Details
| Original language | English |
|---|---|
| Title of host publication | 2023 IEEE 26th International Conference on Intelligent Transportation Systems, ITSC 2023 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 2302-2309 |
| Number of pages | 8 |
| ISBN (electronic) | 9798350399462 |
| Publication status | Published - 2023 |
| Event | 26th IEEE International Conference on Intelligent Transportation Systems, ITSC 2023 - Bilbao, Spain Duration: 24 Sept 2023 → 28 Sept 2023 |
Publication series
| Name | IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC |
|---|---|
| ISSN (Print) | 2153-0009 |
| ISSN (electronic) | 2153-0017 |
Abstract
Ego-localization is a crucial task for autonomous vehicles. On the one hand, it needs to be very accurate, and on the other hand, very robust to provide reliable pose (position and orientation) information, even in challenging environments. Finding the best ego-position is usually tied to optimizing an objective function based on the sensor measurements. The most common approach is to maximize the likelihood, which leads under the assumption of normally distributed random variables to the well-known least squares minimization, often used in conjunction with recursive estimation, e. g. using a Kalman filter. However, least squares minimization is inherently sensitive to outliers, and consequently, more robust loss functions, such as L1 norm or Huber loss have been proposed. Arguably the most robust loss function is the outlier count, also known as maximum consensus optimization, where the outcome is independent of the outlier magnitude. In this paper, we investigate in detail the performance of maximum consensus localization based on LiDAR data. We elaborate on its shortcomings and propose a novel objective function based on Helmert's point error. In an experiment using 3001 measurement epochs, we show that the maximum consensus localization based on the introduced objective function provides superior results with respect to robustness.
Keywords
- LiDAR, Localization, Maximum consensus, Point cloud registration, Robust estimation
ASJC Scopus subject areas
- Engineering(all)
- Automotive Engineering
- Engineering(all)
- Mechanical Engineering
- Computer Science(all)
- Computer Science Applications
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
2023 IEEE 26th International Conference on Intelligent Transportation Systems, ITSC 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 2302-2309 (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Maximum Consensus Localization Using an Objective Function Based on Helmert's Point Error
AU - Axmann, Jeldrik
AU - Zhang, Yimin
AU - Brenner, Claus
PY - 2023
Y1 - 2023
N2 - Ego-localization is a crucial task for autonomous vehicles. On the one hand, it needs to be very accurate, and on the other hand, very robust to provide reliable pose (position and orientation) information, even in challenging environments. Finding the best ego-position is usually tied to optimizing an objective function based on the sensor measurements. The most common approach is to maximize the likelihood, which leads under the assumption of normally distributed random variables to the well-known least squares minimization, often used in conjunction with recursive estimation, e. g. using a Kalman filter. However, least squares minimization is inherently sensitive to outliers, and consequently, more robust loss functions, such as L1 norm or Huber loss have been proposed. Arguably the most robust loss function is the outlier count, also known as maximum consensus optimization, where the outcome is independent of the outlier magnitude. In this paper, we investigate in detail the performance of maximum consensus localization based on LiDAR data. We elaborate on its shortcomings and propose a novel objective function based on Helmert's point error. In an experiment using 3001 measurement epochs, we show that the maximum consensus localization based on the introduced objective function provides superior results with respect to robustness.
AB - Ego-localization is a crucial task for autonomous vehicles. On the one hand, it needs to be very accurate, and on the other hand, very robust to provide reliable pose (position and orientation) information, even in challenging environments. Finding the best ego-position is usually tied to optimizing an objective function based on the sensor measurements. The most common approach is to maximize the likelihood, which leads under the assumption of normally distributed random variables to the well-known least squares minimization, often used in conjunction with recursive estimation, e. g. using a Kalman filter. However, least squares minimization is inherently sensitive to outliers, and consequently, more robust loss functions, such as L1 norm or Huber loss have been proposed. Arguably the most robust loss function is the outlier count, also known as maximum consensus optimization, where the outcome is independent of the outlier magnitude. In this paper, we investigate in detail the performance of maximum consensus localization based on LiDAR data. We elaborate on its shortcomings and propose a novel objective function based on Helmert's point error. In an experiment using 3001 measurement epochs, we show that the maximum consensus localization based on the introduced objective function provides superior results with respect to robustness.
KW - LiDAR
KW - Localization
KW - Maximum consensus
KW - Point cloud registration
KW - Robust estimation
UR - http://www.scopus.com/inward/record.url?scp=85186495219&partnerID=8YFLogxK
U2 - 10.1109/ITSC57777.2023.10422680
DO - 10.1109/ITSC57777.2023.10422680
M3 - Conference contribution
AN - SCOPUS:85186495219
T3 - IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC
SP - 2302
EP - 2309
BT - 2023 IEEE 26th International Conference on Intelligent Transportation Systems, ITSC 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 26th IEEE International Conference on Intelligent Transportation Systems, ITSC 2023
Y2 - 24 September 2023 through 28 September 2023
ER -