带遗忘因子的自适应迭代容积卡尔曼滤波算法

An AICKF Algorithm with Forgetting Factor

自适应迭代滤波算法作为典型的滤波改进算法,有效提高了滤波精度,但旧数据影响过大,导致滤波发散;遗忘因子滤波算法虽然引进遗忘因子减少了旧数据的影响,但是其滤波算法本身的精度不高,难以处理高度非线性问题。基于此,本文借鉴遗忘因子的滤波算法和自适应迭代无迹卡尔曼滤波算法的思想,把遗忘因子与自适应迭代容积卡尔曼滤波相结合,这样既可以发挥遗忘因子的作用,减小历史数据对滤波结果的影响,又可以提高滤波算法本身精度和处理非线性问题的能力。仿真实验表明,该算法可以有效减小误差且提高滤波精度。

Adaptive iteration filter as the typical improvement filter algorithm effectively rises to the filter accuracy, but the old data once influences greatly lead to the filter’s exhale. Although the filtering algorithm with forgetting factor reduces the influence of old data. But in fact, the filter’s exhale is not high, and it is difficult to deal with the high degree of non-linear problem. So this passage learn from Kalman filter with forgetting factor and AIUKF a thought of calculate way, this can not only play the role of forgetting factor, reduce the impact of historical data on the filtering results, but also can improve the accuracy of the filter algorithm and the ability to deal with nonlinear problems. The simulation experiment results indicate that the algorithm effectively reduces the error and improves the filtering accuracy.