Musculoskeletal model predicts multi-joint wrist and hand movement from limited EMG control signals

Electromyography (EMG)-driven human-machine systems permit volitional control of external devices, including powered prosthetic arms. However, current control schemes are either non-intuitive to operate or lack robustness across different arm postures and dynamics, partly because these methods did not incorporate the full knowledge of biological movement production. In this study, we developed and evaluated a new musculoskeletal model to predict hand and wrist motion based on surface EMG signals. Kinematic and EMG data were collected from an able-bodied subject while performing wrist and metacarpophalangeal (MCP) joint movements with either a fixed or random speed in two static upper limb postures. A part of data collected in one posture was used to develop the model with four virtual muscles. Four parameters were optimized for each of four muscles in one posture. The model kinematic predictions were evaluated offline using the other part of the data recorded from both postures. Mean (±SD) RMS errors in predicting the joint movement were significantly lower at the MCP joint (10.1±2.5°) than at the wrist (23.5±5.2°) (p<;0.05). At both the wrist and MCP joints, the model predicted the timing and trend of joint movements reasonably well across postures and for both simple (fixed speed, single joint) and complex (random speed, simultaneous, multi-joint) movements. The results implied that our EMG-driven musculoskeletal model was promising for predicting simultaneous joint motions without significant posture and dynamics dependency. Additional engineering efforts are still needed to improve the musculoskeletal model for various human-machine interfacing applications.