Dynamic Traffic Scene Understanding using Bayesian Sensor Fusion and Motion Prediction - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

Dynamic Traffic Scene Understanding using Bayesian Sensor Fusion and Motion Prediction

Résumé

Autonomous Driving is gradually becoming a major Technological, Industrial, Economical and Societal issue. However, a real deployment of such new technologies first requires addressing the related system dependability, which itself strongly dependent on the capabilities and performance of the involved Embedded Perception and Situation Awareness systems. Recent accidents (e.g. Tesla or Uber) have shown that the level of safety obtained using currently tested Autonomous Driving systems is still insufficient. This talk addresses this important Perception and Situation Awareness issue. Novel solutions based on the concepts of "Bayesian Sensor Fusion", "Motion Prediction" and "Collision Risk Assessment" are presented and discussed. The approach is illustrated using results obtained in the scope of several Research and Development projects conducted in cooperation with the French IRT Nanoelec and with several industrial companies such as Toyota and Renault.
Fichier principal
Vignette du fichier
Invited-talk_ApolloScapeWS-ECCV2018.pdf (7.01 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01968786 , version 1 (04-01-2019)

Licence

Copyright (Tous droits réservés)

Identifiants

  • HAL Id : hal-01968786 , version 1

Citer

Christian Laugier. Dynamic Traffic Scene Understanding using Bayesian Sensor Fusion and Motion Prediction. ECCV 2018 - Workshop on Vision-based Navigation for Autonomous Driving, Sep 2018, Munich, Germany. pp.1-35. ⟨hal-01968786⟩
181 Consultations
227 Téléchargements

Partager

Gmail Facebook X LinkedIn More