抄録
We suggest robot motion adaptation method against environmental changes for service robots. Several motions such as walking, dancing, demonstration and so on are described with time series patterns. These motions are optimized with the architecture of robot and under certain surrounding environment. Under unknown environment, robot cannot achieve their tasks. We propose motion generation system based on heuristic search with histories of internal sensor values. New motion patterns are searched under unknown environment based on self-evaluation function. Self-evaluation function is composed of difference of internal sensor values between typical environment and unknown environment. New motion patterns are generated to maximize self-evaluation function without external information such as run length. Experimental results show that the possibility to adapt autonomously the patterned motions to environmental changes.
