Crowdsourcing Radar Maps with AUTO’s Integration of Multiple Imaging Radars and INS/GNSS for Autonomous Applications

Abdelrahman Ali, Dylan Krupity, Noah Giustini, Hallet Duan, Jacques Georgy, Christopher Goodall

Abstract:	Enabling reliable and accurate localization in all environments typically requires the fusion of information from many different sensors and sources. One common approach is the fusion of perception sensors and high definition (HD) maps. However, obtaining HD maps is often a challenge, due to the high financial costs, large data requirements, and heavy processing demands that are involved. This paper presents AUTO, a real-time integrated navigation system that implements a novel method for map crowdsourcing using imaging radars. AUTO integrates inertial navigation systems (INS), global navigation satellite systems (GNSS), odometer, and multiple radars sensors to crowdsource radar-based maps of the environment. Data is gathered by the same systems used for real-time positioning, thereby eliminating the need for costly survey equipment. Furthermore, large maps are divided into smaller areas using a tiling scheme to limit memory growth and improve processing requirements for map-building. This approach allows the map boundaries to be automatically determined based on the input data. The results demonstrate the accurate mapping of downtown areas in Detroit, MI, and Calgary, AB, using combinations of 3 and 5 imaging radars. The maps are represented as 2D occupancy grid maps generated from real-world data, with a 10cm resolution. The results also show how AUTO can then use the crowdsourced radar maps for reliable and accurate positioning in challenging environments. Key performance indices (KPI) are presented for vehicle using different multi-radar configurations. The presented solution also features integrity monitoring for the integrated navigation solution with protection levels illustrated using a Stanford diagram. AUTO was tested under a wide variety of environments, locations, lighting, and weather conditions to assure the robustness and reliability required by autonomous applications.
Published in:	Proceedings of the 36th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2023) September 11 - 15, 2023 Hyatt Regency Denver Denver, Colorado
Pages:	298 - 313
Cite this article:	Ali, Abdelrahman, Krupity, Dylan, Giustini, Noah, Duan, Hallet, Georgy, Jacques, Goodall, Christopher, "Crowdsourcing Radar Maps with AUTO’s Integration of Multiple Imaging Radars and INS/GNSS for Autonomous Applications," Proceedings of the 36th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2023), Denver, Colorado, September 2023, pp. 298-313. https://doi.org/10.33012/2023.19444
Full Paper:	ION Members/Non-Members: 1 Download Credit Sign In