Interpretable Goal-Based model for Vehicle Trajectory Prediction in Interactive Scenarios - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2023

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

Abstract

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 handcrafted 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.
Fichier principal
Vignette du fichier
root.pdf (366.08 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04108657 , version 1 (08-08-2023)

Identifiers

Cite

Amina Ghoul, Itheri Yahiaoui, Anne Verroust-Blondet, Fawzi Nashashibi. Interpretable Goal-Based model for Vehicle Trajectory Prediction in Interactive Scenarios. IEEE Intelligent Vehicles Symposium (IV), Jun 2023, Anchorage, United States. pp.1-6, ⟨10.1109/IV55152.2023.10186734⟩. ⟨hal-04108657⟩

Collections

INRIA URCA INRIA2
64 View
31 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More