Answers are grounded in this paper and cite their sources.
The integration of the global navigation satellite system (GNSS) and inertial navigation system based on factor graph optimization (FGO) holds significant potential for achieving accurate and robust vehicle localization. However, in complex environments, the uncertainty of GNSS measurement noise severely affects the accuracy of state estimation in FGO. To address this problem, an adaptive FGO integrated navigation framework based on innovation-based adaptive estimation (IAE) is proposed. First, the inertial measurement unit preintegration factor, GNSS positioning factor, and prior factor are constructed for FGO. Then, an IAE-based approach, which estimates the GNSS measurement noise covariance matrix using innovations within a sliding time window, is introduced into the FGO framework to enable simultaneous estimation of vehicle states and measurement noise. To further enhance the accuracy of measurement noise estimation and the adaptability to varying conditions, a strategy based on innovation variance is adopted to dynamically adjust the size of the window for covariance estimation. The proposed method is evaluated through numerical simulations and real-world experiments. The experiment results demonstrate the effectiveness of the proposed approach in enhancing localization accuracy by accurately estimating time-varying GNSS measurement noise.
No takes yet. Share an insight, caveat, or question.
Mao et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: