This paper describes the development of a chess-playing robot called MarineBlue. This robot consists of three components: a computer vision component to recognize chess board situations, a chess engine component to compute new moves and a robot control component to execute these moves by means of a robot arm. In the paper, we focus on the algorithms that have been used to implement the computer vision and robot control components. The MarineBlue robot is fully autonomous, in the sense that it can recognize the moves done by a user, calculate a move in response to the user's move and control a robot arm to perform this calculated move. The robot that was used to develop MarineBlue is a low-cost, educational robot, which results in a cost-effective and compact chess-playing robot.
展开▼
