Fig. 3From: Robust walking control of a lower limb rehabilitation exoskeleton coupled with a musculoskeletal model via deep reinforcement learningRL-based motion imitation control of the LLRE (the LLRE control loop in Fig. 2). The inputs of the motion imitation network consist of the joint state history, the action history and the future target motions. This learning network outputs joint target positions, which are processed by a low-pass filter and then translated into torque-level commands by PD controlBack to article page