Abstract: With the precision demand of a fixed moment at the interval of observation time in target tracking application, this paper presents a target tracking algorithm which is applicable to nonlinear model—fixed point cubature Rauch-Tung-
Striebel smoother. The algorithm combines the traditional cubature Rauch-Tung-Striebel smoother which is applied to nonlinear state-space model with the fixed point strategy in Gaussian optimal smoothing, and it improves the precision of fixed point estimate effectively. An example is used to demonstrate the new algorithm’s performance.

Key words: fixed point, Rauch-Tung-Striebel smoother, cubature transformation

摘要： 针对在目标跟踪实际应用中对于观测时间区间的某个固定时刻估计值精度的要求，提出了一种运用于非线性模型中的目标跟踪算法——固定点容积Rauch-Tung-Striebel平滑。该算法将高斯最优平滑中固定点平滑策略与传统的运用于非线性状态空间模型的容积Rauch-Tung-Striebel平滑相结合，有效地提高了固定点估计值的精度。仿真结果验证了新算法的有效性。

关键词: 固定点, Rauch-Tung-Striebel平滑, 容积变换