Tightly Coupled Integration of GNSS/UWB/VIO for Reliable and Seamless Positioning

The technology of autonomous vehicle (AV) is critical in nowadays Intelligent Transportation Systems. To achieve the fully automated operation for AVs, one important prerequisite is the accurate and reliable seamless localization covering complex outdoor-indoor scenarios. Although many solutions have been proposed to support AV localization, it is still challenging inon achieving reliableglobally drift-free positioning in seamless urbanthe unknown outdoor-indoor environments. With the current on-board sensors such as( GNSS, IMU, LiDAR, and cameras, etc.), it is difficult for AVs to achieve accurate drift-free indoor positioning and smooth indoor-outdoor transition due to the lack of GNSS indoorssignals in indoor environments. Meanwhile, challenges remain in reliable navigation under obscured conditions. In this paper, we propose a tightly coupled integration algorithm of GNSS RTK, Ultra-Wide Band (UWB) and Visual Inertial Odometry (VIO) to enhance the accuracy and reliability for AVs seamless localization in challengingharsh environments. The UWB techniquesystem is innovatively incorporated into the AVs navigation system to extendextent the absolute positioning indoorsinto indoor environments. The stereo cameras are utilized to improve positioning continuity and enhance GNSS/UWB usability in outdoor-indoor obscured environments.The visual-inertial-odometry is utilized to enhance the positioning performance in the outdoor-indoor obscured environments. The proposed algorithm is evaluated over a real-world datasetsdataset in complex seamless environments. The results show that the proposed algorithm achieves 0.411m and 0.077m horizontal positioning accuracy in obscured outdoor and indoor environments, yielding 71.2 % and 18.1 % improvements compared with the traditional LC integration schemes, respectively. The results show that the incorporation of UWB can instantaneously correct the drifts of VIO in unknown indoor environments. The proposed TC integration algorithm achieves 71.2 % and 18.1 % improvements of horizontal positioning in outdoor and indoor tests, compared with the traditional LC integration, respectively.