Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Impact of Localization Errors on Label Quality for Online HD Map Construction

Alexander Blumberg, Jonas Merkert, Richard Fehler, Fabian Immel, Frank Bieder, Jan-Hendrik Pauls, Christoph Stiller

TL;DR

This study trains a variant of MapTRv2, a state-of-the-art on-line HD map construction model on the Argoverse 2 dataset with various levels of localization errors, and assesses the degradation of model performance.

Abstract

High-definition (HD) maps are crucial for autonomous vehicles, but their creation and maintenance is very costly. This motivates the idea of online HD map construction. To provide a continuous large-scale stream of training data, existing HD maps can be used as labels for onboard sensor data from consumer vehicle fleets. However, compared to current, well curated HD map perception datasets, this fleet data suffers from localization errors, resulting in distorted map labels. We introduce three kinds of localization errors, Ramp, Gaussian, and Perlin noise, to examine their influence on generated map labels. We train a variant of MapTRv2, a state-of-the-art online HD map construction model, on the Argoverse 2 dataset with various levels of localization errors and assess the degradation of model performance. Since localization errors affect distant labels more severely, but are also less significant to driving performance, we introduce a distance-based map construction metric. Our experiments reveal that localization noise affects the model performance significantly. We demonstrate that errors in heading angle exert a more substantial influence than position errors, as angle errors result in a greater distortion of labels as distance to the vehicle increases. Furthermore, we can demonstrate that the model benefits from non-distorted ground truth (GT) data and that the performance decreases more than linearly with the increase in noisy data. Our study additionally provides a qualitative evaluation of the extent to which localization errors influence the construction of HD maps.

Impact of Localization Errors on Label Quality for Online HD Map Construction

TL;DR

This study trains a variant of MapTRv2, a state-of-the-art on-line HD map construction model on the Argoverse 2 dataset with various levels of localization errors, and assesses the degradation of model performance.

Abstract

High-definition (HD) maps are crucial for autonomous vehicles, but their creation and maintenance is very costly. This motivates the idea of online HD map construction. To provide a continuous large-scale stream of training data, existing HD maps can be used as labels for onboard sensor data from consumer vehicle fleets. However, compared to current, well curated HD map perception datasets, this fleet data suffers from localization errors, resulting in distorted map labels. We introduce three kinds of localization errors, Ramp, Gaussian, and Perlin noise, to examine their influence on generated map labels. We train a variant of MapTRv2, a state-of-the-art online HD map construction model, on the Argoverse 2 dataset with various levels of localization errors and assess the degradation of model performance. Since localization errors affect distant labels more severely, but are also less significant to driving performance, we introduce a distance-based map construction metric. Our experiments reveal that localization noise affects the model performance significantly. We demonstrate that errors in heading angle exert a more substantial influence than position errors, as angle errors result in a greater distortion of labels as distance to the vehicle increases. Furthermore, we can demonstrate that the model benefits from non-distorted ground truth (GT) data and that the performance decreases more than linearly with the increase in noisy data. Our study additionally provides a qualitative evaluation of the extent to which localization errors influence the construction of HD maps.
Paper Structure (19 sections, 6 equations, 8 figures, 1 table)

This paper contains 19 sections, 6 equations, 8 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Online HD Map Construction
  4. Effect of noisy labels and sensor deviations
  5. Methodology
  6. Noise types
  7. Ramp noise
  8. Gaussian noise
  9. Perlin noise
  10. Heading correction
  11. Partly altered training data
  12. Distance-aware map construction metric
  13. Evaluation
  14. Experimental setup
  15. Qualitative analysis
  16. ...and 4 more sections

Figures (8)

  • Figure 1: Ring evaluation input (colored) over the entire scene (grey). Displayed are the map elements road boundaries (red), centerlines (green), pedestrian crossings (blue), and dividers (pink). Rings plotted as dashed with the currently observed ring (red) and other rings (grey).
  • Figure 2: Flowchart with an overview from map to evaluation. The noise application is described in \ref{['noise_types']}, details about the ground truth (GT) and training can be found in \ref{['sec:setup']} and we introduce our distance-aware evaluation metric in \ref{['evaluation_metric']}.
  • Figure 3: Qualitative example with ground truth (blue) and noisy localization (red) with Ramp noise (left), Gaussian noise (middle) and Perlin noise (right).
  • Figure 4: Qualitative prediction results for the Baseline $B$ (trained without noisy GT labels), Ramp $R_1-R_3$, Gaussian $G_1-G_3$, and Perlin $P_1-P_3$ for the camera input (top left, Baseline results are projected into the image) and the ground truth map $GT$.
  • Figure 5: Gaussian $G_1$ (GT distortion and prediction) and Baseline $B_1$
  • ...and 3 more figures