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

2025-02-19

AI Summary

This study addresses human–robot physical collaboration (HRC) by enabling robots to emulate human-like compliant behavior in multi-task cooperation through dynamic joint impedance modulation. Methodologically, it introduces the first integrated framework combining EMG-driven individual limb impedance modeling with muscle synergy analysis from dyadic collaborative motion, yielding a task-oriented real-time impedance learning architecture: human impedance features are estimated from EMG signals; demonstrated motions are modeled via Gaussian Mixture Models/Regression (GMM/GMR); and state-dependent impedance adaptation policies are learned using Long Short-Term Memory (LSTM) networks—finally embedded within a whole-body impedance controller. Evaluated on object transportation and Tai Chi pushing-hands tasks, the approach reduces peak interaction force by 32% and force variability by 41% compared to constant-impedance control, significantly enhancing collaboration naturalness and stability. This work establishes a generalizable, biomechanics-informed paradigm for anthropomorphic adaptive HRC.

Technology Category

• Intelligent Robots: Manipulation
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Economics, Online Markets and Human Computation: Research challenges in human and human-AI computation

Abstract

Humans are experts in collaborating with others physically by regulating compliance behaviors based on the perception of their partner states and the task requirements. Enabling robots to develop proficiency in human collaboration skills can facilitate more efficient human-robot collaboration (HRC). This paper introduces an innovative impedance regulation skill learning framework for achieving HRC in multiple physical collaborative tasks. The framework is designed to adjust the robot compliance to the human partner states while adhering to reference trajectories provided by human-human demonstrations. Specifically, electromyography (EMG) signals from human muscles are collected and analyzed to extract limb impedance, representing compliance behaviors during demonstrations. Human endpoint motions are captured and represented using a probabilistic learning method to create reference trajectories and corresponding impedance profiles. Meanwhile, an LSTMbased module is implemented to develop task-oriented impedance regulation policies by mapping the muscle synergistic contributions between two demonstrators. Finally, we propose a wholebody impedance controller for a human-like robot, coordinating joint outputs to achieve the desired impedance and reference trajectory during task execution. Experimental validation was conducted through a collaborative transportation task and two interactive Tai Chi pushing hands tasks, demonstrating superior performance from the perspective of interactive forces compared to a constant impedance control method.

Problem

• Enabling robots to learn human-like impedance regulation
• Using human-human demonstrations to adjust robot compliance
• Developing task-oriented impedance policies via LSTM and EMG

Innovation

• EMG signals for limb impedance
• LSTM for task-oriented policies
• Whole-body impedance controller