Abstract
Autonomous driving systems tightly rely on the quality of the data from sensors for tasks such as localization and navigation. In this work, we present an integrity monitoring framework that can assess the quality of multimodal data from exteroceptive sensors. The proposed multisource coherence-based integrity assessment framework is capable of handling highway as well as complex semi-urban and urban scenarios. To achieve such generalization and scalability, we employ a semantic-grid data representation, which can efficiently represent the surroundings of the vehicle. The proposed method is used to evaluate the integrity of sources in several scenarios, and the integrity markers generated are used for identifying and quantifying unreliable data. A particular focus is given to real-world complex scenarios obtained from publicly available datasets where integrity localization requirements are of high importance. Those scenarios are examined to evaluate the performance of the framework and to provide proof-of-concept. We also establish the importance of the proposed integrity assessment framework in context-based localization applications for autonomous vehicles. The proposed method applies the integrity assessment concepts in the field of aviation to ground vehicles and provides the Protection Level markers (Horizontal, Lateral, Longitudinal) for perception systems used for vehicle localization.
Highlights
The second half of the last decade has seen a significant emergence of commercially available vehicles with autonomous driving capabilities
The proposed method applies the integrity assessment concepts in the field of aviation to ground vehicles and provides the Protection Level markers (Horizontal, Lateral, Longitudinal) for perception systems used for vehicle localization
We focus on the integrity assessment of perception data sources such as vision, LiDAR, map, etc
Summary
The second half of the last decade has seen a significant emergence of commercially available vehicles with autonomous driving capabilities. Using road-safety-related statistics and geometry of roads and vehicles, [3] derived bounds for localization error in both highway and urban scenarios They further distributed the derived total integrity risk to allocate integrity levels to every subsystem present in autonomous vehicles. We focus on the integrity assessment of perception data sources such as vision, LiDAR, map, etc. In [11], facades of buildings at intersections are detected using vision and are fused with building footprints extracted from the digital map to provide better localization They further extended their work in [12] to achieve localization at intersections using road structures instead of building facades and map data.
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.
