LIO-SAM for Vehicle Localization Using FGO Architecture

In intelligent transportation systems, accurate positioning is crucial for ensuring the safe and efficient operation of vehicles. This paper addresses the positioning challenges in satellite-constrained scenarios by proposing a solution based on Lidar-Inertial Odometry via Smoothing and Mapping (LIO-SAM) We employed the LIO-SAM algorithm as our core positioning mechanism and designed a multi-sensor fusion positioning architecture that integrates LiDAR, Inertial Measurement Units (IMUs), and GNSS data to enhance positioning accuracy and robustness. By processing multisensor data obtained from on-site railway measurements, we validated and evaluated the feasibility and effectiveness of the algorithm. The experimental results indicate that this method maintains accurate and robust positioning even in satellite-constrained scenarios and achieves higher precision compared to traditional satellite positioning methods. This is significant for improving the safety and efficiency of vehicle operations.