Development of a digital twin environment for smart collision avoidance algorithms for mobile robots using reinforcement learning

被引:1
|
作者
Matsumoto, Natsumi [1 ]
Kobayashi, Kazuyuki [1 ]
Ohkubo, Tomoyuki [2 ]
Tian, Kaiqiao [3 ]
Sebi, Nashwan J. [3 ]
Cheok, Ka C. [3 ]
Cai, Changqing [4 ]
机构
[1] Hosei Univ, Grad Sch Sci & Engn, Tokyo, Japan
[2] Nippon Inst Technol, Fac Adv Engn, Saitama, Japan
[3] Oakland Univ, Sch Engn & Comp Sci, Elect & Comp Engn Dept, Rochester, MI 48309 USA
[4] Changchun Inst Technol, Sch Elect Engn & Informat Technol, Changchun, Peoples R China
来源
2023 62ND ANNUAL CONFERENCE OF THE SOCIETY OF INSTRUMENT AND CONTROL ENGINEERS, SICE | 2023年
关键词
Digital Twin; Point Cloud Data; Mobile Robot; Reinforce Learning;
D O I
10.23919/SICE59929.2023.10354094
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This paper describes a study on building a digital twin environment using point cloud data for mobile robots. A digital twin environment for mobile robots is a method to reproduce almost the same environment in a simulation space as if it were a twin, using data from an actual natural environment. In fact, in the development of mobile robots, experiments on public urban area are conducted, however, they are incredibly time-consuming and labor-intensive, so it would be helpful if a realistic simulation environment could be created. This study focuses on building a digital twin environment using point-cloud-data for mobile robots. In order to verify the effectiveness of this approach, we constructed the environment using data from a real mobile robot that has been driven. The navigation of the mobile robot was performed in the constructed simulation environment, and it was possible to realize a navigation run in the driving environment that was almost the same as the run of the real mobile robot.
引用
收藏
页码:1376 / 1381
页数:6
相关论文
共 50 条
  • [31] Collision Avoidance in Crowded Zone Using Adversarial Reinforcement Learning
    Natesan, Balaji
    Liu, Chuan-Ming
    2021 INTERNATIONAL CONFERENCE ON SECURITY AND INFORMATION TECHNOLOGIES WITH AI, INTERNET COMPUTING AND BIG-DATA APPLICATIONS, 2023, 314 : 276 - 283
  • [32] Ship Collision Avoidance Using Constrained Deep Reinforcement Learning
    Zhang, Rui
    Wang, Xiao
    Liu, Kezhong
    Wu, Xiaolie
    Lu, Tianyou
    Chao Zhaohui
    2018 5TH INTERNATIONAL CONFERENCE ON BEHAVIORAL, ECONOMIC, AND SOCIO-CULTURAL COMPUTING (BESC), 2018, : 115 - 120
  • [33] Obstacle avoidance of multi mobile robots based on behavior decomposition reinforcement learning
    Zu, Linan
    Yang, Peng
    Chen, Lingling
    Zhang, Xueping
    Tian, Yantao
    2007 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND BIOMIMETICS, VOLS 1-5, 2007, : 1018 - +
  • [34] Designing Path of Collision Avoidance for Mobile Manipulator in Worker Safety Monitoring System Using Reinforcement Learning
    Lim, Jiwoong
    Lee, Jihyun
    Lee, Changjoo
    Kim, Gunwoo
    Cha, Younghoon
    Sim, Joonhyung
    Rhim, Sungsoo
    2021 IEEE INTERNATIONAL CONFERENCE ON INTELLIGENCE AND SAFETY FOR ROBOTICS (ISR), 2021, : 94 - 97
  • [35] Collision-Free Deep Reinforcement Learning for Mobile Robots using Crash-Prevention Policy
    Kobelrausch, Markus D.
    Jantsch, Axel
    2021 7TH INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND ROBOTICS (ICCAR), 2021, : 52 - 59
  • [36] Adaptive Environment Modeling Based Reinforcement Learning for Collision Avoidance in Complex Scenes
    Wang, Shuaijun
    Gao, Rui
    Han, Ruihua
    Chen, Shengduo
    Li, Chengyang
    Hao, Qi
    2022 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2022, : 9011 - 9018
  • [37] Collision avoidance for AGV based on deep reinforcement learning in complex dynamic environment
    Cai Z.
    Hu Y.
    Wen J.
    Zhang L.
    Jisuanji Jicheng Zhizao Xitong/Computer Integrated Manufacturing Systems, CIMS, 2023, 29 (01): : 236 - 245
  • [38] Occlusion Avoidance in a Simulated Environment Using Reinforcement Learning
    Szemenyei, Marton
    Szanto, Matyas
    APPLIED SCIENCES-BASEL, 2023, 13 (05):
  • [39] Collision Prediction using LiDAR Sensor in Digital Twin Environment
    Kim, Minseung
    Lee, Jongchae
    Jo, Kanghyun
    2024 33RD INTERNATIONAL SYMPOSIUM ON INDUSTRIAL ELECTRONICS, ISIE 2024, 2024,
  • [40] Cooperative Collision Avoidance in Mobile Robots using Dynamic Vortex Potential Fields
    Martis, Wayne Paul
    Rao, Sachit
    2023 9TH INTERNATIONAL CONFERENCE ON AUTOMATION, ROBOTICS AND APPLICATIONS, ICARA, 2023, : 60 - 64