Abstract
Automated driving systems are in need of accurate localization, i.e., achieving accuracies below 0.1 m at confidence levels above 95%. Although during the last decade numerous localization techniques have been proposed, a common methodology to validate their accuracies in relation to a ground-truth dataset is missing so far. This work aims at closing this gap by evaluating four different methods for validating localization accuracies of a vehicle’s position trajectory to different ground truths: (1) a static driving-path, (2) the lane-centerline of a high-definition (HD) map with validated accuracy, (3) localized vehicle body overlaps of the lane-boundaries of a HD map, and (4) longitudinal accuracy at stop points. The methods are evaluated using two localization test datasets, one acquired by an automated vehicle following a static driving path, being additionally equipped with roof-mounted localization systems, and a second dataset acquired from manually-driven connected vehicles. Results show the broad applicability of the approach for evaluating localization accuracy and reveal the pros and cons of the different methods and ground truths. Results also show the feasibility of achieving localization accuracies below 0.1 m at confidence levels up to 99.9% for high-quality localization systems, while at the same time demonstrate that such accuracies are still challenging to achieve.
Highlights
An automated driving system (ADS) supporting automation levels 3 to 5 according to SAE International Standard J3016TM [1] is supposed to be able to automatically execute driving maneuvers in specific operational design domains (ODDs) [2] with decreasing human intervention
The approach proposed in this paper considers the localization system of an automated vehicle (AV) as black box and evaluates localization accuracy of the resulting position trajectory in relation to two different ground-truth datasets, a pre-defined driving path and a lane-level HD
While numerous localization techniques have been proposed during the last decade, the question of how to validate accuracy and reliability of these techniques in real-world environments remains unaddressed
Summary
An automated driving system (ADS) supporting automation levels 3 to 5 according to SAE International Standard J3016TM [1] is supposed to be able to automatically execute driving maneuvers in specific operational design domains (ODDs) [2] with decreasing human intervention. An ADS being classified as SAE J3016TM level 4 (high automation), for example, requires that the driving system is able to precisely and safely execute driving maneuvers such as lane changes or turns at intersections. In order to execute such driving maneuvers, localization accuracies of 0.1 m at 95% confidence are a crucial requirement of an automated vehicle (AV) [3]. KPI integrity describes the probability to which the localization system is capable to keep the localization error within the alert limits over distance or time and accuracy describes the nominal performance of the localization system and is typically described with a confidence level, e.g., 0.1 m accuracy at 95% confidence. The KPI accuracy describes the measured performance of the localization system while integrity describes to which degree the defined safety limits can be met
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
