Investigating Adaptive Tuning of Assistive Exoskeletons Using Offline Reinforcement Learning: Challenges and Insights

-- Assistive exoskeletons have shown great potential in enhancing mobility for individuals with motor impairments, yet their effectiveness relies on precise parameter tuning for personalized assistance. In this study, we investigate the potential of offline reinforcement learning for optimizing effort thresholds in upper-limb assistive exoskeletons, aiming to reduce reliance on manual calibration. Mixed Q-Functionals (MQF) is employed to efficiently handle continuous action spaces while leveraging pre-collected data, thereby mitigating the risks associated with real-time exploration. Experiments were conducted using the MyoPro 2 exoskeleton across two distinct tasks involving horizontal and vertical arm movements. Our results indicate that the proposed approach can dynamically adjust threshold values based on learned patterns, potentially improving user interaction and control, though performance evaluation remains challenging due to dataset limitations. Assistive robotics, particularly powered exoskeletons, have emerged as a promising technology for enhancing human mobility, whether by helping individuals with disabilities, supporting the elderly in daily activities, or improving physical performance in demanding tasks [1], [2], [3]. Effective control in these systems depends on the ability to interpret user intentions and adapt to user learning and changes in physical conditions (e.g., fatigue) [4].