本文選題：雙目立體視覺(jué) + 同時(shí)定位與地圖構(gòu)建�。� 參考：《東華大學(xué)》2017年碩士論文

【摘要】：同步定位與地圖構(gòu)建(Simultaneous location and mapping,SLAM)是指機(jī)器人在未知環(huán)境中創(chuàng)建環(huán)境地圖并推斷自身位姿的過(guò)程。近年來(lái),SLAM問(wèn)題的解決對(duì)于移動(dòng)機(jī)器人實(shí)現(xiàn)自主定位具有十分重要的意義,已逐漸成為移動(dòng)機(jī)器人導(dǎo)航及計(jì)算機(jī)視覺(jué)領(lǐng)域的熱門(mén)研究課題。由于SLAM中機(jī)器人的特征點(diǎn)匹配往往出現(xiàn)誤匹配且匹配的復(fù)雜度較高而導(dǎo)致機(jī)器人構(gòu)建地圖的周期較長(zhǎng),定位的實(shí)時(shí)性較差。為此,我們對(duì)SLAM的特征匹配與定位技術(shù)展開(kāi)理論研究。本文針對(duì)雙目立體視覺(jué)SLAM系統(tǒng)展開(kāi)研究,具體工作如下:(1)介紹了SLAM系統(tǒng)框架,分析了兩種常用的SLAM濾波算法—擴(kuò)展卡爾曼濾波器算法和粒子濾波器算法。給出了本文研究雙目立體視覺(jué)SLAM的觀測(cè)與運(yùn)動(dòng)兩大基本模型,在此基礎(chǔ)上提出了本文研究的雙目立體視覺(jué)SLAM的整體結(jié)構(gòu)框架。(2)對(duì)雙目立體視覺(jué)SLAM的數(shù)據(jù)關(guān)聯(lián)問(wèn)題進(jìn)行了研究。介紹了特征提取與匹配技術(shù)的相關(guān)知識(shí),并針對(duì)SIFT特征提取與匹配算法的維數(shù)較大且存在較大的誤匹配率問(wèn)題,結(jié)合支持向量機(jī)(SVM)的序列最小優(yōu)化算法(SMO)進(jìn)一步細(xì)匹配提出基于序列最小優(yōu)化的SIFT特征提取與匹配算法—SMO-SIFT算法。最后通過(guò)MATLAB仿真表明SMO-SIFT算法降低了算法的維數(shù),改善了算法的實(shí)時(shí)性,同時(shí)提高了算法精確度。(3)對(duì)SLAM的路徑估計(jì)問(wèn)題進(jìn)行了研究。介紹了RaoBlackwellised粒子濾波器算法(RBPF)并針對(duì)RBPF算法的粒子數(shù)目的增加會(huì)頻繁重采樣從而導(dǎo)致“粒子退化”問(wèn)題,提出了基于小生境遺傳優(yōu)化算法的INGO-RBPF算法。最后通過(guò)MATLAB仿真表明INGO-RBPF算法具較高的估計(jì)精度和穩(wěn)定性,抗干擾能力較強(qiáng),比較適合應(yīng)用在SLAM實(shí)時(shí)定位中。(4)在機(jī)器人操作系統(tǒng)(ROS)的環(huán)境下將SMO-SIFT和INGORBPF算法運(yùn)用于實(shí)驗(yàn)環(huán)境中。給出了SLAM系統(tǒng)中的地圖構(gòu)建、機(jī)器人控制及遠(yuǎn)程控制三大模塊的軟硬件設(shè)計(jì),實(shí)驗(yàn)結(jié)果表明機(jī)器人能夠正確的構(gòu)建出環(huán)境地圖和成功定位,運(yùn)行結(jié)果比較理想。
[Abstract]:Synchronous location and mapping (slam) is a process in which robots create environmental maps and infer their posture in unknown environments. In recent years, the solution of slam problem is very important for mobile robot to achieve autonomous positioning, and has gradually become a hot research topic in the field of mobile robot navigation and computer vision. Due to the false matching of robot feature points in slam and the high complexity of matching, the robot has a long period of map construction and poor real-time localization. Therefore, the feature matching and localization techniques of slam are studied theoretically. The main work of this paper is as follows: (1) the framework of slam system is introduced, and two commonly used slam filtering algorithms, extended Kalman filter algorithm and particle filter algorithm, are analyzed. In this paper, two basic models of observation and motion of binocular stereo slam are presented. Based on these two models, the whole frame of binocular stereo slam is proposed. (2) the data association problem of binocular stereo slam is studied. This paper introduces the knowledge of feature extraction and matching, and aims at the problem that sift feature extraction and matching algorithm has large dimension and large mismatch rate. Combined with support vector machine (SVM) sequence minimum optimization algorithm (SMO), a SMO-SIFT feature extraction and matching algorithm based on sequential minimum optimization is proposed. Finally, MATLAB simulation shows that SMO-SIFT algorithm reduces the dimension of the algorithm, improves the real-time performance of the algorithm, and improves the accuracy of the algorithm. (3) the path estimation problem of slam is studied. In this paper, Rao Blackwellised particle filter algorithm (RBPF) is introduced. Aiming at the problem of "particle degradation" caused by increasing the number of particles in RBPF algorithm, an INGO-RBPF algorithm based on niche genetic optimization algorithm is proposed. Finally, MATLAB simulation shows that INGO-RBPF algorithm has high estimation accuracy and stability, strong anti-jamming ability, and is more suitable for real-time localization of slam. (4) SMO-SIFT and INGORBPF algorithms are applied in the environment of robot operating system (Ros). The software and hardware design of the three modules in slam system are given. The experimental results show that the robot can correctly construct the map of environment and locate successfully, and the result of running is ideal.
【學(xué)位授予單位】：東華大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP242;TN713

