自校正分布式观测融合Kalman滤波器
doi: 10.3724/SP.J.1146.2005.01471
Self-tuning Distributed Measurement Fusion Kalman Filter
-
摘要: 对于带未知噪声统计和带具有相同右因子的观测阵的多传感器系统,应用加权最小二乘(WLS)法可得到一个等价的融合观测方程。该文应用现代时间序列分析方法,基于新息模型参数的在线辨识,可估计未知噪声方差,进而提出了自校正加权观测融合Kalman滤波器。在新息模型参数估计是一致的和观测数据是有界的假设下,该文证明了自校正Kalman滤波器收敛于当噪声统计已知时的全局最优融合Kalman滤波器,因而它具有渐近全局最优性。最后给出了一个4传感器跟踪系统的仿真例子并验证了其有效性。Abstract: For the multisensor system with unknown noise statistics, and with the measurement matrices having a same right factor, based on Weighted Least Squares(WLS) method, an equivalent fusion measurement equation is obtained. Using the modern time series analysis method, based on on-line identification of the innovation model parameters, unknown noise variances can be estimated, and a self-tuning weighted measurement fusion Kalman filter is presented. Under the assumptions that the parameter estimation of the innovation model is consistent and the measurement data are bounded, it is proved that the self-tuning Kalman filter converges to globally optimal fusion Kalman filter with known noise statistics, so that it has asymptotic global optimality. A simulation example for a tracking system with 4-sensor shows its effectiveness.
-
邓自立,郝钢,吴孝慧. 两种加权观测融合方法的全局最优性和完全功能等价性. 科学技术与工程,2005, 5(13): 860-865.[2]邓自立. 自校正滤波理论及其应用现代时间序列分析方法. 哈尔滨:哈尔滨工业大学出版社,2003: 1-343.[3]Kailath T, Sayed A H, and Hassibi B. Linear Estimation. Upper Saddle River, New Jersey: Prentice-Hall, 2000: 78-116.[4]邓自立. 最优估计理论建模、滤波、信息融合估计. 哈尔滨:哈尔滨工业大学出版社,2005: 1-490.[5]邓自立,马建为,高媛. 两传感器自校正信息融合Kalman滤波器. 科学技术与工程,2003, 3(4): 321-324.[6]Sun Shuli and Deng Zili. Multi-sensor optimal information fusion Kalman filter[J].Automatica.2004, 40(6):1017-1023[7]Deng Zili, Gao Yuan, and Mao Lin, et al.. New approach to information fusion steady-state Kalman filtering[J].Automatica.2005, 41(10):1695-1707[8]郑大钟. 线性系统理论(第2版). 北京:清华大学出版社,2002: 441-466.
计量
- 文章访问数: 3284
- HTML全文浏览量: 92
- PDF下载量: 675
- 被引次数: 0