DRQN-based 3D Obstacle Avoidance with a Limited Field of View

被引:8
|
作者
Chen, Yu'an [1 ]
Chen, Guangda [1 ]
Pan, Lifan [1 ]
Ma, Jun [1 ]
Zhang, Yu [1 ]
Zhang, Yanyong [1 ]
Ji, Jianmin [1 ]
机构
[1] Univ Sci & Technol China, Sch Comp Sci & Technol, Hefei 230026, Peoples R China
来源
2021 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) | 2021年
关键词
D O I
10.1109/IROS51168.2021.9635949
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In this paper, we propose a map-based end-to-end DRL approach for three-dimensional (3D) obstacle avoidance in a partially observed environment, which is applied to achieve autonomous navigation for an indoor mobile robot using a depth camera with a narrow field of view. We first train a neural network with LSTM units in a 3D simulator of mobile robots to approximate the Q-value function in double DRQN. We also use a curriculum learning strategy to accelerate and stabilize the training process. Then we deploy the trained model to a real robot to perform 3D obstacle avoidance in its navigation. We evaluate the proposed approach both in the simulated environment and on a robot in the real world. The experimental results show that the approach is efficient and easy to be deployed, and it performs well for 3D obstacle avoidance with a narrow observation angle, which outperforms other existing DRL-based models by 15.5% on success rate.
引用
收藏
页码:8137 / 8143
页数:7
相关论文
共 50 条
  • [41] Research on UAV 3D flight track planning and dynamic obstacle avoidance algorithm
    Tan J.
    Ma X.
    Li X.
    Yi Qi Yi Biao Xue Bao/Chinese Journal of Scientific Instrument, 2019, 40 (12): : 224 - 233
  • [42] Naturalistic arm movements during obstacle avoidance in 3D and the identification of movement primitives
    Grimme, Britta
    Lipinski, John
    Schoner, Gregor
    EXPERIMENTAL BRAIN RESEARCH, 2012, 222 (03) : 185 - 200
  • [43] Planning the obstacle-avoidance trajectory of mobile anchor in 3D sensor networks
    Shu MingLei
    Cui HuanQing
    Wang YingLong
    Wang Cheng-Xiang
    SCIENCE CHINA-INFORMATION SCIENCES, 2015, 58 (10) : 1 - 10
  • [44] Planning the obstacle-avoidance trajectory of mobile anchor in 3D sensor networks
    SHU MingLei
    CUI HuanQing
    WANG YingLong
    WANG Cheng-Xiang
    ScienceChina(InformationSciences), 2015, 58 (10) : 109 - 118
  • [45] Naturalistic arm movements during obstacle avoidance in 3D and the identification of movement primitives
    Britta Grimme
    John Lipinski
    Gregor Schöner
    Experimental Brain Research, 2012, 222 : 185 - 200
  • [46] Manipulator Collision Avoidance System Based on a 3D Potential Field With ISO 15066
    Kang, Yeon
    Kim, Donghan
    Yun, Dongwon
    IEEE ACCESS, 2022, 10 : 126593 - 126602
  • [47] Obstacle avoidance method of mobile robot based on obstacle cost potential field
    Chi S.
    Xie Y.
    Chen X.
    Peng F.
    Beijing Hangkong Hangtian Daxue Xuebao/Journal of Beijing University of Aeronautics and Astronautics, 2022, 48 (11): : 2289 - 2303
  • [48] A 3D scanning system based on laser triangulation and variable field of view
    França, JGDM
    Gazziro, MA
    Ide, AN
    Saito, JH
    2005 International Conference on Image Processing (ICIP), Vols 1-5, 2005, : 773 - 776
  • [49] Underwater large field of view 3D imaging based on fisheye lens
    Xie, Liangliang
    Zhang, Xu
    Tu, Dawei
    OPTICS COMMUNICATIONS, 2022, 511
  • [50] 3D Multiview Holographic Display with Wide Field of View Based on Metasurface
    Xiong, Haoran
    Zhang, Xue
    Li, Peijin
    Zhao, Ruizhe
    Li, Xin
    Geng, Guangzhou
    Li, Junjie
    Wang, Yongtian
    Huang, Lingling
    ADVANCED OPTICAL MATERIALS, 2025, 13 (05):