本文關(guān)鍵詞：基于視覺的多機(jī)器人協(xié)作SLAM研究　出處：《哈爾濱工業(yè)大學(xué)》2016年博士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 多機(jī)器人系統(tǒng) 多機(jī)器人通信 自然路標(biāo)提取 vSLAM 協(xié)作SLAM

【摘要】：移動機(jī)器人是機(jī)器人學(xué)的一個(gè)重要分支,可應(yīng)用于未知環(huán)境探索、巡邏、服務(wù)等諸多領(lǐng)域。目前移動機(jī)器人技術(shù)還不成熟,多項(xiàng)關(guān)鍵技術(shù)需要改進(jìn),其中作為實(shí)現(xiàn)自主、智能移動機(jī)器人前提的即時(shí)定位與地圖構(gòu)建(SLAM,Simultaneous Localization and Mapping)技術(shù)尤其需要進(jìn)一步研究。本課題源于國家自然科學(xué)基金資助項(xiàng)目“基于局部不變映射的雙目移動機(jī)器人協(xié)作SLAM研究”,深入研究了基于視覺的多機(jī)器人協(xié)作SLAM及其相關(guān)技術(shù)。主要內(nèi)容包括以下幾個(gè)方面:首先研究了多機(jī)器人系統(tǒng)及其任務(wù)分配算法。提出了一種基于UPn P(Universal Plug and Play)技術(shù)的多機(jī)器人系統(tǒng)UMRS(UPn P-based Multi-robot System)。該系統(tǒng)使得成員間具有互發(fā)現(xiàn)能力,避免了多機(jī)器人系統(tǒng)通常存在的單點(diǎn)故障、協(xié)作協(xié)議與底層通信耦合度高等問題。在此基礎(chǔ)上對多機(jī)器人任務(wù)分配技術(shù)進(jìn)行了研究,提出一種適用于MT-SR-TA類型任務(wù)分配問題的方法CMRTA(CHNN-based Multi-robot Task Allocation)。其次,研究了基于雙目視覺的自然路標(biāo)提取與描述方法。針對SLAM過程中存在的作為路標(biāo)的特征點(diǎn)過多而導(dǎo)致數(shù)據(jù)關(guān)聯(lián)復(fù)雜度高、準(zhǔn)確度低的問題,提出一種以特征點(diǎn)的三維信息為基礎(chǔ)的路標(biāo)提取方法。該方法從基于雙目視覺獲得的環(huán)境圖像中提取并匹配特征點(diǎn),重建特征點(diǎn)對應(yīng)的空間點(diǎn)的三維信息,并依據(jù)點(diǎn)間距離進(jìn)行聚類分析得到若干點(diǎn)簇,將每個(gè)點(diǎn)簇整體作為一個(gè)路標(biāo)。為了便于進(jìn)行路標(biāo)間的快速匹配,達(dá)到數(shù)據(jù)關(guān)聯(lián)的目的,對路標(biāo)進(jìn)行標(biāo)識,提出了一種路標(biāo)描述符,論述了其生成方法和匹配過程。為了獲得合適的路標(biāo),本文對Mean Shift聚類算法進(jìn)行了改進(jìn),通過最小點(diǎn)數(shù)、聚類半徑初始值、半徑增長幅度、最大聚類半徑等參數(shù)的調(diào)節(jié),使得算法可以根據(jù)空間點(diǎn)具體的分布情況產(chǎn)生適當(dāng)數(shù)量的不同尺寸的點(diǎn)簇。再次,對基于視覺的SLAM進(jìn)行了研究。針對基于EKF(Extended Kalman Filter)的SLAM算法因?yàn)橛?jì)算復(fù)雜度過高不適合大規(guī)模環(huán)境地圖構(gòu)建的問題,提出了一種基于自然路標(biāo)和局部地圖更新的NL-SLAM(Natural landmark and Local map based SLAM)算法。由于自然路標(biāo)的使用,減少了位姿和地圖估計(jì)的誤差,同時(shí)因?yàn)槁窐?biāo)數(shù)量的減少和局部地圖的使用,有效降低了計(jì)算復(fù)雜度。最后,在以上工作的基礎(chǔ)上,進(jìn)一步研究了基于視覺的多機(jī)器人協(xié)作SLAM。提出一種團(tuán)隊(duì)共享路標(biāo)信息的MR-v SLAM(Multi-robot visual SLAM)算法,該算法改進(jìn)了Fast SLAM使之適用于多機(jī)器人協(xié)作SLAM。在該算法中,多機(jī)器人系統(tǒng)的每個(gè)成員均進(jìn)行SLAM,將其他成員視為自身傳感器的延伸,在SLAM過程中不斷將其他成員的觀測到的路標(biāo)信息融合到自己的地圖中,加快了對大規(guī)模未知環(huán)境的地圖構(gòu)建速度。
[Abstract]:Mobile robot is an important branch of robotics, which can be applied to unknown environment exploration, patrol, service and many other fields. At present, mobile robot technology is not mature, many key technologies need to be improved. As the premise of realizing autonomous and intelligent mobile robot, the real-time location and map construction of SLAM are discussed. Simultaneous Localization and Mapping). In particular, further research is needed. This project is a project supported by the National Natural Science Foundation of China, "the study of Binocular Mobile Robot Cooperative SLAM based on Local invariant Mapping". In this paper, the vision-based multi-robot cooperative SLAM and its related technologies are studied in depth. The main contents include the following aspects:. Firstly, the multi-robot system and its task assignment algorithm are studied. A new algorithm based on UPn P(. UMRS(UPn P-based Multi-robot system based on Universal Plug and). The system enables members to discover each other. The problems such as single point failure and high coupling degree