Representation of behavioral history for learning in nonstationary conditions

A robot having to operate in nonstationary conditions needs to learn how to modify its control policy to adapt to the changing dynamics of the environ ment. Using the behavior-based approach to manage the interactions between the robot and its environment, we propose a method that models these intera ctions and adapts the selection of behaviors according to the history of be havior use. The learning and the use of this "Interaction Model" are valida ted using a vision- and sonar-based Pioneer I robot in the context of a mul ti-robot foraging task. Results show the effectiveness of the approach in t aking advantage of any regularities experienced in the world, leading to fa st and adaptable specialization for the learning robot. (C) 1999 Elsevier S cience B.V. All right reserved.