Making informed driving decisions requires reliable prediction of other vehicles' trajectories. In this paper, we present a novel learned multi-modal trajectory prediction architecture for automated driving. It achieves kinematically feasible predictions by casting the learning problem into the space of accelerations and steering angles - by performing action-space prediction, we can leverage valuable model knowledge. Additionally, the dimensionality of the action manifold is lower than that of the state manifold, whose intrinsically correlated states are more difficult to capture in a learned manner. For the purpose of action-space prediction, we present the simple Feed-Forward Action-Space Prediction (FFW-ASP) architecture. Then, we build on this notion and introduce the novel Self-Supervised Action-Space Prediction (SSP-ASP) architecture that outputs future environment context features in addition to trajectories. A key element in the self-supervised architecture is that, based on an observed action history and past context features, future context features are predicted prior to future trajectories. The proposed methods are evaluated on real-world datasets containing urban intersections and roundabouts, and show accurate predictions, outperforming state-of-the-art for kinematically feasible predictions in several prediction metrics.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Self-Supervised Action-Space Prediction for Automated Driving


    Beteiligte:
    Janjos, Faris (Autor:in) / Dolgov, Maxim (Autor:in) / Zollner, J. Marius (Autor:in)


    Erscheinungsdatum :

    11.07.2021


    Format / Umfang :

    934090 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    SELF-SUPERVISED ACTION-SPACE PREDICTION FOR AUTOMATED DRIVING

    Janjoš, Faris / Dolgov, Maxim / Zöllner, J. Marius | British Library Conference Proceedings | 2021


    Self-Supervised Occupancy Grid Map Completion for Automated Driving

    Stojcheski, Jugoslav / Nurnberg, Thomas / Ulrich, Michael et al. | IEEE | 2023


    Self-Supervised Point Cloud Prediction for Autonomous Driving

    Du, Ronghua / Feng, Rongying / Gao, Kai et al. | IEEE | 2024


    Self-Driving Car Using Supervised Learning

    Collins, Ryan ;Kumar Maurya, Himanshu ;Ragul, Raj S.R. | Trans Tech Publications | 2023


    System and method for federated learning of self-supervised networks in automated driving systems

    GYLLENHAMMAR MAGNUS / TONDERSKI ADAM | Europäisches Patentamt | 2025

    Freier Zugriff