本文關(guān)鍵詞： 同時(shí)定位與地圖構(gòu)建(SLAM) Rao-Blackwellized粒子濾波器 特征點(diǎn)提取 掃描匹配 聚類 粒子群優(yōu)化 重采樣 高斯分布　出處：《南京理工大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：移動(dòng)機(jī)器人導(dǎo)航技術(shù)是機(jī)器人領(lǐng)域的一個(gè)熱門研究話題,其主要目的是使機(jī)器人在未知環(huán)境下能夠自主移動(dòng)到目標(biāo)位置并完成特定的任務(wù)。因此,環(huán)境地圖的構(gòu)建和機(jī)器人的實(shí)時(shí)定位是實(shí)現(xiàn)自主導(dǎo)航的基礎(chǔ),這就是機(jī)器人同時(shí)定位與地圖構(gòu)建(SLAM)技術(shù)。本文主要研究室內(nèi)環(huán)境中基于激光雷達(dá)的移動(dòng)機(jī)器人同時(shí)定位與地圖構(gòu)建問題,重點(diǎn)研究基于Rao-Blackwellized粒子濾波器的RBPF-SLAM方法。針對(duì)傳統(tǒng)的RBPF-SLAM方法中存在的粒子退化及掃描匹配準(zhǔn)確度不高等問題,提出了幾種改進(jìn)措施并進(jìn)行了實(shí)驗(yàn)驗(yàn)證。首先我們?cè)O(shè)計(jì)了一個(gè)機(jī)器人平臺(tái)系統(tǒng),并在這個(gè)平臺(tái)基礎(chǔ)上構(gòu)建了統(tǒng)一的機(jī)器人系統(tǒng)模型用于實(shí)驗(yàn)研究。針對(duì)常規(guī)全局掃描匹配準(zhǔn)確度較低的問題,提出了一種基于特征點(diǎn)的掃描匹配方法。首先將所有雷達(dá)數(shù)據(jù)點(diǎn)劃分為若干個(gè)特征路標(biāo)段,然后在每一個(gè)特征段中基于密度和距離信息提取特征點(diǎn)。在掃描匹配中更加重視特征點(diǎn)的作用,對(duì)特征點(diǎn)賦予更高的匹配得分權(quán)重。最后將基于特征點(diǎn)的掃描匹配方法引入到SLAM算法中校正粒子位姿。實(shí)驗(yàn)表明基于特征點(diǎn)的掃描匹配能夠更加準(zhǔn)確地估計(jì)粒子位姿,使得生成的地圖誤差更小,提高了算法性能。針對(duì)傳統(tǒng)RBPF-SLAM方法中存在的粒子退化和粒子耗盡問題,提出了一種基于區(qū)域粒子群優(yōu)化和部分高斯重采樣的SLAM優(yōu)化方法。為了緩解粒子退化,同時(shí)減少粒子數(shù)量,引入?yún)^(qū)域粒子群優(yōu)化方法來調(diào)整粒子的建議分布。首先把粒子集聚類成多個(gè)粒子簇區(qū)域,計(jì)算每個(gè)區(qū)域的加權(quán)中心位置,然后對(duì)區(qū)域內(nèi)粒子進(jìn)行粒子群優(yōu)化操作驅(qū)使粒子向區(qū)域中心位置移動(dòng),保持粒子集的局部收斂性。為了緩解粒子耗盡,在重采樣過程中,對(duì)粒子按照權(quán)值排序,只對(duì)權(quán)值過高或過低的粒子進(jìn)行重采樣,同時(shí)使用高斯分布采樣得到的粒子,保持粒子的多樣性。實(shí)驗(yàn)表明改進(jìn)方法可以用更少粒子就能得到一張高精度的地圖,減少了算法運(yùn)行時(shí)間。
[Abstract]:Mobile robot navigation technology is a hot research topic in the field of robot. Its main purpose is to enable the robot to move to the target position and complete the specific task independently in the unknown environment. The construction of environmental map and the real-time localization of robot are the basis of autonomous navigation. This is the technology of simultaneous localization and map building of robot. In this paper, the problem of simultaneous location and map construction of mobile robot based on lidar in indoor environment is studied. Focusing on the RBPF-SLAM method based on Rao-Blackwellized particle filter, aiming at the problems of particle degradation and low accuracy of scanning matching in the traditional RBPF-SLAM method, Several improvement measures are proposed and verified by experiments. Firstly, a robot platform system is designed. On the basis of this platform, a unified robot system model is constructed for experimental research. A scanning matching method based on feature points is proposed. Firstly, all radar data points are divided into several feature path segments. Then feature points are extracted from each feature segment based on density and distance information. Finally, the feature point-based scanning matching method is introduced to the SLAM algorithm to correct the particle pose. The experimental results show that the feature point-based scanning matching can estimate the particle pose more accurately. It makes the map error smaller and improves the performance of the algorithm. Aiming at the problem of particle degradation and particle depletion in traditional RBPF-SLAM method, This paper presents a SLAM optimization method based on regional particle swarm optimization and partial Gao Si resampling. The regional particle swarm optimization (RPSO) method is introduced to adjust the proposed distribution of particles. Firstly, the particle clusters are classified into multiple cluster regions, and the weighted center positions of each region are calculated. Then the particle swarm optimization operation in the region drives the particles to move to the center of the region to keep the local convergence of the particle set. In order to alleviate the particle depletion, the particles are sorted according to the weight during the resampling process. Only the particles with too high or too low weights are resampled, and the particles sampled by Gao Si distribution are used to keep the diversity of the particles. Experiments show that the improved method can obtain a highly accurate map with fewer particles. Reduce the running time of the algorithm.
【學(xué)位授予單位】：南京理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP242

