Adaptive evolutionary planner/navigator for mobile robots

Based on evolutionary computation (EC) concepts, we developed an adaptive Evolutionary Planner/Navigator (EP/N) as a novel approach to path planning and navigation. The EP/N is characterized by generality, exibility, and adaptability. It uni es o -line planning and on-line planning/navigation processes in the same general and exible evolutionary algorithm which (1) accommodates di erent optimization criteria and changes in these criteria, (2) incorporates various types of problem-speci c domain knowledge, (3) enables good trade-o s among near-optimality of paths, high planning e ciency, and e ective handling of unknown obstacles. More importantly, the EP/N can selftune its performance for di erent task environments and changes in such environments, mostly through adapting probabilities of its operators and adjusting paths constantly even during a robot's motion towards the goal.