Solving the localization problem is a key requirement to enabling the development of autonomous platforms. In the field of autonomous driving, the localization problem imposes two criteria on the navigation solution: solution accuracy and solution reliability or integrity. Integrity monitoring describes the solution trustworthiness and is critical to ensuring safety. A conventional approach in urban environments is multi-sensor fusion, which may integrate Inertial Navigation Systems (INS), GNSS, and other perception sensors. This paper presents AUTO, a real-time integrated navigation system that tightly integrates INS, GNSS-RTK, odometer, and multiple radars sensors with High Definition (HD) maps to achieve a high-rate, accurate, continuous, and reliable navigation solution. The results demonstrate lane level accuracy of the solution in a variety of challenging urban and downtown environments. In addition, Key Performance Indices (KPI) are presented for vehicle and robot using different multi-radar configurations. This paper also shows how AUTO leverages a tight integration of multiple imaging radars with other traditional sensors to provide a robust navigation solution with corresponding estimates of the uncertainty. Furthermore, the tight integration enables the determination of protection levels to describe upper bounds on the uncertainty. The results are illustrated using a Stanford Diagram, along with a user defined Alert Limit (AL), to describe the solution integrity and availability. The proposed algorithm utilizes a map matching technique between the imaging radar data and a globally referenced HD map to better estimate the solution uncertainty and protection levels. AUTO’s tightly integrated approach to integrity monitoring means uncertainties and protection levels can be determined even in areas where the system may experience extended periods of GNSS unavailability. The AUTO solution was tested in a variety of environments and locations, including under a range of conditions such as winter weather, to assure the robustness and reliability required by autonomous applications.
Contact us at email@example.com for the full article.