Communication Dans Un Congrès Année : 2025

Improving Consistency in Vehicle Trajectory Prediction Through Preference Optimization

Lina Achaji
  • Fonction : Auteur
  • PersonId : 1105612
Nicola Poerio
  • Fonction : Auteur
  • PersonId : 1623907
Grzegorz Bartyzel
  • Fonction : Auteur
  • PersonId : 1623908
Sascha Hornauer
Fabien Moutarde

Résumé

Trajectory prediction is an essential step in the pipeline of an autonomous vehicle. Inaccurate or inconsistent predictions regarding the movement of agents in its surroundings lead to poorly planned maneuvers and potentially dangerous situations for the end-user. Current state-of-the-art deep-learningbased trajectory prediction models can achieve excellent accuracy on public datasets. However, when used in more complex, interactive scenarios, they often fail to capture important interdependencies between agents, leading to inconsistent predictions among agents in the traffic scene. Inspired by the efficacy of incorporating human preference into large language models, this work fine-tunes trajectory prediction models in multiagent settings using preference optimization. By taking as input automatically calculated preference rankings among predicted futures in the fine-tuning process, our experiments-using stateof-the-art models on three separate datasets-show that we are able to significantly improve scene consistency while minimally sacrificing trajectory prediction accuracy and without adding any excess computational requirements at inference time.

Fichier principal
Vignette du fichier
ITSC25_0483_FI.pdf (1.33 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05416522 , version 1 (15-12-2025)

Licence

Identifiants

  • HAL Id : hal-05416522 , version 1

Citer

Caio Azevedo, Lina Achaji, Stefano Sabatini, Nicola Poerio, Grzegorz Bartyzel, et al.. Improving Consistency in Vehicle Trajectory Prediction Through Preference Optimization. IEEE International Conference on Intelligent Transportation Systems (ITSC), Nov 2025, Gold Coast, Australia. ⟨hal-05416522⟩
92 Consultations
54 Téléchargements

Partager

  • More