Localization and Mapping is an essential component to enable Autonomous Vehicles navigation, and requires an accuracy exceeding that of commercial GPS-based systems. Current odometry and mapping algorithms are able to provide this accurate information. However, the lack of robustness of these algorithms against dynamic obstacles and environmental changes, even for short time periods, forces the generation of new maps on every session without taking advantage of previously obtained ones. In this paper we propose the use of a deep learning architecture to segment movable objects from 3D LiDAR point clouds in order to obtain longer-lasting 3D maps. This will in turn allow for better, faster and more accurate re-localization and trajectoy estimation on subsequent days. We show the effectiveness of our approach in a very dynamic and cluttered scenario, a supermarket parking lot. For that, we record several sequences on different days and compare localization errors with and without our movable objects segmentation method. Results show that we are able to accurately re-locate over a filtered map, consistently reducing trajectory errors between an average of 35.1% with respect to a non-filtered map version and of 47.9% with respect to a standalone map created on the current session.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Improving Map Re-localization with Deep ‘Movable’ Objects Segmentation on 3D LiDAR Point Clouds


    Contributors:


    Publication date :

    2019-10-01


    Size :

    2433025 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    TRACKING OBJECTS IN LIDAR POINT CLOUDS WITH ENHANCED TEMPLATE MATCHING

    LI DALONG / SMITH ALEX M / HORTON STEPHEN | European Patent Office | 2020

    Free access

    Tracking objects in LIDAR point clouds with enhanced template matching

    LI DALONG / SMITH ALEX M / HORTON STEPHEN | European Patent Office | 2021

    Free access

    SCSSnet: Learning Spatially-Conditioned Scene Segmentation on LiDAR Point Clouds

    Rist, Christoph B. / Schmidt, David / Enzweiler, Markus et al. | IEEE | 2020


    Three-Dimensional Object Co-Localization From Mobile LiDAR Point Clouds

    Guo, Wenzhong / Chen, Jiawei / Wang, Weipeng et al. | IEEE | 2021


    Efficient segmentation of 3D LIDAR point clouds handling partial occlusion

    Aue, Jan / Langer, D. / Muller-Bessler, B. et al. | IEEE | 2011