A dependable detection mechanism for intersection management of Connected Autonomous Vehicles

Rachel Dedinsky, Mohammad Khayatian, Mohammadreza Mehrabian, Aviral Shrivastava

Research output: Contribution to journalConference article

Abstract

Traffic intersections will become automated in the near future with the advent of Connected Autonomous Vehicles (CAVs). Researchers have proposed intersection management approaches that use the position and velocity that are reported by vehicles to compute a schedule for vehicles to safely and efficiently traverse the intersection. However, a vehicle may fail to follow intersection manager (IM) scheduling commands due to erroneous sensor readings or unexpected incidents like engine failure, which can cause an accident if the failure happens inside the intersection. Additionally, rogue vehicles can take the advantage of the IM by providing false position and velocity data and cause traffic congestion. In this paper, we present a new technique and infrastructure to detect anomalies and inform the IM. We propose a vision system that can monitor the position of incoming vehicles and provide real-time data for the IM. The IM can use this data to verify the trajectories of CAVs and broadcast a warning when a vehicle fails to follow commands, making the IM more resilient against attacks and false data. We implemented our method by building infrastructure for an intersection with 1/10 scale model CAVs. Results show our method, when combined with an IM dataflows, is more dependable in the event of a failure compared to an IM without it.

Original languageEnglish (US)
Article number7
JournalOpenAccess Series in Informatics
Volume68
DOIs
StatePublished - Mar 1 2019
Event1st International Workshop on Autonomous Systems Design, ASD 2019 - Florence, Italy
Duration: Mar 29 2019 → …

Fingerprint

Autonomous Vehicles
Intersection
manager
Managers
management
infrastructure
cause
detection
vehicle
traffic congestion
broadcast
Infrastructure
scheduling
incident
accident
Traffic Congestion
engine
Traffic congestion
traffic
Combined Method

Keywords

  • Connected Autonomous Vehicles
  • Dependable systems
  • Intersection Management

ASJC Scopus subject areas

  • Geography, Planning and Development
  • Modeling and Simulation

Cite this

A dependable detection mechanism for intersection management of Connected Autonomous Vehicles. / Dedinsky, Rachel; Khayatian, Mohammad; Mehrabian, Mohammadreza; Shrivastava, Aviral.

In: OpenAccess Series in Informatics, Vol. 68, 7, 01.03.2019.

Research output: Contribution to journalConference article

@article{8a6b34aed11344a49f5da2435b2ead62,
title = "A dependable detection mechanism for intersection management of Connected Autonomous Vehicles",
abstract = "Traffic intersections will become automated in the near future with the advent of Connected Autonomous Vehicles (CAVs). Researchers have proposed intersection management approaches that use the position and velocity that are reported by vehicles to compute a schedule for vehicles to safely and efficiently traverse the intersection. However, a vehicle may fail to follow intersection manager (IM) scheduling commands due to erroneous sensor readings or unexpected incidents like engine failure, which can cause an accident if the failure happens inside the intersection. Additionally, rogue vehicles can take the advantage of the IM by providing false position and velocity data and cause traffic congestion. In this paper, we present a new technique and infrastructure to detect anomalies and inform the IM. We propose a vision system that can monitor the position of incoming vehicles and provide real-time data for the IM. The IM can use this data to verify the trajectories of CAVs and broadcast a warning when a vehicle fails to follow commands, making the IM more resilient against attacks and false data. We implemented our method by building infrastructure for an intersection with 1/10 scale model CAVs. Results show our method, when combined with an IM dataflows, is more dependable in the event of a failure compared to an IM without it.",
keywords = "Connected Autonomous Vehicles, Dependable systems, Intersection Management",
author = "Rachel Dedinsky and Mohammad Khayatian and Mohammadreza Mehrabian and Aviral Shrivastava",
year = "2019",
month = "3",
day = "1",
doi = "10.4230/OASIcs.ASD.2019.7",
language = "English (US)",
volume = "68",
journal = "OpenAccess Series in Informatics",
issn = "2190-6807",

}

TY - JOUR

T1 - A dependable detection mechanism for intersection management of Connected Autonomous Vehicles

AU - Dedinsky, Rachel

AU - Khayatian, Mohammad

AU - Mehrabian, Mohammadreza

AU - Shrivastava, Aviral

PY - 2019/3/1

Y1 - 2019/3/1

N2 - Traffic intersections will become automated in the near future with the advent of Connected Autonomous Vehicles (CAVs). Researchers have proposed intersection management approaches that use the position and velocity that are reported by vehicles to compute a schedule for vehicles to safely and efficiently traverse the intersection. However, a vehicle may fail to follow intersection manager (IM) scheduling commands due to erroneous sensor readings or unexpected incidents like engine failure, which can cause an accident if the failure happens inside the intersection. Additionally, rogue vehicles can take the advantage of the IM by providing false position and velocity data and cause traffic congestion. In this paper, we present a new technique and infrastructure to detect anomalies and inform the IM. We propose a vision system that can monitor the position of incoming vehicles and provide real-time data for the IM. The IM can use this data to verify the trajectories of CAVs and broadcast a warning when a vehicle fails to follow commands, making the IM more resilient against attacks and false data. We implemented our method by building infrastructure for an intersection with 1/10 scale model CAVs. Results show our method, when combined with an IM dataflows, is more dependable in the event of a failure compared to an IM without it.

AB - Traffic intersections will become automated in the near future with the advent of Connected Autonomous Vehicles (CAVs). Researchers have proposed intersection management approaches that use the position and velocity that are reported by vehicles to compute a schedule for vehicles to safely and efficiently traverse the intersection. However, a vehicle may fail to follow intersection manager (IM) scheduling commands due to erroneous sensor readings or unexpected incidents like engine failure, which can cause an accident if the failure happens inside the intersection. Additionally, rogue vehicles can take the advantage of the IM by providing false position and velocity data and cause traffic congestion. In this paper, we present a new technique and infrastructure to detect anomalies and inform the IM. We propose a vision system that can monitor the position of incoming vehicles and provide real-time data for the IM. The IM can use this data to verify the trajectories of CAVs and broadcast a warning when a vehicle fails to follow commands, making the IM more resilient against attacks and false data. We implemented our method by building infrastructure for an intersection with 1/10 scale model CAVs. Results show our method, when combined with an IM dataflows, is more dependable in the event of a failure compared to an IM without it.

KW - Connected Autonomous Vehicles

KW - Dependable systems

KW - Intersection Management

UR - http://www.scopus.com/inward/record.url?scp=85064139317&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064139317&partnerID=8YFLogxK

U2 - 10.4230/OASIcs.ASD.2019.7

DO - 10.4230/OASIcs.ASD.2019.7

M3 - Conference article

AN - SCOPUS:85064139317

VL - 68

JO - OpenAccess Series in Informatics

JF - OpenAccess Series in Informatics

SN - 2190-6807

M1 - 7

ER -