The abilities to understand the social interaction behaviors between a vehicle and its surroundings while predicting its trajectory in an urban environment are critical for road safety in autonomous driving. Social interactions are hard to explain because of their uncertainty. In recent years, neural network-based methods have been widely used for trajectory prediction and have been shown to outperform hand-crafted methods. However, these methods suffer from their lack of interpretability. In order to overcome this limitation, we combine the interpretability of a discrete choice model with the high accuracy of a neural network-based model for the task of vehicle trajectory prediction in an interactive environment. We implement and evaluate our model using the INTERACTION dataset and demonstrate the effectiveness of our proposed architecture to explain its predictions without compromising the accuracy.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Interpretable Goal-Based model for Vehicle Trajectory Prediction in Interactive Scenarios


    Contributors:


    Publication date :

    2023-06-04


    Size :

    1104699 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English





    Variational Autoencoder-Based Vehicle Trajectory Prediction with an Interpretable Latent Space

    Neumeier, Marion / Betsch, Michael / Tollkuhn, Andreas et al. | IEEE | 2021


    A Lightweight Goal-Based model for Trajectory Prediction

    Ghoul, Amina / Messaoud, Kaouther / Yahiaoui, Itheri et al. | IEEE | 2022


    Vehicle Trajectory Prediction on Interaction Driving Scenarios

    Wang, Qingrong / Tan, Xiaoze / Zhu, Changfeng | IEEE | 2023