Embedded Bayesian Percpetion and V2X Communication for Autnomous Driving

Christian Laugier 1, 2, 3
1 CHROMA - Robots coopératifs et adaptés à la présence humaine en environnements dynamiques
Inria Grenoble - Rhône-Alpes, CITI - CITI Centre of Innovation in Telecommunications and Integration of services
3 E-MOTION - Geometry and Probability for Motion and Action
Inria Grenoble - Rhône-Alpes, LIG - Laboratoire d'Informatique de Grenoble
Abstract : This talk presents the technologies developed by the Inria Chroma team to robustly perceive and interpret dynamic environments using Bayesian systems (such as BOF, HSBOF, and CMCDOT) relying on embedded sensors input and V2X communications (vehicle to vehicle and vehicle to infrastructure). These technologies have initially been developed in collaboration with the IRT nanoelec and with industrial partners such as Toyota, Renault, or Probayes SA, with the objective to extend the capabilities of current Advanced Driving Assistance Systems (including autonomous driving functionalities). The technology is also currently transferred to an industrial mobile robots company (EasyMile and BA Systems). We show how heterogeneous sensors can be used efficiently, merged, and filtered in real time into probabilistic grids, and how collision risks can be computed in an optimized way on embedded GPUs, NVIDIA Jetson Tegra X1. The perception of the environment can also be distributed between connected cars and perception units using V2X protocols.
Type de document :
Communication dans un congrès
GPU Technology Conference - GTC 2017, May 2017, San Jose, California, United States. 2017
Liste complète des métadonnées

https://hal.inria.fr/hal-01672113
Contributeur : Christian Laugier <>
Soumis le : samedi 23 décembre 2017 - 13:04:40
Dernière modification le : lundi 28 janvier 2019 - 01:27:27

Identifiants

  • HAL Id : hal-01672113, version 1

Citation

Christian Laugier. Embedded Bayesian Percpetion and V2X Communication for Autnomous Driving. GPU Technology Conference - GTC 2017, May 2017, San Jose, California, United States. 2017. 〈hal-01672113〉

Partager

Métriques

Consultations de la notice

253