Answers are grounded in this paper and cite their sources.
Demonstrates improved state estimation accuracy in UAV tracking, suggesting a new approach for varying noise conditions.
Using UAVs for bearings-only tracking (BOT) of moving targets is a key challenging issue due to weak observability and time-varying measurement noises. To overcome these limitations, we introduce a hybrid framework that integrates a square-root continuous-discrete extended Kalman filter (MSCDEKF) with the Mamba-2 neural network. The MSCDEKF improves estimation accuracy and numerical stability under weak observability conditions by adopting continuous-time state update while ensuring numerical stability through square-root covariance implementation. Meanwhile, the state-space modeling of the Mamba-2 network provides superior continuous measurement noise prediction compared to conventional recurrent neural network approaches by explicitly capturing signal evolution dynamics. Experimental validation in constant velocity (CV) and constant turn (CT) UAV-based BOT scenarios demonstrates that our framework achieves the following: (1) at least a 34.5% improvement in state estimation accuracy (measured by average root-mean-square error, ARMSE) compared with variational Bayesian filters; (2) significant improvements in noise variance estimation; and (3) parameter-free operation with minimal manual tuning. This work establishes a different paradigm for robust UAV-based BOT in complex environments characterized by unknown and time-varying noise conditions.
No takes yet. Share an insight, caveat, or question.
Wu et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: