Dead Reckoning Using Time Series Regression Models

Abstract : Connected car technology promises to drastically reduce the number of accidents involving vehicles. Nevertheless, this technology requires the vehicle precise location to work. The adoption of Global Positioning System (GPS) as a navigation device imposes limitations to geolocation information under non-line-of-sight conditions. This work introduces the Time Series Dead Reckoning System (TedriS) as a solution for dead reckoning navigation when the GPS fails. TedriS uses Time Series Regression Models (TSRM) and the data from the rear wheel speed sensor of the vehicle to estimate the absolute position. The process to estimate the position is carried out in two phases: training and predicting. In the training phase, a novel technique applies TSRM and stores the relationship between the GPS and the rear wheel speed data; then in the predicting phase, this relationship is used. We analyze TedriS using traces collected at the campus of Federal University of Rio de Janeiro (UFRJ), Brazil, and with indoor experiments with a robot. Results show an accuracy compatible with dead-reckoning navigation state-of-art systems.
Document type :
Conference papers
Complete list of metadatas

Cited literature [15 references]  Display  Hide  Download

https://hal.inria.fr/hal-01798550
Contributor : Nathalie Mitton <>
Submitted on : Wednesday, May 23, 2018 - 3:51:23 PM
Last modification on : Friday, June 29, 2018 - 10:04:07 AM

File

dead-reckoning-time.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

João Pinto Neto, Nathalie Mitton, Miguel Elias M. Campista, Luís Henrique M. K. Costa. Dead Reckoning Using Time Series Regression Models. MobiHoc 2018 - 4th ACM MobiHoc Workshop on Experiences with the Design and Implementation of Smart Objects, Jun 2018, Los Angeles, United States. ⟨10.1145/3213299.3213305⟩. ⟨hal-01798550⟩

Share

Metrics

Record views

142

Files downloads

227