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

In this paper, an autonomous exercise generation system based of fuzzy logic approach is presented. This work attempts to close a gap in the design of a completely autonomous robotic rehabilitation system that can recommend exercises to patients based on their data, such as shoulder range of motion (ROM) and muscle strength, from a pre-set library of exercises. The input parameters are fed into a system that uses Mamdani-style fuzzy logic rules to process them. In medical applications, the rationale behind decision making is a sophisticated process that involves a certain amount of uncertainty and ambiguity. In this instance, a fuzzy-logic-based system emerges as a viable option for dealing with the uncertainty. The system's rules have been reviewed by a therapist to ensure that it adheres to the relevant healthcare standards. Moreover, the system has been tested with a series of test data and the results obtained ensures the proposed idea's feasibility.

Automated summary

This paper presents an autonomous exercise generation system based on fuzzy logic approach. The system uses Mamdani-style fuzzy logic rules to process patients' data, such as shoulder range of motion and muscle strength, and recommends exercises accordingly. The system's rules adhere to healthcare standards and have been tested.