Integral Real-time Locomotion Mode Recognition Based on GA-CNN for Lower Limb Exoskeleton

Abstract The wearable lower limb exoskeleton is a typical human-in-loop human–robot coupled system, which conducts natural and close cooperation with the human by recognizing locomotion timely. Requiring subject-specific training main challenge of existing approaches, most methods have problem insufficient recognition. This paper proposes an integral subject-adaptive real-time Locomotion Mode Recognition (LMR) method based on GA-CNN for system. LMR combination Convolutional Neural Networks (CNN) Genetic Algorithm (GA)-based multi-sensor information selection. To improve network performance, hyper-parameters are optimized Bayesian optimization. An prototype system multi-type sensors novel sensing-shoes used to verify proposed method. Twelve modes, composed daily application exoskeleton, can be recognized According series experiments, recognizer shows strong comprehensive abilities including high accuracy, low delay, sufficient adaption different subjects.