A software architecture for behavioral control strategies of autonomous systems

The authors deal with the execution of several tasks for mobile robots while exhibiting various primitive behaviors in a simultaneous or concurrent fashion. The architecture allows for learning to take place, and at the execution level it incorporates the experience gained in executing primitive behaviors as well as the overall task. Some empirical rules are provided for the appropriate mixture of primitive behaviors to produce tasks. The architecture has been implemented in OPMOR, a simulation environment for mobile robots, and several results are presented. The performance of the architecture is excellent