In the context of autonomous driving, pedestrian behavior prediction is a key component for improving road safety. Presently, many existing prediction models prioritize achieving reliable results, however, they often lack insights into the explainability of each prediction. In this work, we propose a novel approach to pedestrian behavior prediction using knowledge graphs (KG), knowledge graph embeddings (KGE), and a Bayesian Inference process, enabling fully inductive reasoning on KGEs. Our approach aims to consolidate knowledge from annotated datasets through explainable pedestrian features and fuzzy rules, evaluating the importance of these two components within the KG. The entire pipeline has been trained and tested using two datasets: Joint Attention for Autonomous Driving (JAAD) and Pedestrian Situated Intent (PSI). Preliminary results demonstrate the effectiveness of this system in providing explainable clues for pedestrian behavior predictions, even improving results by up to 15% compared to other models. Our approach achieves an F1 score of 0.84 for PSI and 0.82 for JAAD.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Knowledge-based explainable pedestrian behavior predictor




    Erscheinungsdatum :

    02.06.2024


    Format / Umfang :

    2238248 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Explainable, automated urban interventions to improve pedestrian and vehicle safety

    Bustos, Cristina / Rhoads, Daniel / Sole-Ribalta, Albert et al. | ArXiv | 2021

    Freier Zugriff

    TREE BASED BEHAVIOR PREDICTOR

    TUMMALA GOPI KRISHNA / SURANA MONU / SADEK AHMED KAMEL et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    BEHAVIOR PREDICTOR

    MINE TAKASHI / GOTO KEN | Europäisches Patentamt | 2020

    Freier Zugriff

    Automated and Explainable Artificial Intelligence to Enhance Prediction of Pedestrian Injury Severity

    Antariksa, Gian / Tamakloe, Reuben / Liu, Jinli et al. | IEEE | 2025


    Pedestrian Behavior at Signalized Pedestrian Crossings

    Lipovac, Krsto | Online Contents | 2013