An Augmented Cubature Kalman Filter for Nonlinear Dynamical Systems with Random Parameters
作者单位：College of Computer Science and TechnologySouthwest University for Nationalities
会议名称：《第36届中国控制会议》
会议届次：36
主办单位：Dalian University of Technology;Systems Engineering Society of China (SESC);Technical Committee on Control Theory (TCCT), Chinese Association of Automation (CAA)
会议日期：2017年
学科分类：0711[理学-系统科学] 080902[工学-电路与系统] 07[理学] 0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 070104[理学-应用数学] 071101[理学-系统理论] 0701[理学-数学]
基 金：supported by the National Natural Science Foundation of China under grant NSFC 61102007 the Fundamental Research Funds for the Central Universities under grant 2016NGJPY05
关 键 词：Cubature Kalman filter augmented system cubature point random parameters
摘 要：In this paper, we investigate the Bayesian filtering problem for discrete nonlinear dynamical systems which contain random parameters. An augmented cubature Kalman filter(CKF) is developed to deal with the random parameters, where the state vector is enlarged by incorporating the random parameters. The corresponding number of cubature points is increased, so the augmented CKF method requires more computational complexity. However, the estimation accuracy is improved in comparison with that of the classical CKF method which uses the nominal values of the random parameters. An application to the mobile source localization with time difference of arrival(TDOA) measurements and random sensor positions is provided where the simulation results illustrate that the augmented CKF method leads to a superior performance in comparison with the classical CKF method.