Autonomous Telerehabilitation via Skeletal Motion Prediction and Joint-Level Performance Assessment

2026-08-12

AI Summary

This work proposes a markerless RGB video–based dual-module system to enable autonomous, therapist-free remote rehabilitation by simultaneously performing action recognition and generating structured feedback. The method innovatively integrates a self-attention bidirectional LSTM with graph-structured motion prediction (STARS) to achieve end-to-end joint-level action quality assessment and short-term pose forecasting. Feedback signals are refined through MMD-NCA metric learning and MPJPE error optimization. Experimental results demonstrate that the system achieves an average class accuracy of 96.45% for action classification on the PROZIS dataset. Furthermore, STARS attains an MPJPE of 75.8 mm over a 560 ms prediction horizon on Human3.6M, outperforming existing baselines.

Abstract

Autonomous rehabilitation systems must not only recognize human motion but also provide structured feedback to support users without continuous therapist supervision. This paper presents a telerehabilitation pipeline that integrates skeleton-based exercise quality assessment and short-term motion prediction into a two-module system operating on marker-free RGB video. A self-attentive Bidirectional LSTM performs exercise quality classification using MMD-NCA metric learning, while a graph-based motion prediction module computes per-joint position errors between predicted and observed poses, generating spatially localized deviation signals. Each module is evaluated independently on established benchmarks: the classifier achieves 96.45% mean-class accuracy on squat sequences from the PROZIS dataset, and the adopted STARS predictor achieves a mean MPJPE of 75.8 mm at 560 ms on Human3.6M, outperforming graph and recurrent baselines across all prediction horizons. The framework is designed for eventual deployment in assistive robotics and home-based rehabilitation contexts; end-to-end integration and clinical validation are important directions for future work. By combining motion recognition and prediction in a single system, this work contributes a step toward autonomous, feedback-driven telerehabilitation, for more accessible and scalable rehabilitation solutions.

Problem

• telerehabilitation
• motion prediction
• exercise quality assessment
• autonomous rehabilitation
• skeletal motion

Innovation

• skeletal motion prediction
• joint-level assessment
• self-attentive BiLSTM
• MMD-NCA metric learning
• marker-free telerehabilitation