基于多智能体强化学习的履带机器人摆臂控制方法  

Articulated Flipper Control Method for Tracked Robots Based on Multi-agent Reinforcement Learning

作　　者：张洪川 任君凯 潘海南 梅勇 卢惠民 Zhang Hongchuan;Ren Junkai;Pan Hainan;Mei Yong;Lu Huimin(Department of Special Computer,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)

机构地区：[1]中国兵器装备集团自动化研究所有限公司特种计算机事业部,四川绵阳621000 [2]国防科技大学智能科学学院,长沙410073

出　　处：《兵工自动化》2025年第2期92-95,共4页Ordnance Industry Automation

基　　金：国家自然科学基金资助项目(62203460,U22A2059);国防科技大学自主创新科学基金(24-ZZCX-GZZ-11)。

摘　　要：为解决摆臂式履带机器人在3维环境下实现自主摆臂控制面临的挑战,提出一种基于多智能体强化学习的摆臂控制方法。将机器人的每个摆臂视为一个独立智能体,设计一套兼顾底盘稳定性和摆臂动作的奖励函数,采用多智能体强化学习训练各个摆臂运动;将所提方法部署在基于Isaac Sim搭建的3维仿真环境中,通过向每个智能体输入局部高程图和机器人状态,输出摆臂转角。实验结果表明:该方法能实现多种地形下的摆臂自主控制,在机器人自主越障方面相对于单智能体强化学习有显著提升。To address the challenges faced by flipper tracked robots in achieving flipper autonomous control in a 3D environment,a flipper control method based on multi-agent reinforcement learning is proposed.Consider each flipper of the robot as an independent intelligent agent,design a reward function that balances chassis stability and flipper movements,and use multi-agent reinforcement learning to train the movements of each flipper;Deploy the proposed method in a 3D simulation environment based on Isaac Sim,and output the flipper angle by inputting local elevation maps and robot states to each agent.The experimental results show that this method can achieve autonomous control of the flipper in various terrains,and has significant improvement in robot autonomous obstacle crossing compared to single agent reinforcement learning.

关 键 词：多智能体强化学习 履带机器人 自主越障 摆臂自主控制 

分 类 号：TP242.6[自动化与计算机技术—检测技术与自动化装置]