This paper is about detecting failures under uncertainty and improving the reliability of radar-only motion estimation. We use weak supervision together with inertial measurement fusion to train a classifier that exploits the principal eigenvector associated with our radar scan matching algorithm at run-time and produces a prior belief in the robot’s motion estimate. This prior is used in a filtering framework to correct for vehicle motion estimates. We demonstrate the system on a challenging outdoor dataset, for which current radar motion estimation algorithms fail frequently. By knowing when failure is likely, we achieve qualitatively superior motion estimates and quantitatively fewer odometry failures. Specifically, we see 24.7 % fewer failures in motion estimation over the course of a 15.81 km drive through a difficult, mixed rural-and-urban scene, with lower RMSE in translational and rotational estimates during particularly challenging conditions.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    What Could Go Wrong? Introspective Radar Odometry in Challenging Environments


    Beteiligte:
    Aldera, Roberto (Autor:in) / Martini, Daniele De (Autor:in) / Gadd, Matthew (Autor:in) / Newman, Paul (Autor:in)


    Erscheinungsdatum :

    01.10.2019


    Format / Umfang :

    2726804 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    GNSS aided Radar Inertial Odometry for UAS Flights in Challenging Conditions

    Doer, Christopher / Atman, Jamal / Trnmmer, Gert F. | IEEE | 2022


    Robust Radar Inertial Odometry in Dynamic 3D Environments

    Yang Lyu / Lin Hua / Jiaming Wu et al. | DOAJ | 2024

    Freier Zugriff

    Introspective autonomous vehicle operational management

    SVEGLIATO JUSTIN / WITWICKI STEFAN / WRAY KYLE HOLLINS et al. | Europäisches Patentamt | 2020

    Freier Zugriff

    Radar odometry for vehicle

    OH JINHYOUNG / LAKEHAL-AYAT MOHSEN | Europäisches Patentamt | 2020

    Freier Zugriff

    Introspective Autonomous Vehicle Operational Management

    SVEGLIATO JUSTIN / WITWICKI STEFAN / WRAY KYLE HOLLINS et al. | Europäisches Patentamt | 2020

    Freier Zugriff