Human-Like Robot Impedance Regulation Skill Learning from Human-Human Demonstrations

TL;DR

This paper presents a novel framework enabling robots to learn human-like impedance regulation skills from human-human demonstrations, enhancing physical collaboration by adapting compliance based on human states and task context.

Contribution

The proposed HIImpRSL framework integrates EMG and motion data with imitation learning and LSTM to enable robots to adapt impedance in real-time during collaborative tasks.

Findings

Robots successfully performed collaborative transportation, Tai Chi pushing, and sawing tasks.

The framework outperformed four related methods in interactive force metrics.

Robots exhibited human-like compliance and adaptability in various physical collaborations.

Abstract

Humans are experts in physical collaboration by leveraging cognitive abilities such as perception, reasoning, and decision-making to regulate compliance behaviors based on their partners' states and task requirements. Equipping robots with similar cognitive-inspired collaboration skills can significantly enhance the efficiency and adaptability of human-robot collaboration (HRC). This paper introduces an innovative HumanInspired Impedance Regulation Skill Learning framework (HIImpRSL) for robotic systems to achieve leader-follower and mutual adaptation in multiple physical collaborative tasks. The proposed framework enables the robot to adapt its compliance based on human states and reference trajectories derived from human-human demonstrations. By integrating electromyography (EMG) signals and motion data, we extract endpoint impedance profiles and reference trajectories to construct a joint representation via imitation learning. An LSTM-based module then learns task-oriented impedance regulation policies, which are implemented through a whole-body impedance controller for online impedance adaptation. Experimental validation was conducted through collaborative transportation, two interactive Tai Chi pushing hands, and collaborative sawing tasks with multiple human subjects, demonstrating the ability of our framework to achieve human-like collaboration skills and the superior performance from the perspective of interactive forces compared to four other related methods.