Vision-Based Behavior Acquisition For A Shooting Robot By Using A Reinforcement Learning

We propose a method which acquires a purposive behavior for a mobile robot to shoot a ball into the goal by using a vision-based reinforcement learning. 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. An action-value function in terms of state is to be learned. Image positions of a ball and a goal are used as a state variable which shows the effect of an action previously taken. After the learning process, the robot tries to carry a ball near the goal and to shoot it. Both computer simulation and real robot experiments are shown, and discussion on the role of vision in the context of the vision-based reinforcement learning is given.