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 劉建華;劉華平;楊建國;高蒙;孫富春;;測距式傳感器同時(shí)定位與地圖創(chuàng)建綜述[J];智能系統(tǒng)學(xué)報(bào);2015年05期

2 趙乃剛;鄧景順;;粒子群優(yōu)化算法綜述[J];科技創(chuàng)新導(dǎo)報(bào);2015年26期

3 王忠立;趙杰;蔡鶴皋;;大規(guī)模環(huán)境下基于圖優(yōu)化SLAM的后端優(yōu)化方法[J];哈爾濱工業(yè)大學(xué)學(xué)報(bào);2015年07期

4 王法勝;魯明羽;趙清杰;袁澤劍;;粒子濾波算法[J];計(jì)算機(jī)學(xué)報(bào);2014年08期

5 馬家辰;張琦;馬立勇;;A novel robust approach for SLAM of mobile robot[J];Journal of Central South University;2014年06期

6 朱磊;樊繼壯;趙杰;吳曉光;;改進(jìn)粒子濾波器的移動(dòng)機(jī)器人同步定位與地圖構(gòu)建方法[J];重慶大學(xué)學(xué)報(bào);2014年04期

7 王宏健;王晶;劉振業(yè);;基于迭代擴(kuò)展Kalman濾波建議分布和線性優(yōu)化重采樣的快速同步定位與構(gòu)圖[J];電子與信息學(xué)報(bào);2014年02期

8 宋宇;李慶玲;康軼非;閆德立;;平方根容積Rao-Blackwillised粒子濾波SLAM算法[J];自動(dòng)化學(xué)報(bào);2014年02期

9 梁明杰;閔華清;羅榮華;;基于圖優(yōu)化的同時(shí)定位與地圖創(chuàng)建綜述[J];機(jī)器人;2013年04期

10 曲麗萍;王宏健;曲永印;;基于粒子群優(yōu)化的同步定位與地圖構(gòu)建[J];沈陽工業(yè)大學(xué)學(xué)報(bào);2013年04期

，

本文編號(hào)：1555406