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 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

2 顏雪軍;趙春霞;袁夏;;2DPCA-SIFT:一種有效的局部特征描述方法[J];自動(dòng)化學(xué)報(bào);2014年04期

3 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

4 馬家辰;張琦;謝瑋;馬立勇;;基于粒子群優(yōu)化的移動(dòng)機(jī)器人SLAM方法[J];北京理工大學(xué)學(xué)報(bào);2013年11期

5 蒲興成;譚少峰;張毅;;基于改進(jìn)FAST算法的移動(dòng)機(jī)器人導(dǎo)航[J];智能系統(tǒng)學(xué)報(bào);2014年04期

6 吳俊君;胡國(guó)生;;室外環(huán)境下移動(dòng)機(jī)器人視覺(jué)SLAM算法改進(jìn)[J];計(jì)算機(jī)工程與設(shè)計(jì);2013年08期

7 趙長(zhǎng)春;姜曉愛(ài);金英漢;;非線性回歸支持向量機(jī)的SMO算法改進(jìn)[J];北京航空航天大學(xué)學(xué)報(bào);2014年01期

8 王民;劉偉光;;基于改進(jìn)SIFT特征的雙目圖像匹配算法[J];計(jì)算機(jī)工程與應(yīng)用;2013年02期

9 黃利;杜偉偉;丁立新;;基于Sigmoid慣性權(quán)重自適應(yīng)調(diào)整的粒子群優(yōu)化算法[J];計(jì)算機(jī)應(yīng)用研究;2012年01期

10 牟忠凱;隋立芬;張清華;甘雨;;顧及線性化模型誤差補(bǔ)償?shù)目柭鼮V波算法[J];武漢大學(xué)學(xué)報(bào)(信息科學(xué)版);2011年09期

相關(guān)碩士學(xué)位論文 前2條

1 查尤平;平滑型SLAM中數(shù)據(jù)關(guān)聯(lián)的魯棒性研究[D];北京交通大學(xué);2016年

2 姜雪菲;雙目立體視覺(jué)SLAM研究[D];北京交通大學(xué);2014年

，

本文編號(hào)：2070737