Musculoskeletal Motion Imitation for Learning Personalized Exoskeleton Control Policy in Impaired Gait

arXiv cs.RO / 4/13/2026

💬 OpinionSignals & Early TrendsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper proposes a device-agnostic framework that uses physiologically plausible musculoskeletal simulation combined with reinforcement learning to learn personalized control policies for lower-limb exoskeletons without extensive data collection or iterative optimization.
The learned policies are intended to reproduce both healthy locomotion dynamics and clinically observed compensatory strategies under targeted muscular deficits, aiming to unify healthy and pathological gait modeling.
Without task-specific tuning, the method reportedly produces hip and ankle assistive torque profiles that match state-of-the-art profiles validated in human experiments and reduces metabolic cost across walking speeds in simulation.
For impaired-gait simulations, it generates deficit-specific asymmetric assistance that improves energetic efficiency and bilateral kinematic symmetry without requiring explicit prescription of a target gait pattern.
Overall, the work argues that reinforcement learning over plausible biomechanics could reduce or eliminate the need for extensive physical trials when personalizing exoskeleton control for clinical populations.

Abstract

Designing generalizable control policies for lower-limb exoskeletons remains fundamentally constrained by exhaustive data collection or iterative optimization procedures, which limit accessibility to clinical populations. To address this challenge, we introduce a device-agnostic framework that combines physiologically plausible musculoskeletal simulation with reinforcement learning to enable scalable personalized exoskeleton assistance for both able-bodied and clinical populations. Our control policies not only generate physiologically plausible locomotion dynamics but also capture clinically observed compensatory strategies under targeted muscular deficits, providing a unified computational model of both healthy and pathological gait. Without task-specific tuning, the resulting exoskeleton control policies produce assistive torque profiles at the hip and ankle that align with state-of-the-art profiles validated in human experiments, while consistently reducing metabolic cost across walking speeds. For simulated impaired-gait models, the learned control policies yield asymmetric, deficit-specific exoskeleton assistance that improves both energetic efficiency and bilateral kinematic symmetry without explicit prescription of the target gait pattern. These results demonstrate that physiologically plausible musculoskeletal simulation via reinforcement learning can serve as a scalable foundation for personalized exoskeleton control across both able-bodied and clinical populations, eliminating the need for extensive physical trials.