Terrain-aided localization using feature-based particle filtering

Sneha Kadetotad, Pramod K. Vemulapalli, Sean N. Brennan, Constantino Lagoa

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

8 Scopus citations

Abstract

The localization of vehicles on roadways without the use of a GPS has been of great interest in recent years and a number of solutions have been proposed for the same. The localization of vehicles has traditionally been divided by their solution approaches into two different categories: global localization which uses feature-vector matching, and local tracking which has been dealt by using techniques like Particle Filtering or Kalman Filtering. This paper proposes a unifying approach that combines the feature-based robustness of global search with the local tracking capabilities of a particle filter. Using feature vectors produced from pitch measurements from Interstate 1-80 and US Route 220 in Pennsylvania, this work demonstrates wide area localization of a vehicle with the computational efficiency of local tracking.

Original languageEnglish (US)
Title of host publicationASME 2011 Dynamic Systems and Control Conference and Bath/ASME Symposium on Fluid Power and Motion Control, DSCC 2011
Pages725-731
Number of pages7
DOIs
StatePublished - 2011
EventASME 2011 Dynamic Systems and Control Conference and Bath/ASME Symposium on Fluid Power and Motion Control, DSCC 2011 - Arlington, VA, United States
Duration: Oct 31 2011Nov 2 2011

Publication series

NameASME 2011 Dynamic Systems and Control Conference and Bath/ASME Symposium on Fluid Power and Motion Control, DSCC 2011
Volume2

Other

OtherASME 2011 Dynamic Systems and Control Conference and Bath/ASME Symposium on Fluid Power and Motion Control, DSCC 2011
Country/TerritoryUnited States
CityArlington, VA
Period10/31/1111/2/11

All Science Journal Classification (ASJC) codes

  • Fluid Flow and Transfer Processes
  • Control and Systems Engineering

Fingerprint

Dive into the research topics of 'Terrain-aided localization using feature-based particle filtering'. Together they form a unique fingerprint.

Cite this