Global and local frameworks for vehicle state estimation using temporally previewed mapped lane features

Alexander A. Brown, Sean N. Brennan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This paper proposes a method for using a forward-looking monocular camera along with previewed road geometry from a high-fidelity, low-dimensional map to estimate lateral planar vehicle states by measuring the vehicle's temporally anticipated reference trajectory. Theoretical estimator performance from a steady-state Kalman Filter implementation of the estimation framework is calculated for various look-ahead distances and vehicle speeds. Application of this filter structure to real driving data is also briefly discussed. The use of temporally previewed measurements of a vehicle's reference path is shown to greatly improve the accuracy of vehicle planar state estimates, and shows promise for use in closed-loop lane keeping and driver assist applications.

Original languageEnglish (US)
Title of host publication2013 IEEE Intelligent Vehicles Symposium Workshops, IV Workshops 2013
Pages127-133
Number of pages7
DOIs
StatePublished - Nov 13 2013
Event2013 IEEE Intelligent Vehicles Symposium Workshops, IV Workshops 2013 - Gold Coast, QLD, Australia
Duration: Jun 23 2013Jun 23 2013

Publication series

NameIEEE Intelligent Vehicles Symposium, Proceedings

Other

Other2013 IEEE Intelligent Vehicles Symposium Workshops, IV Workshops 2013
CountryAustralia
CityGold Coast, QLD
Period6/23/136/23/13

Fingerprint

State Estimation
State estimation
Look-ahead
Estimate
Kalman Filter
Fidelity
Closed-loop
Driver
Lateral
Camera
Trajectory
Filter
Estimator
Path
Kalman filters
Cameras
Trajectories
Framework
Geometry

All Science Journal Classification (ASJC) codes

  • Modeling and Simulation
  • Automotive Engineering
  • Computer Science Applications

Cite this

Brown, A. A., & Brennan, S. N. (2013). Global and local frameworks for vehicle state estimation using temporally previewed mapped lane features. In 2013 IEEE Intelligent Vehicles Symposium Workshops, IV Workshops 2013 (pp. 127-133). [6615238] (IEEE Intelligent Vehicles Symposium, Proceedings). https://doi.org/10.1109/IVWorkshops.2013.6615238
Brown, Alexander A. ; Brennan, Sean N. / Global and local frameworks for vehicle state estimation using temporally previewed mapped lane features. 2013 IEEE Intelligent Vehicles Symposium Workshops, IV Workshops 2013. 2013. pp. 127-133 (IEEE Intelligent Vehicles Symposium, Proceedings).
@inproceedings{41516f886bcd4cddbda34fc96b70f63d,
title = "Global and local frameworks for vehicle state estimation using temporally previewed mapped lane features",
abstract = "This paper proposes a method for using a forward-looking monocular camera along with previewed road geometry from a high-fidelity, low-dimensional map to estimate lateral planar vehicle states by measuring the vehicle's temporally anticipated reference trajectory. Theoretical estimator performance from a steady-state Kalman Filter implementation of the estimation framework is calculated for various look-ahead distances and vehicle speeds. Application of this filter structure to real driving data is also briefly discussed. The use of temporally previewed measurements of a vehicle's reference path is shown to greatly improve the accuracy of vehicle planar state estimates, and shows promise for use in closed-loop lane keeping and driver assist applications.",
author = "Brown, {Alexander A.} and Brennan, {Sean N.}",
year = "2013",
month = "11",
day = "13",
doi = "10.1109/IVWorkshops.2013.6615238",
language = "English (US)",
isbn = "9781479907953",
series = "IEEE Intelligent Vehicles Symposium, Proceedings",
pages = "127--133",
booktitle = "2013 IEEE Intelligent Vehicles Symposium Workshops, IV Workshops 2013",

}

Brown, AA & Brennan, SN 2013, Global and local frameworks for vehicle state estimation using temporally previewed mapped lane features. in 2013 IEEE Intelligent Vehicles Symposium Workshops, IV Workshops 2013., 6615238, IEEE Intelligent Vehicles Symposium, Proceedings, pp. 127-133, 2013 IEEE Intelligent Vehicles Symposium Workshops, IV Workshops 2013, Gold Coast, QLD, Australia, 6/23/13. https://doi.org/10.1109/IVWorkshops.2013.6615238

Global and local frameworks for vehicle state estimation using temporally previewed mapped lane features. / Brown, Alexander A.; Brennan, Sean N.

2013 IEEE Intelligent Vehicles Symposium Workshops, IV Workshops 2013. 2013. p. 127-133 6615238 (IEEE Intelligent Vehicles Symposium, Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Global and local frameworks for vehicle state estimation using temporally previewed mapped lane features

AU - Brown, Alexander A.

AU - Brennan, Sean N.

PY - 2013/11/13

Y1 - 2013/11/13

N2 - This paper proposes a method for using a forward-looking monocular camera along with previewed road geometry from a high-fidelity, low-dimensional map to estimate lateral planar vehicle states by measuring the vehicle's temporally anticipated reference trajectory. Theoretical estimator performance from a steady-state Kalman Filter implementation of the estimation framework is calculated for various look-ahead distances and vehicle speeds. Application of this filter structure to real driving data is also briefly discussed. The use of temporally previewed measurements of a vehicle's reference path is shown to greatly improve the accuracy of vehicle planar state estimates, and shows promise for use in closed-loop lane keeping and driver assist applications.

AB - This paper proposes a method for using a forward-looking monocular camera along with previewed road geometry from a high-fidelity, low-dimensional map to estimate lateral planar vehicle states by measuring the vehicle's temporally anticipated reference trajectory. Theoretical estimator performance from a steady-state Kalman Filter implementation of the estimation framework is calculated for various look-ahead distances and vehicle speeds. Application of this filter structure to real driving data is also briefly discussed. The use of temporally previewed measurements of a vehicle's reference path is shown to greatly improve the accuracy of vehicle planar state estimates, and shows promise for use in closed-loop lane keeping and driver assist applications.

UR - http://www.scopus.com/inward/record.url?scp=84887238721&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84887238721&partnerID=8YFLogxK

U2 - 10.1109/IVWorkshops.2013.6615238

DO - 10.1109/IVWorkshops.2013.6615238

M3 - Conference contribution

AN - SCOPUS:84887238721

SN - 9781479907953

T3 - IEEE Intelligent Vehicles Symposium, Proceedings

SP - 127

EP - 133

BT - 2013 IEEE Intelligent Vehicles Symposium Workshops, IV Workshops 2013

ER -

Brown AA, Brennan SN. Global and local frameworks for vehicle state estimation using temporally previewed mapped lane features. In 2013 IEEE Intelligent Vehicles Symposium Workshops, IV Workshops 2013. 2013. p. 127-133. 6615238. (IEEE Intelligent Vehicles Symposium, Proceedings). https://doi.org/10.1109/IVWorkshops.2013.6615238