Learning Physical Human-Robot Interaction With Coupled Cooperative Primitives for a Lower Exoskeleton

Human-powered lower exoskeletons have received considerable interests from both academia and industry over the past decades, and encountered increasing applications in human locomotion assistance and strength augmentation. One of the most important aspects in those applications is to achieve robust control of lower exoskeletons, which, in the first place, requires the proactive modeling of human movement trajectories through physical human-robot interaction (pHRI). As a powerful representative tool for motion trajectories, dynamic movement primitives (DMP) have been used to model human movement trajectories. However, canonical DMP only offers a general representation of human movement trajectory and may neglects the interactive term, therefore it cannot be directly applied to lower exoskeletons which need to track human joint trajectories online, because different pilots have different trajectories and even same pilot might change his/her motion during walking. This paper presents a novel coupled cooperative primitive (CCP) strategy, which aims at modeling the motion trajectories online. Besides maintaining canonical motion primitives, we model the interaction term between the pilot and exoskeletons through impedance models, and propose a reinforcement learning method based on policy improvement and path integrals (PI2) to learn the parameters online. Experimental results on both a single degree-of-freedom platform and a HUman-powered Augmentation Note to Practitioners - This paper was motivated by the problem of lower exoskeleton when it interacts with different pilots. In both military and industrial applications of lower exoskeleton for strength augmentation, a most challenge problem is how to deal with the pHRI caused by different pilots. This paper suggests a new learning-based strategy, which modeled the pilot's motion with movement primitives and update through the pHRI between the pilot and the lower exoskeleton with online reinforcement learning method. In order to employ the proposed CCP into the real-time application, we also combine the CCP with a hierarchical control framework, and applied on a lower exoskeleton system which we built for strength augmentation application (which named as HUALEX). In the experiments of this paper, we validate the proposed CCP on different pilots with HUALEX system, the proposed CCP also achieve a good performance on the online learning and adaptation of the pilot's gait. In the future, we will extend this algorithm for adapting complex environment in both industrial and military applications, such as in different terrains, stairs, and slopes scenarios, and so on.