CAJ | 학술논문

针对粒子滤波存在的权值退化问题,从研究粒子滤波的建议分布函数出发,提出自适应渐消扩展Kalman粒子滤波方法.该方法使用自适应渐消扩展Kalman滤波产生建议分布,可在线调节参数,从而使得系统具有更好的自适应性和鲁棒性.与用转移先验、扩展Kalman滤波产生建议分布的粒子滤波方法相比,自适应渐消扩展Kalman粒子滤波进一步提高了粒子滤波的精度.
침대입자려파존재적권치퇴화문제,종연구입자려파적건의분포함수출발,제출자괄응점소확전Kalman입자려파방법.해방법사용자괄응점소확전Kalman려파산생건의분포,가재선조절삼수,종이사득계통구유경호적자괄응성화로봉성.여용전이선험、확전Kalman려파산생건의분포적입자려파방법상비,자괄응점소확전Kalman입자려파진일보제고료입자려파적정도.
In respect to the degradation of the weight existing in the particle filtering, from the point of view of the proposal distribution function, a new particle filtering method named the adaptive fading extended Kalman particle filtering is put forward. This method takes advantage of the adaptive fading extended Kalman filter to generate the proposal distribution function, and can adjust the parameter on line, which has better self adaptability and robustness. Compared with the common particle filtering methods whose proposal distribution function coming from the transition prior or the extended Kalman filtering, the adaptive fading extended Kalman particle filter has improved the accuracy of the particle filtering.