Real-time Recognition of User Intent for Neural Control of Artificial Legs

Lower limb amputation significantly affects the quality of the leg amputee’s daily life. Recent advancements in embedded electronics and electromechanical actuators have propelled the recent development of powered artificial legs [1-3]. Usually, finite-state machine (FSM) is utilized in the design of powered prosthetic legs to control the knee joint impedance or knee position in each gait phase [2, 4]. The impedance adjustment of the powered knee depends on the locomotion modes [2-3], since the dynamics and kinematics of the knee joint varies across different locomotion modes. Thus, in order to allow the prosthetic leg appropriately select the prosthetic control mode and smoothly transit the activities from one to another in time, the user must “tell” the prosthetic leg the locomotion intent before execution of the transitions. Currently, the artificial legs are manually controlled by using exaggerated hip and trunk motion [4], which is cumbersome and sometimes unreliable. Accurately recognizing the leg amputee’s locomotion intent is required in order to realize the smooth and seamless control of prosthetic legs.