Sensor Fault Detection and Diagnosis for autonomous vehicles

In recent years testing autonomous vehicles on public roads has become a reality. However, before having autonomous vehicles completely accepted on the roads, they have to demonstrate safe operation and reliable interaction with other traffic participants. Furthermore, in real situations and long te...

Full description

Bibliographic Details
Main Authors: Realpe Miguel, Vintimilla Boris, Vlacic Ljubo
Format: Article
Language:English
Published: EDP Sciences 2015-01-01
Series:MATEC Web of Conferences
Online Access:http://dx.doi.org/10.1051/matecconf/20153004003
id doaj-39b548d703f74d8db2629a24f8e1b737
record_format Article
spelling doaj-39b548d703f74d8db2629a24f8e1b7372021-02-02T02:19:57ZengEDP SciencesMATEC Web of Conferences2261-236X2015-01-01300400310.1051/matecconf/20153004003matecconf_icmset2015_04003Sensor Fault Detection and Diagnosis for autonomous vehiclesRealpe MiguelVintimilla Boris0Vlacic Ljubo1CIDIS - FIEC, Escuela Superior Politecnica del LitoralIntelligent Control Systems Laboratory, Griffith UniversityIn recent years testing autonomous vehicles on public roads has become a reality. However, before having autonomous vehicles completely accepted on the roads, they have to demonstrate safe operation and reliable interaction with other traffic participants. Furthermore, in real situations and long term operation, there is always the possibility that diverse components may fail. This paper deals with possible sensor faults by defining a federated sensor data fusion architecture. The proposed architecture is designed to detect obstacles in an autonomous vehicle’s environment while detecting a faulty sensor using SVM models for fault detection and diagnosis. Experimental results using sensor information from the KITTI dataset confirm the feasibility of the proposed architecture to detect soft and hard faults from a particular sensor.http://dx.doi.org/10.1051/matecconf/20153004003
collection DOAJ
language English
format Article
sources DOAJ
author Realpe Miguel
Vintimilla Boris
Vlacic Ljubo
spellingShingle Realpe Miguel
Vintimilla Boris
Vlacic Ljubo
Sensor Fault Detection and Diagnosis for autonomous vehicles
MATEC Web of Conferences
author_facet Realpe Miguel
Vintimilla Boris
Vlacic Ljubo
author_sort Realpe Miguel
title Sensor Fault Detection and Diagnosis for autonomous vehicles
title_short Sensor Fault Detection and Diagnosis for autonomous vehicles
title_full Sensor Fault Detection and Diagnosis for autonomous vehicles
title_fullStr Sensor Fault Detection and Diagnosis for autonomous vehicles
title_full_unstemmed Sensor Fault Detection and Diagnosis for autonomous vehicles
title_sort sensor fault detection and diagnosis for autonomous vehicles
publisher EDP Sciences
series MATEC Web of Conferences
issn 2261-236X
publishDate 2015-01-01
description In recent years testing autonomous vehicles on public roads has become a reality. However, before having autonomous vehicles completely accepted on the roads, they have to demonstrate safe operation and reliable interaction with other traffic participants. Furthermore, in real situations and long term operation, there is always the possibility that diverse components may fail. This paper deals with possible sensor faults by defining a federated sensor data fusion architecture. The proposed architecture is designed to detect obstacles in an autonomous vehicle’s environment while detecting a faulty sensor using SVM models for fault detection and diagnosis. Experimental results using sensor information from the KITTI dataset confirm the feasibility of the proposed architecture to detect soft and hard faults from a particular sensor.
url http://dx.doi.org/10.1051/matecconf/20153004003
work_keys_str_mv AT realpemiguel sensorfaultdetectionanddiagnosisforautonomousvehicles
AT vintimillaboris sensorfaultdetectionanddiagnosisforautonomousvehicles
AT vlacicljubo sensorfaultdetectionanddiagnosisforautonomousvehicles
_version_ 1724310054428999680