What question did this study set out to answer?

The aim is to enhance gait rehabilitation for post-stroke patients using personalized exoskeleton assistance informed by their specific gait impairments.

June 3, 2026Open Access

Pathology-Informed Personalized Exoskeleton Assistance for Post-Stroke Gait Rehabilitation via Simulation-to-Real Reinforcement Learning

Key Points

The aim is to enhance gait rehabilitation for post-stroke patients using personalized exoskeleton assistance informed by their specific gait impairments.
Developed a reinforcement learning framework combining neuromuscular-inspired parametric augmentation with transfer learning.
Evaluated on a public clinical gait dataset of 50 stroke survivors using various performance metrics.
Pretrained the policy in simulation before adapting it to real clinical gait data.
Reduced total MSE from 14.8681 to 11.9369 (p=5.96×10−8) compared to reinforcement learning from scratch.
Improved reward from −21.2264 to −18.4798 (p=3.76×10−4) showing better policy performance.
Significant reductions in hip MSE from 5.9544 to 4.0143 (p=7.51×10−8) and knee MSE from 6.5507 to 5.4507 (p=1.51×10−5).

Abstract

Background/Objectives: Post-stroke gait impairment is highly heterogeneous, which limits the effectiveness of standardized exoskeleton control strategies. Deep reinforcement learning offers a route to adaptive assistance, but its use in stroke rehabilitation is constrained by limited pathological gait data and the lack of interpretable transfer frameworks. We developed a data-efficient, pathology-informed reinforcement learning framework for personalized exoskeleton assistance under limited clinical gait data. Methods: The framework combines neuromuscular-inspired parametric augmentation (NIPA) with parameter-efficient transfer learning. NIPA synthesizes pathological gait trajectories by modeling weakness, stiffness or contracture, and abnormal synergies. A policy is first pretrained in simulation and then adapted to clinical gait data by freezing a shared feature extractor and fine-tuning the output heads. The framework was evaluated on a public clinical gait dataset of 50 stroke survivors using tracking error, reward, smoothness, generalization, and data efficiency as main outcomes. Results: The proposed method outperformed zero assistance, rule-based control, and reinforcement learning from scratch on the test set. Compared with scratch, it reduced total MSE from 14.8681 to 11.9369 (p=5.96×10−8) and improved reward from −21.2264 to −18.4798 (p=3.76×10−4). Hip MSE decreased from 5.9544 to 4.0143 (p=7.51×10−8) and knee MSE decreased from 6.5507 to 5.4507 (p=1.51×10−5), with significant improvements in repeated experiments. Conclusions: The proposed framework reduces reliance on large pathological training datasets and improves offline trajectory-level personalization under limited clinical data. It also provides an interpretable basis for quantitative characterization of post-stroke gait heterogeneity and may support individualized rehabilitation assessment and assistance planning.

Pathology-Informed Personalized Exoskeleton Assistance for Post-Stroke Gait Rehabilitation via Simulation-to-Real Reinforcement Learning

Key Points

Abstract

Cite This Study

Also Consider

Also Consider