Real-Time Power-Efficient Integration of Multi-Sensor Occupancy Grid on Many-Core

Abstract : Safe Autonomous Vehicles (AVs) will emerge when comprehensive perception systems will be successfully integrated into vehicles. Advanced perception algorithms, estimating the position and speed of every obstacle in the environment by using data fusion from multiple sensors, were developed for AV prototypes. Computational requirements of such application prevent their integration into AVs on current low-power embedded hardware. However, recent emerging many-core architectures offer opportunities to fulfill the automotive market constraints and efficiently support advanced perception applications. This paper, explores the integration of the occupancy grid multi-sensor fusion algorithm into low power many-core architectures. The parallel properties of this function are used to achieve real-time performance at low-power consumption. The proposed implementation achieves an execution time of 6.26ms, 6× faster than typical sensor output rates and 9× faster than previous embedded prototypes.
Type de document :
Communication dans un congrès
IEEE International Workshop on Advanced Robotics and its Social Impacts. ARSO 2015, Jul 2015, Lyon, France. 2015, 〈http://arso2015.inria.fr/〉
Liste complète des métadonnées

Littérature citée [14 références]  Voir  Masquer  Télécharger

https://hal-cea.archives-ouvertes.fr/cea-01176446
Contributeur : Julien Mottin <>
Soumis le : mercredi 15 juillet 2015 - 14:16:12
Dernière modification le : mercredi 6 décembre 2017 - 01:20:25
Document(s) archivé(s) le : mercredi 26 avril 2017 - 05:11:17

Fichier

RAKOTOVAO_submitted.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : cea-01176446, version 1

Collections

Citation

Tiana Rakotovao, Julien Mottin, Diego Puschini, Christian Laugier. Real-Time Power-Efficient Integration of Multi-Sensor Occupancy Grid on Many-Core. IEEE International Workshop on Advanced Robotics and its Social Impacts. ARSO 2015, Jul 2015, Lyon, France. 2015, 〈http://arso2015.inria.fr/〉. 〈cea-01176446〉

Partager

Métriques

Consultations de la notice

380

Téléchargements de fichiers

305