基于区域粒子群优化和部分高斯重采样的SLAM方法  

SLAM Method Based on Region Particle Swarm Optimization and Partial Gaussian Resampling

作　　者：王田橙 蔡云飞[1] 唐振民[1] 

机构地区：[1]南京理工大学智能机器人研究所,南京210094

出　　处：《计算机工程》2017年第11期310-316,共7页Computer Engineering

基　　金："核高基"重大专项(2015ZX01041101);国家自然科学基金青年基金(61305134);国家教育部博士点基金(20133219120035)

摘　　要：为解决Rao-Blackwellized粒子滤波同时定位与地图构建方法中存在的粒子退化和粒子耗尽现象,提出一种同时定位与地图构建优化方法。为缓解粒子退化,通过区域粒子群优化方法调整粒子的建议分布,把粒子集聚类成多个区域,计算每个区域的加权中心位置,对区域内粒子进行粒子群优化操作使得粒子向区域中心位置移动。在重采样过程中,给出一种部分高斯重采样算法,只对权值过高或过低的粒子进行重采样。实验结果表明,与MT-GMapping方法相比,改进方法可以通过更少的粒子得到精度更高的地图,满足实际使用的需求。In order to solve the phenomenon that Simultaneous Localization And Mapping（ SLAM） method based on Rao-Blackwellized particle filtering might lead to particle degeneracy and particle depletion,a SLAM optimization method is proposed. To mitigate particle degeneracy,a kind of region Particle Swarm Optimization（ PSO） method is introduced to adjust the particles＇ proposal distribution. All particles are clustered into several regions and the weighted central position of each region is calculated. With the particle swarm optimization operation,the particles of each region are derived to the regional central position. During the resampling process,a partial Gaussian resampling algorithm is proposed,in which only the particles whose weight is too high or too low will be processed. Experimental results prove that compared with MT-Gmapping method,the improved method can use fewer particles to generate a high-precision map and satisfy the actual requirement.

关 键 词：同时定位与地图构建 RAO-BLACKWELLIZED粒子滤波器 聚类 粒子群优化 重采样 高斯分布 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]