Multi-modal sensor fusion constitutes an essential ingredient for safe autonomous navigation. In the last years, many works have improved the accuracy of Deep-Learning-based odometry estimators. However, the robustness of these algorithms to sensor failure or measurement degradation, which are very likely to happen during navigation, has been studied less extensively. Furthermore, works studying the robustness of the fusion modules are developed without modeling the correlation between sensor features, which is crucial to filter out features derived from noisy measurements and in sensor faults scenarios. To bridge this gap, in this paper, we propose a fault-resistant odometry estimator, which produces robust estimates even when the sensors completely fail, or measurements progressively degrade. Our framework models the correlation between the sensor embedding using Message Passing Neural Network (MPNN), a particular type of Graph Neural Network (GNN). A mask is then computed from the updated node features of the graph to weigh the multi-modal features computed from different sensors. We evaluate the proposed fusion strategy on the modified raw KITTI dataset with sensor degradation scenarios. Finally, we compare against state-of-the-art baselines based on trivial features concatenation and soft-fusion to demonstrate our method’s superiority in terms of accuracy and robustness to sensor degradation and failures.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Fault Resistant Odometry Estimation using Message Passing Neural Network


    Beteiligte:


    Erscheinungsdatum :

    04.06.2023


    Format / Umfang :

    2774407 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    2.5D vehicle odometry estimation

    Ciarán Eising / Leroy‐Francisco Pereira / Jonathan Horgan et al. | DOAJ | 2022

    Freier Zugriff

    Dynamic actuation map using neural network fed by visual odometry

    BACCHIANI GIULIO | Europäisches Patentamt | 2025

    Freier Zugriff

    An LSTM Network for Real-Time Odometry Estimation

    Valente, Michelle / Joly, Cyril / de La Fortelle, Arnaud | IEEE | 2019


    Classification-Aided Robust Multiple Target Tracking Using Neural Enhanced Message Passing

    Bai, Xianglong / Wang, Zengfu / Pan, Quan et al. | IEEE | 2025


    Java Message Passing Interface

    Young, G.H. / Lai-Man Wan / Yiu, V.S. | IEEE | 1997