【摘要】 研究机器人移动过程引入粒子滤波进行状态估计问题,粒子滤波中的重采样是为了解决粒子群退化现象而引入的方法。根据重采样方法(SIR)解决粒子退化的同时却带来了粒子的贫化问题,因而降低了滤波器的收敛性能。传统的各种重采样改进方法都是用优等粒子替代劣等粒子,因而会导致粒子多样性的丧失。针对上述问题,提出了一种趋优重采样方法,使次等粒子向优等粒子的方向移动,且分布在优等粒子的周围,因而有效地保持了粒子的多样性。针对机器人即时定位与制图(SLAM)问题的仿真实验表明,所提出的趋优重采样算法能够有效地改善粒子滤波器的性能。更多还原

【Abstract】 Resampling procedure in Particle Filter aims for degradation of swarm of particle.Basic resampling method-SIR is capable of alleviating particle degeneration,but poses particles impoverishment at the same time.Less diversity has severe consequence in the filter estimation accuracy.Various resample approaches have been developed in recent years,including multi-nominal resample,residual resample,stratified resample and systematic resample.All of them,however,will inevitably lead to the losing of diversity in scatter of particles because they simply replace lower weighed particles with higher weighed particles.In this paper,an optimal taxis resampling algorithm is presented.It is suggested that inferior particles move towards the direction of superior ones and distributed around latter.By doing so,diversity of particles is well kept.It is indicated by the simulations that the proposed optimal taxis resampling method improves the performance of Particle Filter.更多还原