CAJ | 학술논문

在非线性条件下，扩展Kalman 滤波（ EKF）的应用最为广泛。但是，由于它采用了Taylor展开的线性变换来近似非线性模型，因而存在计算量大、实时性差、估计精度低等缺点。粒子滤波（ PF）用一些带有权值的随机样本（粒子）来表示所需要的后验概率密度，并通过这些粒子的加权来估计目标运动的状态，从而得到基于物理模型的近似最优数值解，具有精度高、收敛速度快等特点。通过仿真实验将PF与EKF的性能进行了对比，并且研究了噪声协方差与粒子数对PF的影响。 PF与EKF的对比实验结果表明，在强非线性条件下，PF比EKF跟踪精度更高，误差更低。
재비선성조건하，확전Kalman 려파（ EKF）적응용최위엄범。단시，유우타채용료Taylor전개적선성변환래근사비선성모형，인이존재계산량대、실시성차、고계정도저등결점。입자려파（ PF）용일사대유권치적수궤양본（입자）래표시소수요적후험개솔밀도，병통과저사입자적가권래고계목표운동적상태，종이득도기우물리모형적근사최우수치해，구유정도고、수렴속도쾌등특점。통과방진실험장PF여EKF적성능진행료대비，병차연구료조성협방차여입자수대PF적영향。 PF여EKF적대비실험결과표명，재강비선성조건하，PF비EKF근종정도경고，오차경저。
The Extended Kalman Filter ( EKF) is the most popular approach to recursive nonlinear estima-tion.Because it is a linearization technique based on a first order Taylor series expansion of the nonlinear system and measurement functions about the current estimate of the state , it often provides an insufficiently accurate rep-resentation in many cases .The particle filtering method ( PF) has become an important alternative to the EKF . It represents the desired distributions by discrete random measures , which are composed of weighted particles .It has a high accuracy and a rapid convergence .In this paper , the comparison experiment between the PF and EKF has been carried out , and a study about the influence of the particle filter by the noise covariance and the particle number are presented .The comparison experiment shows that the target tracking accuracy of PF is higher than that of EKF under the condition of strong non-linear system .