Learning-based visual navigation still remains a challenging problem in robotics, with two overarching issues: how to transfer the learnt policy to unseen scenarios, and how to deploy the system on real robots. In this paper, we propose a deep neural network based visual navigation system, SnapNav. Unlike map-based navigation or Visual-Teach-andRepeat (VT&R), SnapNav only receives a few snapshots of the environment combined with directional guidance to allow it to execute the navigation task. Additionally, SnapNav can be easily deployed on real robots due to a two-level hierarchy: a high level commander that provides directional commands and a low level controller that provides real-time control and obstacle avoidance. This also allows us to effectively use simulated and real data to train the different layers of the hierarchy, facilitating robust control. Extensive experimental results show that SnapNav achieves a highly autonomous navigation ability compared to baseline models, enabling sparse, map-less navigation in previously unseen environments.


    Access

    Download


    Export, share and cite



    Title :

    SnapNav: learning mapless visual navigation with sparse directional guidance and visual reference


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

    Publication date :

    2020-02-27



    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English


    Classification :

    DDC:    629




    Deep Reinforcement Learning for Mapless Navigation of Unmanned Aerial Vehicles

    Grando, Ricardo B. / de Jesus, Junior C. / Drews-Jr, Paulo L. J. | IEEE | 2020


    FreeNavi: Landmark-Based Mapless Indoor Navigation Based on WiFi Fingerprints

    Guo, Yao / Wang, Wenjun / Chen, Xiangqun | IEEE | 2017


    MSN: Mapless Short-Range Navigation Based on Time Critical Deep Reinforcement Learning

    Li, Bohan / Huang, Zhelong / Chen, Tony Weitong et al. | IEEE | 2023


    DVT-Tree: Dynamic Visible Topology Tree for Efficient Mapless Navigation in Maze Environments

    Zhong, Yucong / Liu, Jianyi / Jian, Zhiqiang et al. | IEEE | 2023