Please use this identifier to cite or link to this item:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/90699
Title: | 在比例未知的樓層平面圖上進行基於空間圖形方法的定位與導航 Spatial Graph-based Localization and Navigation on Scaleless Floorplan |
Authors: | 游祖霖 Zu Lin Ewe |
Advisor: | 傅立成 Li-Chen Fu |
Keyword: | 平面圖定位,平面圖導航,移動型機器人,場景圖導航,圖形空間表示, Floorplan Localization,Floorplan Navigation,Mobile Robots,Graph-based Navigation,Spatial Graph Representation, |
Publication Year : | 2023 |
Degree: | 碩士 |
Abstract: | 受到科技進步、人口結構變化以及對自動化和無接觸互動的需求的推動,服務機器人在大眾應用領域的利用預計在不久的將來會大幅增加。然而,要在未勘察的環境中成功部署機器人,有效的導航能力成為關鍵因素。現有方法主要依賴於自主或遠程操作的環境探索和地圖建立來理解環境,但這些方法對於缺乏技術能力的使用者可能存在挑戰。相反,人類展示了使用抽象平面圖進行導航的卓越能力,利用它們提供的高層次空間信息。這引出了一個問題,即服務機器人能否利用基於樓層平面圖的導航技術來提高它們在陌生環境中的性能和可用性。通過利用平面圖作為導航輔助工具,機器人有可能減輕對廣泛探索和地圖創建的需求,簡化使用者的操作和互動過程。儘管有關平面圖定位和導航的文獻存在,但大多數現有方法僅考慮具有精確測量或比例的樓層平面圖,這可能很難獲得並且可能需要機器人預先探索環境。這一限制影響了它們的實用性,特別是對於旨在大規模部署的服務機器人而言。因此,需要新的方法,可以利用平面圖信息而無需依賴精確的比例或廣泛的預先探索。
本碩士論文旨在解決上述挑戰,研究樓層平面圖導航在未勘察的環境中對服務機器人的可行性。具體而言,我們提出了一種新的平面圖定位方法,利用樓層平面圖的尺度不變幾何特徵,實現無需依賴精確比例信息的導航。此外,我們引入了一種增量圖擴充方法,從機器人觀測中提取實際的空間信息和物件語義信息,豐富了樓層平面圖的圖形表示,提供對環境的準確和全面的理解。最後,我們開發了一個高效的導航框架,能夠利用樓層平面圖的固有結構和實時觀測。通過廣泛的實驗和評估,我們將我們的方法與基線進行比較,評估其在表示環境、定位精度和導航效能方面的質量。 這項研究的成果有助於推動服務機器人在未勘察的環境中的部署,尤其是在廣泛探索和地圖建立可能對使用者來說不切實際或技術上具有挑戰性的情況下。通過利用抽象樓層平面圖導航的優勢,我們旨在促進服務機器人的廣泛應用,使它們能夠無縫地融入各種公共場景。 Technological advancements, shifting demographics, and the drive for automation and contactless interactions are prompting an expected surge in service robot use for mass public applications. Nevertheless, effective navigation in unfamiliar environments remains a critical challenge for successful deployment. Current navigation methods, which rely on autonomous or teleoperated exploration and map building, pose technical difficulties for end-users. In contrast, humans can effectively navigate using abstract floorplans, suggesting the potential for service robots to leverage similar techniques. The practical application of floorplan-based navigation, however, is currently limited by methods that require exact measurements or scale and significant pre-exploration. This thesis aims to address the aforementioned challenges and investigate the feasibility of floorplan-based navigation for service robots in unexplored environments. Specifically, we propose a novel scale-invariant floorplan localization method, enabling navigation without relying on precise scale information. Furthermore, we introduce an incremental graph augmentation approach that enriches the floorplan representation with traversability and semantic information derived from robot observations. Finally, we develop an efficient navigation framework capable of utilizing both the inherent structure of the floorplan and real-time observations. Experimental results demonstrate that our scale-invariant floorplan localization method outperforms baseline methods in most cases when floorplan scale information is unavailable, and our graph-based navigation system exhibits superior success and efficiency compared to grid-based counterparts. Furthermore, qualitative analyses confirm that our method accurately reflects the real-time environmental conditions across diverse settings. The outcomes of this research contribute to the advancement of service robot deployment in unexplored environments, particularly in scenarios where extensive exploration and map building may be impractical or technically challenging for end-users. |
URI: | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/90699 |
DOI: | 10.6342/NTU202303013 |
Fulltext Rights: | 同意授權(全球公開) |
Appears in Collections: | 電機工程學系 |
Files in This Item:
File | Size | Format | |
---|---|---|---|
ntu-111-2.pdf Until 2026-08-06 | 24.42 MB | Adobe PDF |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.