Trajectory generation for human-friendly behavior of partner robot using fuzzy evaluating interactive genetic algorithm

Abstract

This paper deals with a human-friendly trajectory generation using an interactive genetic algorithm for a partner robot. Human evaluation is very important for generating robotic behavior, but the structure of human evaluation is not clear beforehand. Therefore, a fuzzy state-value function is used for estimating the structure of human evaluation of a trajectory candidate generated by an interactive genetic algorithm. We apply a profit sharing plan based on human evaluation to update the state-value function. Some experimental results show the effectiveness of the proposed method.