Navigating dense urban environments remains one of the most significant hurdles for autonomous systems due to GNSS signal blockages, multipath effects, and rapidly changing satellite geometry. In our research paper, “Real-time tightly coupled GNSS and IMU integration via Factor Graph Optimization,” we present a robust solution to these challenges.
While Factor Graph Optimization (FGO) is known for its accuracy, it is frequently limited to offline applications. Our work introduces a tightly coupled architecture that enables real-time, causal state estimation. By employing incremental optimization with fixed-lag marginalization, our method maintains high performance even in GNSS-degraded scenarios. Evaluated using the UrbanNav dataset in highly urbanized settings, this approach provides the reliability and precision necessary for the next generation of autonomous vehicles operating in complex cityscapes
https://arxiv.org/abs/2603.03556
