Hierarchical Interactive Learning for a HUman-Powered Augmentation Lower EXoskeleton

Abstract

Learning by demonstration methods have gained considerable interest in human-coupled robot control. It aims at modeling the goal motion trajectories through human demonstration. However, in lower exoskeleton control, the physical human-robot interaction is changing from pilot to pilot or even for one pilot in different walking patterns. This characteristic requires that the exoskeletons should have the ability to learn and adapt the motion trajectories as well as controllers online. This paper presents a novel Hierarchical Interactive Learning (HIL) strategy which reduces the complexity of the exoskeleton sensory system and is able to handle varying interaction dynamics. The proposed HIL strategy is composed of two learning hierarchies, namely, high-level motion learning and low-level controller learning. The Dynamic Movement Primitives (DMPs) combined with Locally Weighted Regression (LWR) are employed to model and learn the motion trajectories, while reinforcement learning (RL) is used to learn the modelbased controller. We demonstrate the efficiency of proposed HIL strategy on a single degree-of-freedom (DOF) platform as well as a HUman-powered Augmentation Lower EXoskeleton (HUALEX) system. Experimental results indicate that the proposed HIL strategy is able to handle the varying interaction dynamics with less interaction force between the pilot and the exoskeleton when compared to traditional model-based control algorithms.

Survey on Artificial Intelligence for Vehicles

“…Human-machine semi-physical coupling AI is a foreground in AIV. Huang [12] utilized human-machine physical coupling AI on interactive learning for human-powered augmentation lower exoskeleton [12,13]. Human-machine-based AI is referred as artificial super intelligence (ASI).…”

Probabilistic Sensitivity Amplification Control for Lower Extremity Exoskeleton

“…Therefore, choosing a fixed sensitivity factor is not a good option. An improvement has been made in [27], where the sensitivity factor is learned with Qlearning. Compared with the classic SAC, the interaction force has been reduced.…”

“…Note that not akin to the control algorithm in [27], where the penalty function consists of the previous loop trajectory data, the desired control input (q des i ,q des i , q des i ) is computed and predicted from the identification process. Therefore, our scheme is more suitable for improving real-time control performance.…”

“…The control algorithms compared in the experiment are SAC [10], SAC + Qlearning [27], SAC + CMA-ES and our proposed algorithm.…”

A Robot Learning Method with Physiological Interface for Teleoperation Systems

“…The performance of the teleoperation was improved by the method and demonstrated by remotely operated vehicle (ROV) tasks [26,27]. In order to simplify the complexity of the system and to cope up with the varying dynamical interaction, Huang et al [28] developed a hierarchical interactive learning (HIL) algorithm with dynamic movement primitives (DMPs) and locally weighted regression (LWR) to learn the task trajectories for an exoskeleton system. Furthermore, researchers also employed the human-in-the-loop method with shared control and LWR for robot learning online in the non-trivial task [29,30].…”