Control architectures for autonomous mobile robots

The paper discusses issues related to the design of the control architecture of an autonomous robot capable of performing tasks efficiently and intelligently, i.e., in a manner adapted to its environment, to its own state and to the execution status of its task. We examine and criticize some of the arguments of the proponents of the "behavior based" approach to the design of control architectures. Based on our own developments and experimentations on indoor and outdoor mobile robot navigation, we show hour it is necessary to produce representations at several levels of abstraction, that are manipulated by adequate processes. We also show that deliberation is also necessary for the robot to anticipate events, take efficient decisions, and react adequately to asynchronous events.