Research of Brain Controlled Lower Limb Rehabilitation Exoskeleton

Recently, lower limb exoskeleton robots have been widely used to assist stroke patients in completing lower limb rehabilitation training, and active rehabilitation training guided by patients' motor intentions can stimulate rehabilitation enthusiasm and improve training effectiveness. In order to achieve motion intention recognition and control lower limb exoskeletons to complete rehabilitation training, in this paper, a lower limb exoskeleton control method based on a brain computer interface based on motion imagery signals and lower limb joint angle gait data planning is proposed. Firstly, the common spatial pattern method is used to extract electroencephalogram (EEG) features, and convolutional neural network is employed to recognize motor intentions. Then, based on Fourier series fitting, the lower limb joint angle data is optimized to complete gait planning, and the lower limb exoskeleton is controlled to perform three training actions: walking straight, going up and down stairs. Finally, experiments on EEG recognition and exoskeleton control were completed. The results showed that the proposed method can recognize EEG signals and control the lower limb exoskeleton to drive the subject to complete corresponding rehabilitation training actions.