Reinforcement learning-based assist-as-needed control for shoulder rehabilitation robot based on virtual biomechanical model

Key Points

• The assist-as-needed control improves rehabilitation outcomes for shoulder users, enhancing recovery efficiency.
• Critical outcome measures indicate significantly better therapy engagement with robotic intervention as tailored by reinforcement learning techniques.
• Assessment using a virtual biomechanical model ensures personalized adjustments for each user's rehabilitation journey in this setting.
• These findings highlight the potential for robotic interventions to enhance traditional rehabilitation methods and require further real-world trials.