Promoting active participation in robot-aided rehabilitation via machine learning and impedance control.

Introduction: Active patient participation is crucial for effective robot-assisted rehabilitation. Quantifying the user's Active Level of Participation (ALP) during therapy and developing human-robot interaction strategies that promote engagement can improve rehabilitation outcomes. However, existing methods for estimating participation are often unimodal and do not provide continuous participation assessment. Methods: This study proposes a novel approach for estimating ALP during upper-limb robot-aided rehabilitation by leveraging machine learning within a multimodal framework. The system integrates pressure sensing at the human-robot interface and muscle activity monitoring to provide a more comprehensive assessment of user participation. The estimated ALP is used to dynamically adapt task execution time, enabling an adaptive ALP-driven impedance control strategy. The proposed approach was tested in a laboratory setting using a collaborative robot equipped with the sensorized interface. A comparative analysis was conducted against a conventional impedance controller, commonly used in robot-aided rehabilitation scenarios. Results: The results demonstrated that participants using the ALP-driven impedance control exhibited significantly higher positive mechanical work and greater muscle activation compared to the control group. Additionally, subjective feedback indicated increased engagement and confidence when interacting with the adaptive system. Discussion: Closing the robot's control loop by adapting to ALP effectively enhanced human-robot interaction and motivated participants to engage more actively in their therapy. These findings suggest that ALP-driven control strategies may improve user involvement in robot-assisted rehabilitation, warranting further investigation in clinically relevant settings.