Decentralized Structural-RNN for Robot Crowd Navigation with Deep Reinforcement Learning

被引:46
|
作者
Liu, Shuijing [1 ]
Chang, Peixin [1 ]
Liang, Weihang [1 ]
Chakraborty, Neeloy [1 ]
Driggs-Campbell, Katherine [1 ]
机构
[1] Univ Illinois, Dept Elect & Comp Engn, Urbana, IL 61801 USA
关键词
OBSTACLES; ENVIRONMENTS; MODELS;
D O I
10.1109/ICRA48506.2021.9561595
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Safe and efficient navigation through human crowds is an essential capability for mobile robots. Previous work on robot crowd navigation assumes that the dynamics of all agents are known and well-defined. In addition, the performance of previous methods deteriorates in partially observable environments and environments with dense crowds. To tackle these problems, we propose decentralized structural-Recurrent Neural Network (DS-RNN), a novel network that reasons about spatial and temporal relationships for robot decision making in crowd navigation. We train our network with model-free deep reinforcement learning without any expert supervision. We demonstrate that our model outperforms previous methods in challenging crowd navigation scenarios. We successfully transfer the policy learned in the simulator to a real-world TurtleBot 2i.
引用
收藏
页码:3517 / 3524
页数:8
相关论文
共 50 条
  • [31] Socially Aware Robot Navigation Using Deep Reinforcement Learning
    Truong Xuan Tung
    Trung Dung Ngo
    [J]. 2018 IEEE CANADIAN CONFERENCE ON ELECTRICAL & COMPUTER ENGINEERING (CCECE), 2018,
  • [32] Continuous Control with Deep Reinforcement Learning for Mobile Robot Navigation
    Xiang, Jiaqi
    Li, Qingdong
    Dong, Xiwang
    Ren, Zhang
    [J]. 2019 CHINESE AUTOMATION CONGRESS (CAC2019), 2019, : 1501 - 1506
  • [33] A Brief Survey: Deep Reinforcement Learning in Mobile Robot Navigation
    Jiang, Haoge
    Wang, Han
    Yau, Wei-Yun
    Wan, Kong-Wah
    [J]. PROCEEDINGS OF THE 15TH IEEE CONFERENCE ON INDUSTRIAL ELECTRONICS AND APPLICATIONS (ICIEA 2020), 2020, : 592 - 597
  • [34] Crowd-Comfort Robot Navigation Among Dynamic Environment Based on Social-Stressed Deep Reinforcement Learning
    Zhengxi Hu
    Yingli Zhao
    Sen Zhang
    Lei Zhou
    Jingtai Liu
    [J]. International Journal of Social Robotics, 2022, 14 : 913 - 929
  • [35] Crowd-Comfort Robot Navigation Among Dynamic Environment Based on Social-Stressed Deep Reinforcement Learning
    Hu, Zhengxi
    Zhao, Yingli
    Zhang, Sen
    Zhou, Lei
    Liu, Jingtai
    [J]. INTERNATIONAL JOURNAL OF SOCIAL ROBOTICS, 2022, 14 (04) : 913 - 929
  • [36] Scheduling of decentralized robot services in cloud manufacturing with deep reinforcement learning
    Liu, Yongkui
    Ping, Yaoyao
    Zhang, Lin
    Wang, Lihui
    Xu, Xun
    [J]. ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING, 2023, 80
  • [37] Self-Learning Robot Autonomous Navigation with Deep Reinforcement Learning Techniques
    Pintos Gomez de las Heras, Borja
    Martinez-Tomas, Rafael
    Cuadra Troncoso, Jose Manuel
    [J]. APPLIED SCIENCES-BASEL, 2024, 14 (01):
  • [38] End-to-end Decentralized Multi-robot Navigation in Unknown Complex Environments via Deep Reinforcement Learning
    Lin, Juntong
    Yang, Xuyun
    Zheng, Peiwei
    Cheng, Hui
    [J]. 2019 IEEE INTERNATIONAL CONFERENCE ON MECHATRONICS AND AUTOMATION (ICMA), 2019, : 2499 - 2506
  • [39] Decentralized Reinforcement Learning of Robot Behaviors
    Leottau, David L.
    Ruiz-del-Solar, Javier
    Babuska, Robert
    [J]. ARTIFICIAL INTELLIGENCE, 2018, 256 : 130 - 159
  • [40] Decentralized Global Connectivity Maintenance for Multi-Robot Navigation: A Reinforcement Learning Approach
    Li, Minghao
    Jie, Yingrui
    Kong, Yang
    Cheng, Hui
    [J]. 2022 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, ICRA 2022, 2022, : 8801 - 8807