Learning Hip Exoskeleton Control Policy via Predictive Neuromusculoskeletal Simulation

TL;DR

This paper introduces a simulation-based neuromusculoskeletal framework for developing hip exoskeleton controllers that generalize across conditions, reducing reliance on extensive real-world data and enabling effective transfer to hardware.

Contribution

The study presents a novel physics-based simulation approach for training exoskeleton control policies entirely in silico, with successful transfer to real hardware without additional tuning.

Findings

Simulation-trained policies reduce muscle activation and joint power.

Assistance benefits increase with walking speed.

High correlation between simulated and real assistance profiles.

Abstract

Developing exoskeleton controllers that generalize across diverse locomotor conditions typically requires extensive motion-capture data and biomechanical labeling, limiting scalability beyond instrumented laboratory settings. Here, we present a physics-based neuromusculoskeletal learning framework that trains a hip-exoskeleton control policy entirely in simulation, without motion-capture demonstrations, and deploys it on hardware via policy distillation. A reinforcement learning teacher policy is trained using a muscle-synergy action prior over a wide range of walking speeds and slopes through a two-stage curriculum, enabling direct comparison between assisted and no-exoskeleton conditions. In simulation, exoskeleton assistance reduces mean muscle activation by up to 3.4% and mean positive joint power by up to 7.0% on level ground and ramp ascent, with benefits increasing systematically with walking speed. On hardware, the assistance profiles learned in simulation are preserved across matched speed-slope conditions (r: 0.82, RMSE: 0.03 Nm/kg), providing quantitative evidence of sim-to-real transfer without additional hardware tuning. These results demonstrate that physics-based neuromusculoskeletal simulation can serve as a practical and scalable foundation for exoskeleton controller development, substantially reducing experimental burden during the design phase.