ABSTRACT In cross‐domain target tracking involving an unmanned surface vehicle (USV) and autonomous underwater vehicle (AUV), the high maneuverability of these platforms combined with complex marine environments may result in tracking latency and filter divergence. This paper introduces a time‐varying attenuation UKF (TA‐UKF) method designed to dynamically adapt the state covariance matrix in response to target maneuvers and environmental disturbances. The proposed methodology integrates time and direction‐of‐arrival measurements within a CT rate and velocity motion model. By incorporating the instantaneous innovation sequence to regulate the attenuation factor, the algorithm effectively adjusts the prediction covariance during model mismatches to prioritize real‐time measurements. Monte Carlo simulations demonstrate that the TA‐UKF outperforms not only standard filters (EKF/UKF) but also advanced methods. Specifically, it eliminates the model‐switching latency in the interacting multiple model and the statistical adaptation lag of Sage‐Husa methods. Furthermore, the algorithm exhibits robustness to unmodeled ocean currents and non‐Gaussian measurement outliers. Field experiments conducted at Liquan Lake further validate the algorithm's practicality and robustness under real‐world acoustic conditions.
Zhang et al. (Fri,) studied this question.