Vehicle Motion Forecasting using Prior Information and Semantic-assisted Occupancy Grid Maps - Archive ouverte HAL Accéder directement au contenu
Poster De Conférence Année : 2023

Vehicle Motion Forecasting using Prior Information and Semantic-assisted Occupancy Grid Maps

Résumé

Motion prediction is a challenging task for autonomous vehicles due to uncertainty in the sensor data, the non-deterministic nature of future, and complex behavior of agents. In this paper, we tackle this problem by representing the scene as dynamic occupancy grid maps (DOGMs), associating semantic labels to the occupied cells and incorporating map information. We propose a novel framework that combines deep learning-based spatio-temporal and probabilistic approaches to predict vehicle behaviors. Contrary to the conventional OGM prediction methods, evaluation of our work is conducted against the ground truth annotations. We experiment and validate our results on real-world NuScenes dataset and show that our model shows superior ability to predict both static and dynamic vehicles compared to OGM predictions. Furthermore, we perform an ablation study and assess the role of semantic labels and map in the architecture.
Fichier principal
Vignette du fichier
IROS2023_Poster_hal.pdf (697.6 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04416326 , version 1 (25-01-2024)

Licence

Paternité

Identifiants

  • HAL Id : hal-04416326 , version 1

Citer

Rabbia Asghar, Manuel Alejandro Diaz-Zapata, Lukas Rummelhard, Anne Spalanzani, Anne Spalanzani, et al.. Vehicle Motion Forecasting using Prior Information and Semantic-assisted Occupancy Grid Maps. NAVER LABS 2023 - Europe International Workshop on AI for Robotics, Nov 2023, Grenoble, France. ⟨hal-04416326⟩
11 Consultations
3 Téléchargements

Partager

Gmail Facebook X LinkedIn More