Estimating the reliability of georeferenced lane markings for map-aided localization

Welte, Anthony; Xu, Philippe; Zinoune, Clément

doi:10.1109/ivs.2019.8814214

Cited by 7 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the authors did not explicitly explain how the errors in lane marking position will affect the ego-vehicle localization. In addition, the errors that can be stored in the map are not taken into account, which can also affect the accuracy obtained as pointed out by Welte et al [ 122 ].…”

Section: Lane-level Localization (Lll)mentioning

confidence: 99%

A Survey of Localization Methods for Autonomous Vehicles in Highway Scenarios

Laconte

Kasmi

Aufrère

et al. 2021

Sensors

View full text Add to dashboard Cite

In the context of autonomous vehicles on highways, one of the first and most important tasks is to localize the vehicle on the road. For this purpose, the vehicle needs to be able to take into account the information from several sensors and fuse them with data coming from road maps. The localization problem on highways can be distilled into three main components. The first one consists of inferring on which road the vehicle is currently traveling. Indeed, Global Navigation Satellite Systems are not precise enough to deduce this information by themselves, and thus a filtering step is needed. The second component consists of estimating the vehicle’s position in its lane. Finally, the third and last one aims at assessing on which lane the vehicle is currently driving. These two last components are mandatory for safe driving as actions such as overtaking a vehicle require precise information about the current localization of the vehicle. In this survey, we introduce a taxonomy of the localization methods for autonomous vehicles in highway scenarios. We present each main component of the localization process, and discuss the advantages and drawbacks of the associated state-of-the-art methods.

show abstract

Section: Lane-level Localization (Lll)mentioning

confidence: 99%

A Survey of Localization Methods for Autonomous Vehicles in Highway Scenarios

Laconte

Kasmi

Aufrère

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…It is for that reason that this method is not applied to lane markings. The lane marking observation model as stated in [15] would result in residuals depending on the point of view (e.g. positive residuals when observing a marking driving East to West but negative residuals when driving West to East).…”

Section: Map Error Detectionmentioning

confidence: 99%

HD Map Errors Detection using Smoothing and Multiple Drives

Welte

Zinoune

2021

2021 IEEE Intelligent Vehicles Symposium Workshops (IV Workshops)

Self Cite

View full text Add to dashboard Cite

High Definition (HD) maps enable autonomous vehicles to not only navigate roads but also localize. Using perception sensors such as cameras or lidars, map features can be detected and used for localization. The accuracy of vehicle localization is directly influenced by the accuracy of the features. It is therefore essential for the localization system to be able to detect erroneous map features. In this paper, an approach using Kalman smoothing with observation residuals is presented to address this issue. A covariance intersection of the residuals is proposed to manage their unknown correlation. The method also leverages the information of multiple runs to improve the detection of small errors. The performance of the method is evaluated using experimental data recorded on public roads with erroneous road signs. Our results allow to evaluate the gain of detection brought during successive drives.

show abstract

“…When this process is computed for both landmarks and detections, it is called Point-to-Point (P2P) association. Another strategy is the Point-to-Line association (P2L) [33], [34]. In this case, the authors project point detections in the landmarks polylines in each pose estimation iteration.…”

Section: B Data Representationmentioning

confidence: 99%

DA-LMR: A Robust Lane Marking Representation for Data Association

Muñoz-Bañón¹,

Pauls²,

Hu³

et al. 2021

Preprint

View full text Add to dashboard Cite

While complete localization approaches are widely studied in the literature, their data association and data representation subprocesses usually go unnoticed. However, both are a key part of the final pose estimation.In this work, we present DA-LMR (Delta-Angle Lane Markings Representation), a robust data representation in the context of localization approaches. We propose a representation of lane markings that encodes how a curve changes in each point and includes this information in an additional dimension, thus providing a more detailed geometric structure description of the data. We also propose DC-SAC (Distance-Compatible Sample Consensus), a data association method. This is a heuristic version of RANSAC that dramatically reduces the hypothesis space by distance compatibility restrictions.We compare the presented methods with some state-of-theart data representation and data association approaches in different noisy scenarios. The DA-LMR and DC-SAC produce the most promising combination among those compared, reaching 98.1% in precision and 99.7% in recall for noisy data with 0.5m of standard deviation.

show abstract

Estimating the reliability of georeferenced lane markings for map-aided localization

Cited by 7 publications

References 15 publications

A Survey of Localization Methods for Autonomous Vehicles in Highway Scenarios

A Survey of Localization Methods for Autonomous Vehicles in Highway Scenarios

HD Map Errors Detection using Smoothing and Multiple Drives

DA-LMR: A Robust Lane Marking Representation for Data Association

Contact Info

Product

Resources

About