做无人机状态估计或机器人定位的团队，终于有了一个能自适应噪声变化、在传感器中断时依然可靠的滤波方案，值得在实机测试中尝试。
针对无人机在动态环境中面临的遥测中断、结构振动等噪声非平稳问题，传统卡尔曼滤波假设失效。Sage-Husa卡尔曼滤波虽能在线估计噪声统计量，但其静态标量遗忘因子在稳态稳定性和瞬态响应间存在权衡。本文提出NDR-SHKF，用分层循环网络学习向量化的记忆衰减策略，替代标量参数。该网络处理白化新息序列，浅层状态捕捉瞬时异常，深层状态编码持续动态趋势，并通过辅助重构目标防止特征崩溃。在混沌吸引子和真实无人机飞行数据集上的评估表明，该方法在跨域泛化和传感器中断时优于纯数据驱动方法和经典自适应估计器。
Learned Memory Attenuation in Sage-Husa Kalman Filters for Robust UAV State Estimation
Unmanned Aerial Vehicles in dynamic environments face telemetry outages, structural vibrations, and regime-dependent noise that invalidate the stationary covariance assumptions of classical Kalman filters. The Sage-Husa Kalman Filter (SHKF) estimates noise statistics online, but its reliance on a static, scalar forgetting factor forces a strict compromise between steady-state stability and transient responsiveness. We introduce the N-Deep Recurrent Sage-Husa Filter (NDR-SHKF), which replaces this scalar parameter with a vector-valued memory attenuation policy learned by a hierarchical recurrent network operating on whitened innovation sequences. A bifurcated architecture routes shallow recurrent states to capture instantaneous sensor anomalies and deep states to encode sustained dynamic trends, while an auxiliary reconstruction objective prevents feature collapse. The complete filter, including recursive covariance updates, is trained end-to-end via backpropagation through time to directly minimize state estimation error. Evaluations on topologically distinct chaotic attractors demonstrate cross-domain generalization, outperforming purely data-driven baselines that diverge under out-of-distribution dynamics. Furthermore, evaluations on recorded real-world UAV flight datasets validate the framework's practical viability, demonstrating its capacity to bridge transitions into proprioceptive dead reckoning and outperform classical adaptive estimators during sensor outages.