Realization of human-computer interaction of lower limbs rehabilitation robot based on sEMG

To improve the efficiency of the lower limbs rehabilitation robot in the rehabilitation training for stroke patients, a human-computer interaction model based on sEMG signals is presented. First, joint torque is got by decoding the sEMG signals according to Hill model, and the model´s parameters are optimized using simulated annealing algorithm. Second, an assist coefficient is defined, and the lower limbs rehabilitation robot is controlled using sEMG by making the assist coefficient remains constant in the rehabilitation process. Finally, the significance of the man-machine interaction based on sEMG signal in rehabilitation robot is analyzed.