Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | Proceedings - 3rd IEEE International Conference on Robotic Computing, IRC 2019 |
| Herausgeber (Verlag) | Institute of Electrical and Electronics Engineers Inc. |
| Seiten | 25-31 |
| Seitenumfang | 7 |
| ISBN (elektronisch) | 9781538692455 |
| Publikationsstatus | Veröffentlicht - 25 Feb. 2019 |
| Extern publiziert | Ja |
| Veranstaltung | 3rd IEEE International Conference on Robotic Computing, IRC 2019 - Naples, Italien Dauer: 25 Feb. 2019 → 27 Feb. 2019 |
Publikationsreihe
| Name | Proceedings - 3rd IEEE International Conference on Robotic Computing, IRC 2019 |
|---|
Abstract
Most autonomous vehicles rely on some kind of map for localization or navigation. Outdated maps however are a risk to the performance of any map-based localization system applied in autonomous vehicles. It is necessary to update the used maps to ensure stable and long-term operation. We address the problem of computing landmark updates live in the vehicle, which requires efficient use of the computational resources. In particular, we employ a graph-based sliding window approach for simultaneous localization and incremental map refinement. We propose a novel method that approximates sliding window marginalization without inducing fill-in. Our method maintains the exact same sparsity pattern as without performing marginalization, but simultaneously improves the landmark estimates. The main novelty of this work is the derivation of sparse global priors that approximate dense marginalization. In comparison to state-of-the-art work, our approach utilizes global instead of local linearization points, but still minimizes linearization errors. We first approximate marginalization via Kullback-Leibler divergence and then recalculate the mean to compensate linearization errors. We evaluate our approach on simulated and real data from a prototype vehicle and compare our approach to state-of-theart sliding window marginalization.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Artificial intelligence
- Mathematik (insg.)
- Steuerung und Optimierung
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
Proceedings - 3rd IEEE International Conference on Robotic Computing, IRC 2019. Institute of Electrical and Electronics Engineers Inc., 2019. S. 25-31 8675637 (Proceedings - 3rd IEEE International Conference on Robotic Computing, IRC 2019).
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Approximating Marginalization with Sparse Global Priors for Sliding Window SLAM-Graphs
AU - Wilbers, Daniel
AU - Rumberg, Lars
AU - Stachniss, Cyrill
N1 - Publisher Copyright: © 2019 IEEE.
PY - 2019/2/25
Y1 - 2019/2/25
N2 - Most autonomous vehicles rely on some kind of map for localization or navigation. Outdated maps however are a risk to the performance of any map-based localization system applied in autonomous vehicles. It is necessary to update the used maps to ensure stable and long-term operation. We address the problem of computing landmark updates live in the vehicle, which requires efficient use of the computational resources. In particular, we employ a graph-based sliding window approach for simultaneous localization and incremental map refinement. We propose a novel method that approximates sliding window marginalization without inducing fill-in. Our method maintains the exact same sparsity pattern as without performing marginalization, but simultaneously improves the landmark estimates. The main novelty of this work is the derivation of sparse global priors that approximate dense marginalization. In comparison to state-of-the-art work, our approach utilizes global instead of local linearization points, but still minimizes linearization errors. We first approximate marginalization via Kullback-Leibler divergence and then recalculate the mean to compensate linearization errors. We evaluate our approach on simulated and real data from a prototype vehicle and compare our approach to state-of-theart sliding window marginalization.
AB - Most autonomous vehicles rely on some kind of map for localization or navigation. Outdated maps however are a risk to the performance of any map-based localization system applied in autonomous vehicles. It is necessary to update the used maps to ensure stable and long-term operation. We address the problem of computing landmark updates live in the vehicle, which requires efficient use of the computational resources. In particular, we employ a graph-based sliding window approach for simultaneous localization and incremental map refinement. We propose a novel method that approximates sliding window marginalization without inducing fill-in. Our method maintains the exact same sparsity pattern as without performing marginalization, but simultaneously improves the landmark estimates. The main novelty of this work is the derivation of sparse global priors that approximate dense marginalization. In comparison to state-of-the-art work, our approach utilizes global instead of local linearization points, but still minimizes linearization errors. We first approximate marginalization via Kullback-Leibler divergence and then recalculate the mean to compensate linearization errors. We evaluate our approach on simulated and real data from a prototype vehicle and compare our approach to state-of-theart sliding window marginalization.
KW - Automated Driving
KW - Incremental Mapping
KW - Localization
KW - Sensor Fusion
KW - SLAM
UR - http://www.scopus.com/inward/record.url?scp=85064136851&partnerID=8YFLogxK
U2 - 10.1109/IRC.2019.00013
DO - 10.1109/IRC.2019.00013
M3 - Conference contribution
AN - SCOPUS:85064136851
T3 - Proceedings - 3rd IEEE International Conference on Robotic Computing, IRC 2019
SP - 25
EP - 31
BT - Proceedings - 3rd IEEE International Conference on Robotic Computing, IRC 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 3rd IEEE International Conference on Robotic Computing, IRC 2019
Y2 - 25 February 2019 through 27 February 2019
ER -