Obstacle Avoidance Path Planning for Delta Robots Based on Digital Twin and Deep Reinforcement Learning  

作　　者：Hongxiao Wang Hongshen Liu Dingsen Zhang Ziye Zhang Yonghui Yue Jie Chen 

机构地区：[1]College of Information Science and Engineering,Northeastern University,Shenyang,110819,China [2]Xufeng Electronics Co.,Ltd.,Shenyang,110819,China

出　　处：《Computers, Materials & Continua》2025年第5期1987-2001,共15页计算机、材料和连续体(英文)

基　　金：supported in part by the National Natural Science Foundation of China under Grants 62303098 and 62173073;in part by China Postdoctoral Science Foundation under Grant 2022M720679;in part by the Central University Basic Research Fund of China under Grant N2304021;in part by the Liaoning Provincial Science and Technology Plan Project-Technology Innovation Guidance of the Science and Technology Department under Grant 2023JH1/10400011.

摘　　要：Despite its immense potential,the application of digital twin technology in real industrial scenarios still faces numerous challenges.This study focuses on industrial assembly lines in sectors such as microelectronics,pharmaceuticals,and food packaging,where precision and speed are paramount,applying digital twin technology to the robotic assembly process.The innovation of this research lies in the development of a digital twin architecture and system for Delta robots that is suitable for real industrial environments.Based on this system,a deep reinforcement learning algorithm for obstacle avoidance path planning in Delta robots has been developed,significantly enhancing learning efficiency through an improved intermediate reward mechanism.Experiments on communication and interaction between the digital twin system and the physical robot validate the effectiveness of this method.The system not only enhances the integration of digital twin technology,deep reinforcement learning and robotics,offering an efficient solution for path planning and target grasping inDelta robots,but also underscores the transformative potential of digital twin technology in intelligent manufacturing,with extensive applicability across diverse industrial domains.

关 键 词：Digital twin deep reinforcement learning delta robot obstacle path planning 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]