Performance Evaluation of Metaheuristic Algorithms for Optimal Exoskeleton Controller Design

Abstract

Exoskeletons are used for a wide variety of applications, with one of the most important being assistance and rehabilitation for those who have lost control of their limbs. Exoskeleton controllers must be robust and show stable behavior under varied conditions. Intelligent control schemes prove to be a good option for achieving this. However, there are no standard practices in literature to tune adaptive intelligent controllers which guarantee their performance. Keeping this in mind, an attempt has been made in this work to optimize the parameters of an adaptive fuzzy control scheme applied to a dynamic exoskeleton focusing on the knee and ankle joints. Three different algorithms, namely—Grasshopper Optimization Algorithm (GOA), Grey Wolf Optimizer (GWO), and Moth-Flame Optimization (MFO) are used for this purpose. The performance of the tuned controllers has been investigated and thorough comparative studies have been drawn. Based on the integral time of absolute error values (ITAE), it is concluded that GWO shows an overall better performance over the other two.