Interactive Robot for Playing Russian Checkers

Abstract

Human–robot interaction in board games is a rapidly developing field of robotics. This paper presents a robot capable of playing Russian checkers designed for entertaining, training, and research purposes. Its control program is based on a novel unsupervised self-learning algorithm inspired by AlphaZero and represents the first successful attempt of using this approach in the checkers game. The main engineering challenge in mechanics is to develop a board state acquisition system non-sensitive to lighting conditions, which is achieved by rejecting computer vision and utilizing magnetic sensors instead. An original robot face is designed to endow the robot an ability to express its attributed emotional state. Testing the robot at open-air multiday exhibitions shows the robustness of the design to difficult exploitation conditions and the high interest of visitors to the robot.

Playing Checkers with an Intelligent and Collaborative Robotic System

“…This issue is easily solved by knowing the starting board configuration and tracking the game state. Another example is described in [20], where the authors propose to place Hall sensors under squares for detecting the pieces on the board. Hall sensors recognize the presence and magnitude of a magnetic field.…”

“…Another method to reduce computation time is illustrated in [24], where the authors develop a hybrid tree search algorithm on parallel CPU and GPU in order to exploit the full potential of the computer. A method different from the tree search is to adopt a neural network, as outlined in [20].…”