Autonomous Exercise Generator for Upper Extremity Rehabilitation: A Fuzzy-Logic-Based Approach

Area of Science:

• Robotics
• Artificial Intelligence
• Biomedical Engineering

Background:

• Rehabilitation systems require personalized exercise recommendations.
• Existing systems lack full autonomy in exercise selection.
• Uncertainty and ambiguity in patient data complicate decision-making.

Purpose of the Study:

• To develop a fully autonomous robotic rehabilitation system.
• To create a system that recommends exercises based on patient-specific data.
• To address the challenge of uncertainty in medical decision-making.

Main Methods:

• Implemented a fuzzy logic approach, specifically Mamdani-style rules.
• Utilized patient data including shoulder range of motion (ROM) and muscle strength as inputs.
• Ensured system rules were reviewed by a therapist for clinical relevance.

Main Results:

• The fuzzy logic system effectively processes patient data for exercise recommendation.
• The system demonstrated feasibility through testing with various datasets.
• Therapist review confirmed adherence to healthcare standards.

Conclusions:

• The proposed autonomous exercise generation system is feasible.
• Fuzzy logic is a viable approach for handling uncertainty in robotic rehabilitation.
• This system advances the development of autonomous rehabilitation technologies.