Muscle Synergy Priors Enhance Biomechanical Fidelity in Predictive Musculoskeletal Locomotion Simulation
This work addresses the problem of enhancing biomechanical accuracy in locomotion simulations for biomechanics and robotics researchers, representing an incremental improvement by integrating neurophysiological constraints into existing methods.
The researchers tackled the challenge of predictive musculoskeletal simulation in human locomotion by embedding muscle synergy priors into a reinforcement learning framework, resulting in stable gait across variable speeds and slopes with improved biomechanical fidelity, such as reduced non-physiological knee kinematics and strong correlation of ground reaction forces with human measurements.
Human locomotion emerges from high-dimensional neuromuscular control, making predictive musculoskeletal simulation challenging. We present a physiology-informed reinforcement-learning framework that constrains control using muscle synergies. We extracted a low-dimensional synergy basis from inverse musculoskeletal analyses of a small set of overground walking trials and used it as the action space for a muscle-driven three-dimensional model trained across variable speeds, slopes and uneven terrain. The resulting controller generated stable gait from 0.7-1.8 m/s and on $\pm$ 6$^{\circ}$ grades and reproduced condition-dependent modulation of joint angles, joint moments and ground reaction forces. Compared with an unconstrained controller, synergy-constrained control reduced non-physiological knee kinematics and kept knee moment profiles within the experimental envelope. Across conditions, simulated vertical ground reaction forces correlated strongly with human measurements, and muscle-activation timing largely fell within inter-subject variability. These results show that embedding neurophysiological structure into reinforcement learning can improve biomechanical fidelity and generalization in predictive human locomotion simulation with limited experimental data.