Learning Therapist Policy from Therapist-Exoskeleton-Patient Interaction

2026-03-02

AI Summary

Post-stroke gait rehabilitation relies heavily on intensive, physically demanding therapist interventions, which are difficult to maintain consistently and continuously. This work proposes a Patient–Therapist Force Field (PTFF) framework that, for the first time, models therapist strategies as a learnable force field combined with a sequence prediction model. Specifically, a variational autoencoder constructs a shared latent manifold, a Gaussian mixture model characterizes the interactive force field, and an LSTM network predicts in real time the joint torques applied by the therapist. Integrated into a ROS-based exoskeleton system, the resulting Synthetic Therapist (ST) model was validated via leave-one-out cross-validation on data from eight stroke patients, demonstrating its ability to effectively visualize and automate the transfer of therapeutic expertise, thereby offering a novel paradigm for robot-assisted rehabilitation.

Technology Category

• Intelligent Robots: State Estimation
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search

Abstract

Post-stroke rehabilitation is often necessary for patients to regain proper walking gait. However, the typical therapy process can be exhausting and physically demanding for therapists, potentially reducing therapy intensity, duration, and consistency over time. We propose a Patient-Therapist Force Field (PTFF) to visualize therapist responses to patient kinematics and a Synthetic Therapist (ST) machine learning model to support the therapist in dyadic robot-mediated physical interaction therapy. The first encodes patient and therapist stride kinematics into a shared low-dimensional latent manifold using a Variational Autoencoder (VAE) and models their interaction through a Gaussian Mixture Model (GMM), which learns a probabilistic vector field mapping patient latent states to therapist responses. This representation visualizes patient-therapist interaction dynamics to inform therapy strategies and robot controller design. The latter is implemented as a Long Short-Term Memory (LSTM) network trained on patient-therapist interaction data to predict therapist-applied joint torques from patient kinematics. Trained and validated using leave-one-out cross-validation across eight post-stroke patients, the model was integrated into a ROS-based exoskeleton controller to generate real-time torque assistance based on predicted therapist responses. Offline results and preliminary testing indicate the potential of their use as an alternative approach to post-stroke exoskeleton therapy. The PTFF provides understanding of the therapist's actions while the ST frees the human therapist from the exoskeleton, allowing them to continuously monitor the patient's nuanced condition.

Problem

• post-stroke rehabilitation
• therapist fatigue
• gait recovery
• physical therapy
• human-robot interaction

Innovation

• Patient-Therapist Force Field
• Synthetic Therapist
• Variational Autoencoder
• Gaussian Mixture Model
• LSTM-based torque prediction