Obstacle avoidance is a fundamental requirement for autonomous robots which operate in, and interact with, the real world. When perception is limited to monocular vision avoiding collision becomes significantly more challenging due to the lack of 3D information. Conventional path planners for obstacle avoidance require tuning a number of parameters and do not have the ability to directly benefit from large datasets and continuous use. In this paper, a dueling architecture based deep double-Q network (D3QN) is applied for obstacle avoidance, using only monocular RGB vision. Based on the dueling and double-Q mechanisms, D3QN can efficiently learn how to avoid obstacles even with very noisy depth information predicted from RGB image. Extensive experiments show that D3QN enables twofold acceleration on learning compared with a normal deep Q network and the models trained solely in virtual environments can be directly transferred to real robots, generalizing well to various new environments with previously unseen dynamic objects.


    Access

    Download


    Export, share and cite



    Title :

    Towards monocular vision based obstacle avoidance through deep reinforcement learning


    Contributors:
    Xie, L (author) / Wang, S (author) / Markham, A (author) / Trigoni, N (author)

    Publication date :

    2020-03-03


    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English


    Classification :

    DDC:    629




    Obstacle avoidance for small UAVs using monocular vision

    Lee, Jeong-Oog / Lee, Keun-Hwan / Park, Sang-Heon et al. | Emerald Group Publishing | 2011


    Obstacle avoidance for small UAVs using monocular vision

    Lee, Jeong-Oog | Online Contents | 2011


    Monocular vision-based obstacle detection/avoidance for unmanned aerial vehicles

    Al-Kaff, Abdulla / Qinggang Meng, / Martin, David et al. | IEEE | 2016


    MONOCULAR VISION-BASED OBSTACLE DETECTION/AVOIDANCE FOR UNMANNED AERIAL VEHICLES

    Al-Kaff, Abdulla / Meng, Qinggang / Martín, David et al. | British Library Conference Proceedings | 2016