Simultaneous localization and mapping (SLAM) plays a significant role in autonomous vehicles when a global navigation satellite system (GNSS) is not available. Environment models and underlying estimation techniques are key factors of this algorithm. In this paper, we present a hybrid map-based SLAM approach using Rao-Blackwellized particle filters (RBPFs). We represent the environment with the hybrid map which consists of feature and grid maps. The joint posterior between the vehicle positions and both maps are maintained using RBPFs. This approach allows a vehicle to update its states in a more robust and efficient way. We derived a novel sampling formula by combining a feature measurement likelihood to the traditional grid-based SLAM framework and can decrease the uncertainty of the predicted vehicle position significantly. Moreover, we represent the grid maps with 3D models because 2D models could be insufficient and less reliable to achieve tasks such as navigation and obstacle avoidance in complex 3D environment. We are also able to show that the 3D grid measurement likelihood has a lower variance and with that we can improve the overall performance of the algorithm.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Simultaneous localization and mapping based on the local volumetric hybrid map


    Contributors:


    Publication date :

    2015-06-01


    Size :

    760018 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English





    Simultaneous Localization and Mapping

    Ribas, David / Ridao, Pere / Neira, Jose | Tema Archive | 2010


    Robocentric Simultaneous Localization and Mapping

    Ram, S. P. Arjun / Zanetti, Renato | AIAA | 2024


    Local map fusion for real-time indoor simultaneous localization and mapping

    Rodriguez-Losada, D. / Matia, F. / Jimenez, A. et al. | British Library Online Contents | 2006