自适应交互多模型跟踪算法的模型集设计

自适应交互多模型算法（AIMM）是标准交互多模型算法（IMM）的一种改进。但AIMM遇到了新的问题，包括如何选择自适应模型集的结构，如何从基于旧模型集的滤波器中继承各种数据。本文分析了这些问题，并给出了AIMM中模型集和模型转移概率的设计方法。仿真结果表明，改进的AIMM算法比普通的AIMM算法的跟踪性能有明显的提高。

Model set design of the adaptive interacting multiple model tracking algorithm

Adaptive Interacting Multiple Model (AIMM) estimation is a method for improving the Interacting Multiple Model (IMM) estimation. But some new problems appear in the AIMM, such as how to select the structure of the adaptive model set, how to inherit the different data from the filters based on the old model set. In this paper some instructive conclusions and formulas of the design of the model set and the model transition probability are presented to solve these problems. Simulation results show that the tracking performance is improved when considering these factors.