Overview of computational intelligence (CI) techniques for powered exoskeletons

Abstract

There is an emerging need to synchronise wearable function with user intention as many exoskeletons reported in current literature have limited capability to predict user intention. In order to achieve good synchronization, closed loop feedback is required. Overcoming these limitations necessitates an architecture composed of networked sensors and actuators with smart control algorithms to fuse sensor data and create smooth actuation. This review chapter discusses the growing need to deploy computational intelligence (CI) techniques as well as machine learning (ML) algorithms so that exoskeletons are able to predict the user intentions and consequently operate in parallel with human intention. A comprehensive review of major portable, active exoskeletons are provided for both upper and lower limbs with a focus on the need for smart algorithms integration to drive them. The application areas include rehabilitation and human performance augmentation.