Human-machine cooperation method and related device based on human intention estimation and impedance adjustment

Through intention estimation and adaptive impedance adjustment based on the Transformer architecture, the lag problem of robot intention recognition and trajectory adjustment in complex environments in the existing technology is solved, and efficient and safe collaboration of robots on complex surfaces is achieved.

CN120791791APending Publication Date: 2025-10-17INST OF AUTOMATION CHINESE ACAD OF SCI
0 Cites 1 Cited by

Patent Information

Application Number
CN202511244802.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-09-02
Publication Date
2025-10-17

AI Technical Summary

Technical Problem

Existing human-robot collaboration methods lack multimodal perception capabilities when recognizing human intentions and are unable to dynamically adjust trajectory and stiffness, resulting in delayed robot response and poor adaptability, making it difficult to conduct efficient and safe physical interactions on complex and irregular surfaces.

Method used

A human intention estimator based on the Transformer architecture is used, combined with an adaptive force coupling enhanced dynamic motion primitive module and an auxiliary impedance controller. Human intention is estimated in real time through multimodal sensing signals, the desired motion trajectory and stiffness parameters are generated, and the stiffness and damping coefficients of the robot are dynamically adjusted.

Benefits of technology

It improves the collaborative ability, environmental adaptability and interactive safety of the robot system, can achieve high flexibility and stability on complex and irregular surfaces, and adapt to collaborative tasks in multiple tasks and scenarios.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a human-machine cooperation method based on human intention estimation and impedance adjustment and a related device. The human-machine cooperation method comprises the steps that multi-mode sensing signals of a robot tail end and human operation are acquired; inputting the multi-modal sensing signals of the robot tail end and the human operation into a human intention estimator to obtain a real-time human intention estimation result; inputting the real-time human intention estimation result into an adaptive force coupling enhanced dynamic motion primitive module to generate an expected motion track and a stiffness parameter; and the expected movement track and the rigidity parameter are input into an auxiliary impedance controller, the rigidity and the damping coefficient of the robot are adjusted through the auxiliary impedance controller, and the method and the related device can effectively improve the cooperation ability, the environment adaptability and the interaction safety of a robot system.
Need to check novelty before this filing date? Find Prior Art