Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | 2018 IEEE Intelligent Vehicles Symposium, IV 2018 |
| Herausgeber (Verlag) | Institute of Electrical and Electronics Engineers Inc. |
| Seiten | 656-661 |
| Seitenumfang | 6 |
| ISBN (elektronisch) | 9781538644522 |
| ISBN (Print) | 978-1-5386-4453-9 |
| Publikationsstatus | Veröffentlicht - 2018 |
| Veranstaltung | 2018 IEEE Intelligent Vehicles Symposium, IV 2018 - Changshu, Suzhou, China Dauer: 26 Sept. 2018 → 30 Sept. 2018 |
Publikationsreihe
| Name | IEEE Intelligent Vehicles Symposium |
|---|---|
| ISSN (Print) | 1931-0587 |
Abstract
Global vehicle localization is normally done by GNSS sensors. In case of GNSS outages, such as in urban canyons or tunnels, highly automated cars cannot localize without an initial known position. In this paper we propose a method for absolute localization in a city based on only one 2D laser scanner.In out method, localization is done by matching vertical scan lines captured by a 2D laser scanner mounted on the vehicle with scan lines derived from a reference point cloud of the environment. We use a neural network to derive significant features describing the shape of the scan lines. Every scan line of a reference data set is labeled with a specific cluster-id using a k-means algorithm and stored in a reference graph. The same k-means algorithm is used to label the single scan lines of a test drive. The localization is done via a sequence mining approach, where a sequence with a specific length is matched to the position with the highest correlation in the reference sequence.In our experiments we analyze the effect of several parameters, including the number of features and sequence length. The results show that the algorithm performs with an accuracy of about 1.4 m and a completeness of up to 99%. Even if the input scan is represented by only ten features, the results are betten than those obtained by using the whole range scan in the localization step.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Angewandte Informatik
- Ingenieurwesen (insg.)
- Fahrzeugbau
- Mathematik (insg.)
- Modellierung und Simulation
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
2018 IEEE Intelligent Vehicles Symposium, IV 2018. Institute of Electrical and Electronics Engineers Inc., 2018. S. 656-661 8500358 (IEEE Intelligent Vehicles Symposium).
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Global Vehicle Localization by Sequence Analysis Using LiDAR Features Derived by an Autoencoder
AU - Schlichting, Alexander
AU - Feuerhake, Udo
N1 - Publisher Copyright: © 2018 IEEE.
PY - 2018
Y1 - 2018
N2 - Global vehicle localization is normally done by GNSS sensors. In case of GNSS outages, such as in urban canyons or tunnels, highly automated cars cannot localize without an initial known position. In this paper we propose a method for absolute localization in a city based on only one 2D laser scanner.In out method, localization is done by matching vertical scan lines captured by a 2D laser scanner mounted on the vehicle with scan lines derived from a reference point cloud of the environment. We use a neural network to derive significant features describing the shape of the scan lines. Every scan line of a reference data set is labeled with a specific cluster-id using a k-means algorithm and stored in a reference graph. The same k-means algorithm is used to label the single scan lines of a test drive. The localization is done via a sequence mining approach, where a sequence with a specific length is matched to the position with the highest correlation in the reference sequence.In our experiments we analyze the effect of several parameters, including the number of features and sequence length. The results show that the algorithm performs with an accuracy of about 1.4 m and a completeness of up to 99%. Even if the input scan is represented by only ten features, the results are betten than those obtained by using the whole range scan in the localization step.
AB - Global vehicle localization is normally done by GNSS sensors. In case of GNSS outages, such as in urban canyons or tunnels, highly automated cars cannot localize without an initial known position. In this paper we propose a method for absolute localization in a city based on only one 2D laser scanner.In out method, localization is done by matching vertical scan lines captured by a 2D laser scanner mounted on the vehicle with scan lines derived from a reference point cloud of the environment. We use a neural network to derive significant features describing the shape of the scan lines. Every scan line of a reference data set is labeled with a specific cluster-id using a k-means algorithm and stored in a reference graph. The same k-means algorithm is used to label the single scan lines of a test drive. The localization is done via a sequence mining approach, where a sequence with a specific length is matched to the position with the highest correlation in the reference sequence.In our experiments we analyze the effect of several parameters, including the number of features and sequence length. The results show that the algorithm performs with an accuracy of about 1.4 m and a completeness of up to 99%. Even if the input scan is represented by only ten features, the results are betten than those obtained by using the whole range scan in the localization step.
UR - http://www.scopus.com/inward/record.url?scp=85056775704&partnerID=8YFLogxK
U2 - 10.1109/ivs.2018.8500358
DO - 10.1109/ivs.2018.8500358
M3 - Conference contribution
AN - SCOPUS:85056775704
SN - 978-1-5386-4453-9
T3 - IEEE Intelligent Vehicles Symposium
SP - 656
EP - 661
BT - 2018 IEEE Intelligent Vehicles Symposium, IV 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2018 IEEE Intelligent Vehicles Symposium, IV 2018
Y2 - 26 September 2018 through 30 September 2018
ER -