A New Robotic Knee Impedance Control Parameter Optimization Method Facilitated by Inverse Reinforcement Learning

Recent efforts in the design of intelligent controllers for configuring robotic prostheses have demonstrated new possibilities in improving mobility and restoring locomotion for individuals with lower-limb disabilities. In these efforts, personalizing the controller of the robotic device is a crucial step in order to meet individual user's needs and physical conditions. Reinforcement learning (RL) based control designs are among some of the most promising approaches to achieving real-time, optimal adaptive tuning capability. However, such designs to date rely on subjectively determining human-robot walking performance measures, commonly in a quadratic form. To further automate the RL design for robotic knee control parameter tuning and potentially improve human-robot locomotion performance, this study introduces a new bilevel optimization method to objectively specify such control design performance measures via inverse reinforcement learning (IRL), which in turn, will be used in low level (forward) RL design of the impedance control parameters. We demonstrate the effectiveness of the bilevel optimization approach with improved human-robot walking performance using systematic OpenSim simulation studies.