Muscle Synergy Priors Enhance Biomechanical Fidelity in Predictive Musculoskeletal Locomotion Simulation

TL;DR

This paper introduces a reinforcement learning framework constrained by muscle synergies, which improves the biomechanical realism and generalization of simulated human locomotion across various conditions.

Contribution

It presents a physiology-informed reinforcement learning approach that incorporates muscle synergies to enhance the accuracy of predictive musculoskeletal locomotion simulations.

Findings

Reduced non-physiological knee kinematics

Simulated ground reaction forces match human data

Muscle activation timing aligns with variability in humans

Abstract

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.