GVINS: Tightly Coupled GNSS-Visual-Inertial Fusion for Smooth and Consistent State Estimation

Visual-inertial odometry (VIO) is known to suffer from drifting, especially over long-term runs. In this article, we present GVINS, a nonlinear optimization-based system that tightly fuses global navigation satellite system (GNSS) raw measurements with visual and inertial information for real-time and drift-free state estimation. Our system aims to provide accurate global six-degree-of-freedom estimation under complex indoor-outdoor environments, where GNSS signals may be intermittent or even inaccessible. To establish the connection between global measurements and local states, a coarse-to-fine initialization procedure is proposed to efficiently calibrate the transformation online and initialize GNSS states from only a short window of measurements. The GNSS code pseudorange and Doppler shift measurements, along with visual and inertial information, are then modeled and used to constrain the system states in a factor graph framework. For complex and GNSS-unfriendly areas, the degenerate cases are discussed and carefully handled to ensure robustness. Thanks to the tightly coupled multisensor approach and system design, our system fully exploits the merits of three types of sensors and is able to seamlessly cope with the transition between indoor and outdoor environments, where satellites are lost and reacquired. We extensively evaluate the proposed system by both simulation and real-world experiments, and the results demonstrate that our system substantially suppresses the drift of the VIO and preserves the local accuracy in spite of noisy GNSS measurements. The versatility and robustness of the system are verified on large-scale data collected in challenging environments. In addition, experiments show that our system can still benefit from the presence of only one satellite, whereas at least four satellites are required for its conventional GNSS counterparts.

Automated summary

This article presents GVINS, a system that tightly fuses GNSS, visual, and inertial information for drift-free state estimation. The system utilizes a coarse-to-fine initialization process and a factor graph framework to connect global measurements with local states and constrain system states. Experimental results demonstrate that our system effectively suppresses VIO drift and maintains local accuracy under noisy GNSS measurements.