Doodbot: A Human-Machine Chess-Playing System Based on Edge-Assisted Manipulator

Manipulators have been widely adopted in realistic scenarios like industrial manufacturing, given their many degrees of freedom and extendability. However, under non-ideal environments, the autonomous human-machine interaction of manipulators is still a challenging problem. Moreover, despite numerous advanced methods for environmental perception and planning control, deploying these intricate methods directly to manipulators with limited resources remains difficult. This paper proposes Doodbot, an edge computing assisted manipulator system for human-machine chess-playing. Under the hood, Doodbot makes a geometric model for the manipulator and adopts a model predictive control method to realize the rolling optimal control of the manipulator. Furthermore, Doodbot deploys a hybrid chess-board recognition algorithm combining traditional line detection and convolutional neural network-based image recognition, thus enjoying both the adaptiveness of the conventional method and the high recognition performance of the deep neural network. These computing tasks are offloaded to an edge node in proximity for computing capability augmentation, avoiding long-delayed execution on resource-limited manipulators. The feasibility and robustness of Doodbot are verified through realistic prototype system implementation. The experimental results show that Doodbot has improved the accuracy of chessboard perception by up to 31%. In addition, it can also correctly plan the motion trajectory of the robotic arm and reduce control errors by 36%. A video demo of Doodbot on a real robotic arm can be found on https://ykqm.jyen.top/index.php/s/9q2qH4RajdDffPB.