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

cs.ROMar 3, 2026

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

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

Organizations: Institute of Measurement and Control Systems, Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany · FZI Research Center for Information Technology, Karlsruhe, Germany

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.

Figures & tables

Fig. 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).

Fig. 2 : Flowchart with an overview from map to evaluation. The noise application is described in Section III-A , details about the ground truth (GT) and training can be found in Section IV-A and we introduce our distance-aware evaluation metric in Section III-B .

Fig. 3 : Qualitative example with ground truth (blue) and noisy localization (red) with Ramp noise (left), Gaussian noise (middle) and Perlin noise (right).

Experiment	Noise parameters						$\mathbf{AP_{dsh}}$	$\mathbf{AP_{sol}}$	$\mathbf{AP_{bou}}$	$\mathbf{AP_{cen}}$	$\mathbf{AP_{ped}}$	mAP
Experiment	$\epsilon_{L}$	$\sigma_{L}$	$\epsilon_{R}$	$\sigma_{R}$	$NR$	$HC$	$\mathbf{AP_{dsh}}$	$\mathbf{AP_{sol}}$	$\mathbf{AP_{bou}}$	$\mathbf{AP_{cen}}$	$\mathbf{AP_{ped}}$	mAP
Baseline $B$	-	-	-	-	-	-	36.7	54.4	49.6	48.3	40.0	45.8
Ramp $R_{1}$	2 m	-	1°	-	50 %	✓	34.8	52.1	46.0	46.1	36.5	43.1
Ramp $R_{2}$	2 m	-	0°	-	100 %	✗	32.0	49.0	46.5	44.3	33.6	41.1
Ramp $R_{3}$	2 m	-	0°	-	100 %	✓	30.6	46.4	43.7	42.7	33.1	39.3
Ramp $R_{4}$	2 m	-	1°	-	100 %	✓	29.8	45.6	44	43.1	31.8	38.9

TABLE I : Comparison between prediction results for the noise types Ramp, Gaussian, and Perlin evaluated using Average Precision (AP). As noise parameters, we defined the maximum translation error

\epsilon_{L}

, maximum angular error

\epsilon_{R}

, for the Gaussian noise case standard deviation in translation

\sigma_{L}

and angular

\sigma_{R}

direction, noise ratio

NR

as the percentage of altered ground truth, and heading correction

HC

as correction to the now altered driving direction.

Panel of Figure 5 — Fig. 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 $GT$ .

Fig. 5 : Gaussian

G_{1}

(GT distortion and prediction) and Baseline

B_{1}

Fig. 6 : Ramp

R_{2}

(GT distortion and prediction) and Baseline

B_{1}

Fig. 7 : Perlin

P_{2}

(GT distortion and prediction) and Baseline

B_{1}

Fig. 8 : Perlin

P_{3}

(GT distortion and prediction) and Baseline

B_{1}

HD Map Construction

High-definition map construction turns sensor and geographic data into precise, structured road maps for autonomous driving and simulation.

See all 39 papers

D2HDMap: Non-visible Driveline Map Prior for Online Vectorized HD Map Prediction
Jun 17, 2026Seojun Shon, Chikao Tsuchiya, Dhaval Bhanderi +3HD Map Construction Autonomous Driving
Nissan North America · Nissan Advanced Technology Center - Silicon Valley, Nissan North America, Santa Clara, CA 95014, USA
Driver2Map: Imitating Human Driving for Online High-Definition Map Construction
Aug 2, 2026Pan Yin, Runtian Xia, Weisong Kuang +3HD Map Construction Multimodal Sensor Fusion
Xi’an Jiaotong University
MapGCLR: Geospatial Contrastive Learning of Representations for Online Vectorized HD Map Construction
Mar 11, 2026Jonas Merkert, Alexander Blumberg, Jan-Hendrik Pauls +1HD Map Construction Geospatial Representation Learning
Institute of Measurement and Control Systems, Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany

Jun 17, 2026J/K move · Enter open · S save

D2HDMap: Non-visible Driveline Map Prior for Online Vectorized HD Map Prediction

Seojun Shon, Chikao Tsuchiya, Dhaval Bhanderi, David Ilstrup+2

Nissan North America · Nissan Advanced Technology Center - Silicon Valley, Nissan North America, Santa Clara, CA 95014, USA

HD Map Construction Autonomous Driving Autonomous Driving Perception

Open paper AskPDF arXiv

Accurate, up-to-date representations of road structures are critical for the safe operation of autonomous vehicles. Existing systems rely either on costly, maintenance-heavy high-definition (HD) maps which compromise safety when outdated, or purely sensor-based online mapping which struggles with long-range reliability and occlusion. Systems incorporating map prior information into online mapping seek to overcome drawbacks of both approaches by combining them in some way. We propose 'Driveline To HD Map' (D2HDMap), an online mapping system that injects a lightweight, non-visible driveline prior to guide the estimation of visible road structures such as lane dividers, road boundaries and crosswalks. This prior incurs less effort to create and update compared to full HD map priors used in other approaches. We also show that training with such a prior can improve generalization at inference time when no prior is available. Ablation studies conducted on the nuScenes and Argoverse 2 dataset demonstrate that models trained using a driveline prior largely retain performance even when priors are not available. On a geographically disjoint split, D2HDMap achieves 44.8 mAP, surpassing recent state-of-the-art. Additionally, noise-aware training substantially increases robustness to realistic localization error.

Abstract

HD Map Construction

Explore similar work

D2HDMap: Non-visible Driveline Map Prior for Online Vectorized HD Map Prediction

Driver2Map: Imitating Human Driving for Online High-Definition Map Construction

MapGCLR: Geospatial Contrastive Learning of Representations for Online Vectorized HD Map Construction