視覚に基づく強化学習によるロボットの行動獲得

概要

論文の詳細を見る
We propose a method which acquires a purposive behavior for a mobile robot to shoot a ball into the goal by using the Q-learning, one of the reinforcement learning methods. A mobile robot (an agent) does not need to know any parameters of the 3-D environment or its kinematics/dynamics. Information about the changes of the environment is only the image captured from a single TV camera mounted on the robot. Image positions of the ball and the goal are used as a state variable which shows the effect of an action taken by the robot during the learning process. After the learning process, the robot tries to carry a ball near the goal and to shoot it. Computer simulation is used not only to check the validity of the method but also to save the learning time on the real robot. The real robot succeeded in shooting a ball into the goal using the learned policy transferred to it.
社団法人日本ロボット学会の論文
1995-01-15