Simple EMG-driven musculoskeletal model enables consistent control performance during path tracing tasks

Consistent, robust performance is critical for the utility and user-acceptance of neurally-controlled powered upper limb prostheses. We preliminarily evaluated the performance consistency of an electromyography (EMG)-driven controller based on a two degree-of-freedom musculoskeletal hand model, whose simplified structure is more practical for real-time prosthesis control than existing, complex models. Parameters of four virtual muscles were computed by numerical optimization from an able-bodied subject's kinematic and EMG data collected during wrist and metacarpophalangeal (MCP) flexion/extension movements. The subject attempted to trace a series of paths of different complexity (straight and curved) with the fingertip of a virtual hand displayed on a computer screen; the straight-path tracing tasks were repeated on a second test day to evaluate performance consistency over time. The subject's tracing accuracy during the tasks was consistent both between tasks of varying complexity (i.e. straight vs curved) and between test days when tracing the straight paths. Additionally, task duration, straightness, and smoothness did not significantly differ between the two straight-path test days. The consistent performance between days was achieved even with a very short (~15 seconds) calibration period to re-normalize EMG. The subject also coordinated movements of the wrist and MCP joints simultaneously during the task, much like with healthy, intact limb movement. Our promising results suggest that a musculoskeletal model-based controller may provide consistent and effective performance across a range of operating conditions, making it potentially practical for prosthesis control. Further research is needed to determine whether musculoskeletal model-based control (1) is effective for executing real-world tasks, and (2) can be extended to populations with neuromuscular impairment (e.g. amputation).