Cooperative Control of An Ankle Rehabilitation Robot Based on Human Intention

Abstract

Motor imagery electroencephalogram (EEG) is a kind of brain signal induced by subjective consciousness. Relevant studies in the field of sports rehabilitation show that motor imagery training can promote the recovery of damaged nerves and the reconstruction of motor nerve pathways. This paper proposes a human-brain cooperative control strategy of a pneumatic muscle-driven ankle rehabilitation robot based on motor imagery EEG. Robots provide assisted rehabilitation training for patients with impaired neural transmission but with movement intentions. The brain network algorithm is used to select the optimal channels for the motor imagery signal, and the common spatial pattern (CSP) method is combined with the time-frequency analysis method local characteristic-scale decomposition (LCD) to extract the time-frequency information. Finally, the classification is processed by the spectral regression discriminant analysis (SRDA) classifier. In addition, two rehabilitation training modes are designed, namely, synchronous rehabilitation training and asynchronous rehabilitation training. The experimental results prove that a brain intention driven human robot cooperative control method is realized to complete an ankle rehabilitation training task effectively.