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

被引:7
|
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
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
  • [1] Field Based Navigation for 3D Obstacle Avoidance
    Wickramaratna, Sajila D.
    Udage, Akila S.
    Jayasekara, Roshan T.
    Kariyapperuma, Dilhan A.
    Abeysiriwardhana, W. A. Shanaka P.
    Abeykoon, A. M. Harsha S.
    2ND INTERNATIONAL MERCON 2016 MORATUWA ENGINEERING RESEARCH CONFERENCE, 2016, : 391 - 396
  • [2] 3D Collision Avoidance Algorithm for Unmanned Aerial Vehicles with Limited Field of View Constraints
    Roelofsen, Steven
    Martinoli, Alcherio
    Gillet, Denis
    2016 IEEE 55TH CONFERENCE ON DECISION AND CONTROL (CDC), 2016, : 2555 - 2560
  • [3] 3d Sonar for Navigation and Obstacle Avoidance
    Bowles, I.
    Markowski, Z.
    TRANSNAV-INTERNATIONAL JOURNAL ON MARINE NAVIGATION AND SAFETY OF SEA TRANSPORTATION, 2010, 4 (01) : 61 - 64
  • [4] 3D sonar system promises obstacle avoidance
    不详
    NAVAL ARCHITECT, 2007, : 75 - 75
  • [5] Stereo Based 3D Perception for Obstacle Avoidance in Autonomous Wheelchair Navigation
    Gomes, Bruno
    Torres, Jose
    Sobral, Pedro
    Sousa, Armando
    Reis, Luis Paulo
    ROBOT2022: FIFTH IBERIAN ROBOTICS CONFERENCE: ADVANCES IN ROBOTICS, VOL 1, 2023, 589 : 321 - 332
  • [6] 3D Vision Based Local Obstacle Avoidance Method for Humanoid Robot
    Lee, Do-Young
    Lu, Yan-Feng
    Kang, Tae-Koo
    Choi, In-Hwan
    Lim, Myo-Taeg
    2012 12TH INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND SYSTEMS (ICCAS), 2012, : 473 - 475
  • [7] A 3D Trajectory Planning Scheme Based on Visual Obstacle Localization and Avoidance
    Wang Gang
    Ge, Shuzhi Sam
    2013 32ND CHINESE CONTROL CONFERENCE (CCC), 2013, : 5889 - 5894
  • [8] Path Planning with Potential Field-Based Obstacle Avoidance in a 3D Environment by an Unmanned Aerial Vehicle
    Batinovic, Ana
    Goricanec, Jurica
    Markovic, Lovro
    Bogdan, Stjepan
    2022 INTERNATIONAL CONFERENCE ON UNMANNED AIRCRAFT SYSTEMS (ICUAS), 2022, : 394 - 401
  • [9] 3D Obstacle Avoidance System Using Ellipsoid Geometry
    Sasongko, R. A.
    Rawikara, S. S.
    2016 INTERNATIONAL CONFERENCE ON UNMANNED AIRCRAFT SYSTEMS (ICUAS), 2016, : 562 - 571
  • [10] UAV Path Planning and Obstacle Avoidance Based on Reinforcement Learning in 3D Environments
    Tu, Guan-Ting
    Juang, Jih-Gau
    ACTUATORS, 2023, 12 (02)