Fuzzy fixed-time multi-source fusion with attention-based neural networks for reliable navigation under satellite signal loss

Abstract

Accurate and reliable navigation is critical for autonomous systems, particularly in environments with sensor errors, unknown dynamic variations, global navigation satellite system (GNSS) outages, and complex maneuvers. This paper presents an innovative navigation framework that combines an adaptive observer with fixed-time convergence and a deep learning model based on an attention-equipped convolutional neural network (CNN) and a gated recurrent unit (GRU) with conditional fusion of air-data sensors in both GNSS-available and GNSS-denied conditions. At the core of the system lies a nonlinear observer with theoretical guarantees for fixed-time convergence, capable of estimating both the system state and perturbations independently of initial conditions. To enhance resilience against noise, sensor drift, and the limitations of low-cost inertial measurement units (IMUs), a fuzzy logic-based mechanism is employed to adaptively adjust observer gains using the normalized estimation error and its variance. During GNSS outages, the deep learning predictor — based on CNN and GRU with an attention mechanism — is used to estimate horizontal position changes from IMU data. Convolutional neural network layers extract local features, GRU layers capture temporal dependencies, and the attention mechanism prioritizes informative segments, enabling accurate and reliable predictions. In addition, a conditional sensor fusion strategy is proposed, which selectively utilizes pitot tube velocity and barometric altitude only during GNSS-denied phases, effectively mitigating the drift of the strap-down inertial navigation system (SINS). Field experiments across complex trajectories — including several GNSS interruptions — demonstrate that the proposed hybrid artificial intelligence-based framework offers improved estimation accuracy and real-time autonomous navigation in challenging real-world environments.