作者: Seiji Yamada
关键词: Evolutionary algorithm 、 Obstacle avoidance 、 Artificial intelligence 、 Robot 、 Adaptive system 、 Computer science 、 Genetic algorithm 、 Artificial neural network 、 Mobile robot
摘要: This paper describes an evolutionary way to lean behaviors of a mobile robot for recognizing environments. We have proposed AEM (Action-based Environment Modeling) which is appropriate approach simple recognize environments, and made experiments using real robot. The suitable been described by human designer. However the design very difficult them because huge search space. Thus we propose method such genetic algorithm make in recognizes environments with different structures. As results, found out that promising automatically acquire AEM.