Imitation Learning for Adaptive Control of a Virtual Soft Exoglove

2025-05-14

AI Summary

To address the high inter-subject heterogeneity in muscle strength deficits among patients with hand motor impairments and the poor personalization capability of existing wearable exoskeletons, this paper proposes a task-compensatory adaptive controller for a virtual soft exoglove. Methodologically, we introduce the first integration of video-driven learning-from-demonstration (LfD) with a biomechanically realistic, injury-simulatable musculoskeletal model to establish a closed-loop shared-control framework; individualized neuromuscular impairment modeling is further achieved via reinforcement learning and model fine-tuning. Our key innovation lies in unifying visual demonstrations, physiological constraints, and task objectives within a unified virtual simulation environment, enabling end-to-end policy transfer from observation to execution. Experimental results demonstrate that the controller restores 90.5% of baseline dexterity under simulated muscle weakness, significantly improving both completion quality and movement naturalness in hand–object interaction tasks.

Technology Category

• Intelligent Robots: Manipulation
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

The use of wearable robots has been widely adopted in rehabilitation training for patients with hand motor impairments. However, the uniqueness of patients' muscle loss is often overlooked. Leveraging reinforcement learning and a biologically accurate musculoskeletal model in simulation, we propose a customized wearable robotic controller that is able to address specific muscle deficits and to provide compensation for hand-object manipulation tasks. Video data of a same subject performing human grasping tasks is used to train a manipulation model through learning from demonstration. This manipulation model is subsequently fine-tuned to perform object-specific interaction tasks. The muscle forces in the musculoskeletal manipulation model are then weakened to simulate neurological motor impairments, which are later compensated by the actuation of a virtual wearable robotics glove. Results shows that integrating the virtual wearable robotic glove provides shared assistance to support the hand manipulator with weakened muscle forces. The learned exoglove controller achieved an average of 90.5% of the original manipulation proficiency.

Problem

• Customized control for unique muscle deficits in rehabilitation
• Adaptive exoglove compensates weakened hand manipulation forces
• Learning from demonstration to restore grasping proficiency

Innovation

• Customized wearable robotic controller for muscle deficits
• Learning from demonstration for manipulation model training
• Virtual exoglove compensates weakened muscle forces effectively