29P-B-6 車両型ロボットの経路探索に関する研究(知的システム,一般講演)

抄録

Recently, rapid progress is being made in the autonomous driving technology of vehicles. However, it cannot hope to compete with that of human being. Especially, it is quite difficult to autonomously drive complicated vehicles like trailer trucks in the environment in which many obstacles are placed. Why human expert can execute such complicated tasks- We consider that neither indiscriminate learning alone nor deliberation alone are sufficient. Indiscriminate learning without deliberation cannot execute complicated tasks. On the other hand, deliberation without learning consumes huge time. In this paper, we propose a system in which learning and deliberation are fused, and use it for the path planning of the trailer truck.