Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/111048
PIRA download icon_1.1View/Download Full Text
Title: Man-machine cooperation safety control method and device based on mixed reality and digital twinning
Other Title: 基于混合现实和数字孪生的人机协作安全控制方法及装置
Authors: Zheng, P 
Li, C 
Issue Date: 12-Nov-2024
Source: 中国专利 ZL 202410958101.3
Abstract: The invention provides a man-machine cooperation safety control method and device based on mixed reality and digital twinning, and particularly relates to the technical field of man-machine cooperation intelligent manufacturing assembly, and the scheme comprises the steps: obtaining the first posture information of a physical robot, and obtaining the second posture information of a virtual robot; on the basis of the first attitude information and the second attitude information, performing pose registration on a physical robot and a virtual robot to obtain a registration result; path planning is carried out based on the registration result and a preset man-machine working area depth in combination with reinforcement learning, and a man-machine cooperative motion path is determined; and executing a man-machine cooperation safety control action based on the man-machine cooperation motion path. According to the scheme, the man-machine posture information is extracted by using the mixed reality equipment, man-machine posture registration is realized through a virtual-real space mapping method, a man-machine two-way collaborative safety interaction strategy based on deep reinforcement learning is designed, and the safety and effectiveness of man-machine interaction operation are effectively improved.
本发明提供的基于混合现实和数字孪生的人机协作安全控制方法及装置,具体涉及人机协同智能制造装配技术领域,方案包括:获取物理机器人的第一姿态信息,以及获取虚拟机器人的第二姿态信息;基于第一姿态信息和所述第二姿态信息,将物理机器人和虚拟机器人进行位姿配准,获得配准结果;基于配准结果和预设的人机工作区域深度结合强化学习进行路径规划,确定人机协同运动路径;基于人机协同运动路径,执行人机协作安全控制动作。该方案利用混合现实设备提取人机姿态信息,通过虚实空间映射的方法实现了人机位姿配准,并设计了基于深度强化学习的人机双向协同的安全交互策略,有效提高了人机交互操作的安全性和有效性。
Publisher: 中华人民共和国国家知识产权局
Rights: Assignee: 香港理工大学深圳研究院
Appears in Collections:Patent

Files in This Item:
File Description SizeFormat 
ZL202410958101.3.pdf666.64 kBAdobe PDFView/Open
Open Access Information
Status open access
File Version Version of Record
Show full item record

Page views

203
Citations as of Feb 9, 2026

Downloads

215
Citations as of Feb 9, 2026

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.