As a safety critical task, autonomous driving requires accurate predictions of road users’ future trajectories for safe motion planning, particularly under challenging conditions. Yet, many recent deep learning methods suffer from a degraded performance on the challenging scenarios, mainly because these scenarios appear less frequently in the training data. To address such a long-tail issue, existing methods force challenging scenarios closer together in the feature space during training to trigger information sharing among them for more robust learning. These methods, however, primarily rely on the motion patterns to characterize scenarios, omitting more informative contextual information, such as interactions and scene layout. We argue that exploiting such information not only improves prediction accuracy but also scene compliance of the generated trajectories. In this paper, we propose to incorporate richer training dynamics information into a prototypical contrastive learning framework. More specifically, we propose a two-stage process. First, we generate rich contextual features using a baseline encoder-decoder framework. These features are split into clusters based on the model’s output errors, using the training dynamics information, and a prototype is computed within each cluster. Second, we retrain the model using the prototypes in a contrastive learning framework. We conduct empirical evaluations of our approach using two large-scale naturalistic datasets and show that our method achieves state-of-the-art performance by improving accuracy and scene compliance on the long-tail samples. Furthermore, we perform experiments on a subset of the clusters to highlight the additional benefit of our approach in reducing training bias.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    TrACT: A Training Dynamics Aware Contrastive Learning Framework for Long-Tail Trajectory Prediction


    Beteiligte:


    Erscheinungsdatum :

    02.06.2024


    Format / Umfang :

    2845666 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Long-Tail Prediction Uncertainty Aware Trajectory Planning for Self-driving Vehicles

    Zhou, Weitao / Cao, Zhong / Xu, Yunkang et al. | IEEE | 2022


    Long-tail pedestrian trajectory prediction method based on subclass balance contrast learning

    YANG BIAO / FANG LEI / YAN KAI et al. | Europäisches Patentamt | 2024

    Freier Zugriff


    SURROUNDING AWARE TRAJECTORY PREDICTION

    ZHANG ETHAN / XIAO HAO / GAN YIQIAN et al. | Europäisches Patentamt | 2025

    Freier Zugriff

    A context-aware pedestrian trajectory prediction framework for automated vehicles

    Kalatian, Arash / Farooq, Bilal | ArXiv | 2021

    Freier Zugriff