-motor control of an eight-legged mobile robot and for the synthesis of the robot Pits. The robot does not have a prioriknowledge of the environment and its own internal model. It is only assumed that the robot can acquire stable Gaits by learning how to reach a goal area. During the learning process the control system is self-organized by reinforcement signals. Reaching the coal area defines a global reward. Forward motion gets a local reward, while stepping back and falling down get a local punishment. As learning progresses, the number of the action rules in the classifier systems is stabilized to a certain level, corresponding to the acquired gait patterns. Feasibility of the proposed self-organized systemis tested under simulation and experiment. A minimal simulation model thatdoes not require sophisticated computational schemes is constructed and used in simulations. The simulation data, evolved on the minimal model of therobot, is downloaded to the control system of the real robot. Overall, of 10 simulation data seven are successful in running the real robot. (C) 2001Elsevier Science Ltd. All rights reserved.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 09/04/20 alle ore 07:42:55