between the cooperation protocol and the underlying communication are avoided in the multi-robot system. On this basis, the multi-robot task allocation technology is studied. This paper presents a method for MT-SR-TA type task assignment problem, CMRTA(. CHNN-based Multi-robot Task allocation. The method of extracting and describing natural landmarks based on binocular vision is studied. Aiming at the problems of high complexity and low accuracy of data association caused by too many feature points as landmarks in the process of SLAM. A road sign extraction method based on 3D information of feature points is proposed, which extracts and matches feature points from environmental images obtained from binocular vision, and reconstructs 3D information of spatial points corresponding to feature points. Cluster analysis based on the distance between points to obtain a number of points, each cluster as a whole as a road sign. In order to facilitate the rapid matching between the road signs, to achieve the purpose of data association, the road signs are identified. In this paper, a signpost descriptor is proposed, and its generating method and matching process are discussed. In order to obtain the appropriate signpost, the Mean Shift clustering algorithm is improved, and the minimum number of points is obtained. The adjustment of the initial value of the clustering radius, the radius increase amplitude and the maximum clustering radius makes the algorithm produce a proper number of different size clusters according to the specific distribution of the spatial points. In this paper, SLAM based on vision is studied. Because of the high computational complexity, the SLAM algorithm is not suitable for large-scale environmental map construction. A NL-SLAM(Natural landmark and Local map based slam based on natural road sign and local map updating is proposed. Algorithm. Due to the use of natural road signs. The errors of pose and map estimation are reduced, and the computational complexity is effectively reduced because of the reduction of the number of road signs and the use of local maps. Finally, based on the above work. Furthermore, the vision-based multi-robot cooperative slam is studied. A MR-v SLAM(Multi-robot visual slam is proposed to share the roadmap information in a team. Algorithm. The algorithm improves Fast SLAM and makes it suitable for multi-robot cooperative slam. In this algorithm, every member of a multi-robot system performs SLAM. The other members are regarded as the extension of their own sensors. In the process of SLAM, the information of the road signs observed by other members is continuously fused into their own maps, which speeds up the construction of maps of large-scale unknown environments.
【學(xué)位授予單位】：哈爾濱工業(yè)大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2016
【分類號】：TP242

【參考文獻(xiàn)】

相關(guān)期刊論文 前4條

1 李園;原魁;鄭睿;;基于無線局域網(wǎng)的多機(jī)器人通信系統(tǒng)性能分析[J];系統(tǒng)仿真學(xué)報(bào);2009年08期

2 原魁;李園;房立新;;多移動機(jī)器人系統(tǒng)研究發(fā)展近況[J];自動化學(xué)報(bào);2007年08期

3 陶海軍;王亞東;郭茂祖;王翰倫;;基于熟人聯(lián)盟及擴(kuò)充合同網(wǎng)協(xié)議的多智能體協(xié)商模型[J];計(jì)算機(jī)研究與發(fā)展;2006年07期

4 范永,譚民;MRCS中機(jī)器人控制體系框架結(jié)構(gòu)[J];控制與決策;2000年03期

，

本文編號：1367001