提出一种应用于机场泊位引导系统的模糊联合卡尔曼滤波算法,通过将视觉和激光传感器的信息融合,解决了基于单一传感器引导系统可靠性不高的问题.该算法监视测量值是否发生较大波动,应用模糊推理系统调整各局部滤波器输出状态向量的协方差阵,在线修正全局穗波器内各融合信息的权值,降低了波动数据对估值的影响.实验证明该算法对测量值的波动有较强的鲁棒性,提高了机场泊位引导系统的可靠性.
This paper presents an algorithm of Fuzzy Federal Kalman Filtering used for the Airport Automatic Docking Guidance System. Information of vision and laser sensors is fused to improve the reliability of the single-sensor system. Monitoring the fluctuation of the measure values, adjusting the state vector covariance of each local filtering in use of the Fuzzy Inference Sys- tem (FIS) and modifying the weight of each fusion data online in main filtering, the algorithm reduces the disturbance of the fluctuation data. The results of the experiment prove that this algorithm has good robustness for fluctuation of the measure values and improves the reliability of the system.