Embedded Bayesian Perception by Dynamic Occupancy Grid Filtering - Archive ouverte HAL Access content directly
Poster Communications Year : 2017

Embedded Bayesian Perception by Dynamic Occupancy Grid Filtering

(1) , (1)
1

Abstract

A generic Bayesian perception framework, designed to estimate a dense representation of dynamic environments, by fusing and filtering multi-sensor data, has been developed, implemented and tested on embedded devices. The main features of the approach are the followings: • Data from multiple sensors are properly fused in probabilistic occupancy grids. • Motion and robust occupancy are estimated by a specific Bayesian filter. • Short-term collision risks and object parameters are assessed. • The whole system has been implemented and tested on Nvidia embedded devices, and produces real-time results.
Fichier principal
Vignette du fichier
poster-gtc2017.pdf (9.45 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01672134 , version 1 (23-12-2017)

Licence

Public Domain

Identifiers

  • HAL Id : hal-01672134 , version 1

Cite

Lukas Rummelhard, Christian Laugier. Embedded Bayesian Perception by Dynamic Occupancy Grid Filtering. GTC 2017 - GPU Technology Conference, May 2017, San Jose, California, United States. , pp.1, 2017. ⟨hal-01672134⟩
191 View
116 Download

Share

Gmail Facebook Twitter LinkedIn More