Novel Sequential Monte Carlo Method to Bearing Only Tracking
Extended Kalman Filter (EKF) and Unscented Kalman Filter (UKF) are often used in target tracking, but the required Posterior Density Function (PDF) is still approximated by a Gaussian, which may be a gross distortion of the true underlying structure and lead to filter differgence when performing EKF or UKF. Because the uncertainty of process model in bearing only tracking is small compared with the uncertainty of the measurements, resample introduces the problem of loss of differsity among the particles with Particle Filter. This may lead to undesired clustering of the samples and eventually inaccurate results. The SMCEKF and SMCUKF algorithms given in this paper ensure the independency of particles by introducing parallel independent EKFs and UKFs for the bearing only tracking problem. The resample technique, which was suggested in the particle filter as a method to reduce the degeneracy problem, is given up. The required density of the state vector is represented as a set of random samples, which is updated and propagated recursively on their own estimate. The performance of the filters is greatly superior to the standard EKF and UKF. Analysis and simulation results of the bearing only tracking problem have proved validity of the algorithms.
Hongquan Qu Shaohong Li
School of Electronics and Information Engineering, Beihang University Beijing 100083, China
国际会议
Progress in Electromagnetics Research Symposium 2007(2007年电磁学研究新进展学术研讨会)(PIERS 2007)
北京
英文
918-924
2007-03-26（万方平台首次上网日期，不代表论文的发表时间）