2025年4月6日 7:40 星期日
首页 > 过刊浏览>2023年第15卷第2期 >201-209. DOI:10.13878/j.cnki.jnuist.2023.02.009
PDF HTML阅读 XML下载 导出引用 引用提醒
安全屏障机制下基于SAC算法的机器人导航系统
作者:
中图分类号:

TP242.6

基金项目:

国家自然科学基金(61773152).


Robot navigation system based on SAC with security barrier mechanism
Author:
  • 摘要
    • | |
  • 访问统计
    • |
  • 参考文献
    • |
  • 相似文献
    • | | |
  • 文章评论
    摘要:

    为了提高移动机器人自主导航系统的智能化水平和安全性,设计了安全屏障机制下基于SAC(Soft Actor-Critic)算法的自主导航系统,并构建了依赖于机器人与最近障碍物距离、目标点距离以及偏航角的回报函数.在Gazebo仿真平台中,搭建载有激光雷达的移动机器人以及周围环境.实验结果表明,安全屏障机制在一定程度上降低了机器人撞击障碍物的概率,提高了导航的成功率,并使得基于SAC算法的移动机器人自主导航系统具有更高的泛化能力.在更改起终点甚至将静态环境改为动态时,系统仍具有自主导航的能力.

    Abstract:

    An autonomous navigation system was proposed based on Soft Actor-Critic under the security barrier mechanism to improve the intelligence and security of mobile robot autonomous navigation system.The return function was designed based on distance between the robot and the nearest obstacle,the distance from the target point,and the yaw angle.On the Gazebo simulation platform,a mobile robot with lidar and its surrounding environment were built.Experiments showed that the security barrier mechanism reduced the probability of collision with obstacles to a certain extent,improved the success rate of navigation,and made the SAC-based mobile robot autonomous navigation system have high generalization ability.The system still had the ability of autonomous navigation when changing the origin and destination or even changing the environment from static to dynamic.

    参考文献
    [1] Sutton R S,Barto A G.Reinforcement learning:an intro-duction[J].IEEE Transactions on Neural Networks,1998,9(5):1054
    [2] 刘志荣,姜树海.基于强化学习的移动机器人路径规划研究综述[J].制造业自动化,2019,41(3):90-92 LIU Zhirong,JIANG Shuhai.Review of mobile robot path planning based on reinforcement learning[J].Manufacturing Automation,2019,41(3):90-92
    [3] Mnih V,Kavukcuoglu K,Silver D,et al.Playing atari with deep reinforcement learning[J].arXiv e-print,2013,arXiv:1312.5602
    [4] Lillicrap T P,Hunt J J,Pritzel A,et al.Continuous control with deep reinforcement learning[J].arXiv e-print,2015,arXiv:1509.02971
    [5] Haarnoja T,Zhou A,Abbeel P,et al.Soft actor-critic:off-policy maximum entropy deep reinforcement learning with a stochastic actor[J].arXiv e-print,2018,arXiv:1801.01290
    [6] Haarnoja T,Zhou A,Hartikainen K,et al.Soft actor-critic algorithms and applications[J].arXiv e-print,2018,arXiv:1812.05905
    [7] Schulman J,Wolski F,Dhariwal P,et al.Proximal policy optimization algorithms[J].arXiv e-print,2017,arXiv:1707.06347
    [8] Xiang J Q,Li Q D,Dong X W,et al.Continuous control with deep reinforcement learning for mobile robot navigation[C]//2019 Chinese Automation Congress (CAC).November 22-24,2019,Hangzhou,China.IEEE,2019:1501-1506
    [9] de Jesus J C,Kich V A,Kolling A H,et al.Soft actor-critic for navigation of mobile robots[J].Journal of Intelligent & Robotic Systems,2021,102(2):31
    [10] 代珊珊,刘全.基于动作约束深度强化学习的安全自动驾驶方法[J].计算机科学,2021,48(9):235-243 DAI Shanshan,LIU Quan.Action constrained deep reinforcement learning based safe automatic driving method[J].Computer Science,2021,48(9):235-243
    [11] Polyak B T,Juditsky A B.Acceleration of stochastic approximation by averaging[J].SIAM Journal on Control and Optimization,1992,30(4):838-855
    [12] Koenig N,Howard A.Design and use paradigms for Gazebo,an open-source multi-robot simulator[C]//2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).September 28-October 2,2004,Sendai,Japan.IEEE,2004:2149-2154
    [13] Quigley M,Gerkey B P,Conley K,et al.ROS:an open-source robot operating system[C]//ICRA Workshop on Open-Source Software,2009
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

马丽新,刘磊,刘晨.安全屏障机制下基于SAC算法的机器人导航系统[J].南京信息工程大学学报(自然科学版),2023,15(2):201-209
MA Lixin, LIU Lei, LIU Chen. Robot navigation system based on SAC with security barrier mechanism[J]. Journal of Nanjing University of Information Science & Technology, 2023,15(2):201-209

复制
分享
文章指标
  • 点击次数:323
  • 下载次数: 1406
  • HTML阅读次数: 92
  • 引用次数: 0
历史
  • 收稿日期:2022-06-01
  • 在线发布日期: 2023-04-13

地址：江苏省南京市宁六路219号    邮编：210044

联系电话：025-58731025    E-mail：nxdxb@nuist.edu.cn

南京信息工程大学学报 ® 2025 版权所有  技术支持：北京勤云科技发展有限公司