Path planning for autonomous mobile robots in unknown environments remains a challenging task, as it requires the ability to collect and process environmental information in real time for the exploration of uncertain areas. Currently, the state-of-the-art method effectively navigates by building a Rapid Visible Tree(RVT) [1] to reserve potential openings detected during exploration, thereby avoiding getting trapped in local minima and achieving good results. However, the RVT method regards the openings as one-dimensional frontiers between known and unknown areas without considering the spatial continuity, resulting in excessive redundancy of frontiers information in the tree. In this paper, we propose a novel, efficient and safe navigation method specifically tailored for scenarios where no prior maps are available. Technically, our method extracts the topological representation of the perception space, and selects topological zones for safe exploration. The robot is steered to discover the frontiers of the unknown environment, and the exploration strategy gets updated in real time as the environment evolves. As part of the exploration procedure, the Dynamic Visible Topology Tree (DVT-Tree) continually expands in response to the environment's topological data. The proposed method is validated on a two-wheeled differential robot platform in simulation as well as real-world. Comparative results with other existing methods confirm that our method outperforms in terms of efficiency and real-time response for navigation without a map in maze environments.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

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


    Contributors:
    Zhong, Yucong (author) / Liu, Jianyi (author) / Jian, Zhiqiang (author) / Pang, Jinlong (author) / Chen, Shitao (author) / Zheng, Xinhu (author)


    Publication date :

    2023-09-24


    Size :

    2079699 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English





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

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


    Deep Reinforcement Learning for Mapless Navigation of Unmanned Aerial Vehicles

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


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

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