Multiagent team formation performed by operant learning: an animat approach

Author

Gutnisky, D.A. ; Zelmann, R. ; Zanutto, B.S.

fYear

0

fDate

0-0 0

Firstpage

2944

Lastpage

2950

Abstract

An animat approach to dynamic team formation in a group of distributed robots is studied. The goal is that robots learn to align with the others in order to form a row or a column without having communication among them, just local sensing and a reinforcement signal. The action of the robot is controlled by a biologically plausible neural network model of operant learning. The remarkable performance achieved by the proposed model allows the building of new artificial intelligence agents based on neurobiology, psychology and ethology research.

Keywords

artificial life; collision avoidance; learning (artificial intelligence); multi-agent systems; multi-robot systems; neural nets; animat approach; artificial Intelligence agent; distributed robot; multiagent team formation; neural network; operant learning; Animation; Artificial intelligence; Artificial neural networks; Biological control systems; Biological system modeling; Communication system control; Learning; Psychology; Robot control; Robot sensing systems; Multiagent System; Neural Networks; Operant behavior; Reinforcement Learning;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2006. IJCNN '06. International Joint Conference on

Conference_Location

Vancouver, BC

Print_ISBN

0-7803-9490-9

Type

conf

DOI

10.1109/IJCNN.2006.247228

Filename

1716498