基于无建图的强化学习人工势场法编队  

Artificial Potential Field Formation Method Based on Reinforcement Learning without Graph Construction

作　　者：丁磊 骆云志 洪华杰[2] 黄杰[2] 樊鹏 赵伟 陈斯灏 Ding Lei;Luo Yunzhi;Hong Huajie;Huang Jie;Fan Peng;Zhao Wei;Chen Sihao(Department of System General,Automation Research Institute Co.,Ltd.of China South Industries Group Corporation,Mianyang 621000,China;College of Intelligence Science and Technology,National University of Defense Technology,Changsha 410073,China;Military Representative Office of Army Equipment Department in Guangyuan District,Guangyuan 628000,China)

机构地区：[1]中国兵器装备集团自动化研究所有限公司系统总体部,四川绵阳621000 [2]国防科技大学智能科学学院,长沙410073 [3]陆装驻广元地区军代室,四川广元628000

出　　处：《兵工自动化》2025年第4期96-100,共5页Ordnance Industry Automation

摘　　要：针对同步定位与建图(simultaneous localization and mapping,SLAM)技术对计算资源的高需求、有限环境适应性、累积误差问题、系统复杂度高、成本昂贵、大场景处理能力受限以及缺乏有效的回环检测机制的缺点,提出一种结合人工势场法和深度强化学习的方法。利用图论模拟人工势场在机器人间的相互作用以及机器人与目的地之间的势场力,并采用孪生延迟深度确定性策略梯度(twin delayed deep deterministic policy gradient,TD3)算法来优化机器人对障碍物信息的感知和处理。仿真试验结果表明:该方法使机器人能够在未知环境中快速、准确地进行定位、移动,同时维持队形的稳定性和一致性。For simultaneous localization and mapping(SLAM)technology has the disadvantages of high demand for computing resources,limited environmental adaptability,cumulative error problem,high system complexity,high cost,limited large scene processing capacity and lack of effective loop detection mechanism,so a method combining artificial potential field method and deep reinforcement learning is proposed.The graph theory is used to simulate the interaction between robots and the potential force between robots and the destination,and the twin delayed deep deterministic policy gradient algorithm is used to optimize the robot's perception and processing of obstacle information.The simulation results show that the method can make the robot locate and move quickly and accurately in the unknown environment,while maintaining the stability and consistency of the formation.

关 键 词：人工势场法 强化学习 双延时确定策略梯度 图论 

分 类 号：TP242.6[自动化与计算机技术—检测技术与自动化装置]