Autonomous navigation of a mobile robot is a challenging task which requires ability of mapping, localization, path planning and path following. Conventional mapping methods build a dense metric map like an occupancy grid, which is affected by odometry error accumulation and consumes a lot of memory and computations in large environments. Another approach to mapping is the usage of topological properties, e.g. adjacency of locations in the environment. Topological maps are less prone to odometry error accumulation and high resources consumption, and also enable fast path planning because of the graph sparsity. Based on this idea, we proposed NavTopo – a full navigation pipeline based on topological map and two-level path planning. The pipeline localizes in the graph by matching neural network descriptors and 2D projections of the input point clouds, which significantly reduces memory consumption compared to metric and topological point cloud-based approaches. We test our approach in three large indoor photo-relaistic simulated environments and compare it to a metric map-based approach based on popular metric mapping method RTAB-MAP. The experimental results show that our topological approach significantly outperforms the metric one in terms of performance with 8 times less memory usage and two orders less path planning time, keeping proper navigational efficiency.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    NavTopo: Leveraging Topological Maps for Autonomous Navigation of a Mobile Robot


    Weitere Titelangaben:

    Lect.Notes Computer


    Beteiligte:
    Ronzhin, Andrey (Herausgeber:in) / Savage, Jesus (Herausgeber:in) / Meshcheryakov, Roman (Herausgeber:in) / Muravyev, Kirill (Autor:in) / Yakovlev, Konstantin (Autor:in)

    Kongress:

    International Conference on Interactive Collaborative Robotics ; 2024 ; New Mexico, Mexico October 14, 2024 - October 18, 2024



    Erscheinungsdatum :

    04.09.2024


    Format / Umfang :

    14 pages




    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Sensor Fusion for Autonomous Mobile Robot Navigation

    Plascencia, Alfredo | BASE | 2008

    Freier Zugriff

    Fuzzy helps to autonomous mobile robot navigation

    Maaref, H. / Benreguieg, M. / Barret, C. | British Library Online Contents | 1996


    Disparity Maps Based Path Planning Algorithm for Autonomous Robot Navigation

    Shetty, Akhil Appu / George, V. I. / Nayak, C Gurudas et al. | IEEE | 2019


    Fuzzy Logic Controller for Autonomous Mobile Robot Navigation

    Batti, Habiba / Jabeur, Chiraz Ben / Seddik, Hassene | IEEE | 2019


    Intelligent Navigation Control of an Autonomous Mobile Robot

    Young Hoon Joo / Hee Soo Hwang / Kwang Bang Woo et al. | British Library Conference Proceedings | 1993