Learning obstacle avoidance with an operant behavioral model

D. GUTNISKY, B.S. ZANUTTO

ARTIFICIAL LIFE

Mit Press

Lugar: Estados Unidos; Año: 2004 vol. 10 p. 65 - 81

1064-5462

Abstract ArtiŽcial intelligence researchers have been attracted by the idea of having robots learn how to accomplish a task, rather than being told explicitly.Reinforcement learning has been proposed as an appealing framework to be used in controlling mobile agents. Robot learning research, as well as research in biological systems, face many similar problems in order to display high ?exibility in performing a variety of tasks. In this work, the controlling of a vehicle in an avoidance task by a previously developed operant learning model (a form of animal learning) isstudied. An environment in which a mobile robot with proximity sensors has to minimize the punishment for colliding against obstacles is simulated. The results were compared with the Q-Learning algorithm, and the proposed model had better performance. In this way a new artiŽcial intelligence agent inspired by neurobiology, psychology, and ethology research is proposed.