Research on Unmanned Positioning Technology Based on Factor Graph Optimization

A fusion positioning algorithm based on factor graph optimization is proposed to tackle the issues of low positioning accuracy and poor environmental adaptability associated with a single sensor in the unmanned positioning system. This algorithm integrates data from multiple sources, including the Global Positioning System (GPS), Inertial Measurement Unit (IMU), Light Detection and Ranging (LiDAR), and wheel tachometer. Through front-end processing and back-end optimization, the algorithm significantly enhances the accuracy and adaptability of the unmanned positioning system. Validated under a scenario of the missing differential signal and laser point cloud features, the fusion positioning algorithm, harnessing factor graph optimization, exhibits substantial accuracy improvements of 84% and 63% over laser-based Simultaneous Localization and Mapping (SLAM) and GPS, respectively.