Conceptual design and implementation of arm wrestling robot

In this paper, we develop a novel robotic arm wrestling system integrated with mechanical arm, elbow/wrist force sensors, servo motor, encoder, 3-D MEMS accelerometer, and USB camera. The arm wrestling robot (AWR) is intended to play arm wrestling game with real human on a table for entertainment. The designing scenario of the prototype model's hardware is performed. Elbow/wrist force sensors, as a crucial device in the force sensing system, are described in details. Software is developed for device driven and interface. The surface electromyographic (EMG) signals from the upper limb are sampled when a real player competes with the force testing system. By using the method of wavelet packet transformation (WPT), the high-frequency noises can be eliminated effectively and the characteristics of EMG signals can be extracted. Artificial neural network is adopted to estimate the elbow joint torque. The effectiveness of the humanoid algorithm using torque control estimated via WRT and neural network is confirmed by experiments.