Cooperative learning and planning for multiple robots

Author

van der Zwaan, S. ; Moreira, José A A ; Lima, Pedro U.

Author_Institution

Inst. de Sistema e Robotica, Inst. Superior Tecnico, Lisbon, Portugal

fYear

2000

fDate

2000

Firstpage

351

Lastpage

356

Abstract

The paper deals with the the subject of learning and planning for real mobile robots, using Sutton´s (1991) Dyna algorithm. The Dyna algorithm integrates reinforcement learning, planning and reactive execution. We present an extension of the Dyna algorithm which includes symmetric and cooperative learning with multiple robots. We applied the extended version of the algorithm to a population of two real robots. Practical problems associated with the implementation of the algorithm on a real setup are solved. Results obtained from simulations and real experiments are presented and discussed

Keywords

cooperative systems; intelligent control; learning (artificial intelligence); mobile robots; multi-robot systems; path planning; Dyna algorithm; cooperative learning; cooperative planning; multiple robots; reactive execution; reinforcement learning; Control systems; Costs; Density estimation robust algorithm; Dynamic programming; Learning; Mobile robots; Navigation; Orbital robotics; Robot control; State-space methods;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control, 2000. Proceedings of the 2000 IEEE International Symposium on

Conference_Location

Rio Patras

ISSN

2158-9860

Print_ISBN

0-7803-6491-0

Type

conf

DOI

10.1109/ISIC.2000.882949

Filename

882949