教師著作
Permanent URI for this collectionhttp://rportal.lib.ntnu.edu.tw/handle/20.500.12235/31268
Browse
7 results
Search Results
Item 應用於室內自然環境且可與人自然溝通之居家服務機器人--子計畫三:居家服務機器人之即時動態導航與定位學習之設計與實現(行政院國家科學委員會, 2010-07-31) 許陳鑑; 盧明智本計畫之主要目的在於研究居家服務機器人即時動態導航與定位之設計與實現,包 含:環境感知、導航(robot navigation)、以及迴避障礙等功能,使居家服務機器人能具有 自主認知與熟習環境的能力,以協助各個子計畫達成希望執行的任務。配合總計畫第 一、二年預定完成Robotcup@home 基礎及進階指定競賽項目的目標,本計畫將以:(1) 多感測器之障礙物偵測系統、(2)感測器資料融合、(3)虛擬環境地圖建立與定位、(4)自 主避障、(5)動態路徑規劃、以及(6)障礙空間資訊描述等六項研究重點,完成:(1)建立 一多重感知障礙物偵測系統,整合各種異質感測器之量測資訊,提供可靠之環境障礙物 資訊,(2)利用多種數據融合(sensor fusion)技術實現感測器資料融合,以提供可靠的量測 結果,作為建立地圖與避障之依據,(3)利用多種建地圖(map building)技術,建立並更新 未知環境之虛擬空間地圖,作為機器人自主導航的依據,(4)以多種啟引式演算法 (heuristic)以及演化計算法(evolutionary computation)實現最佳路徑之規劃,使機器人能據 以行動,快速且安全到達目的地,(5)依多重感測數據融合資料以及目標物移動方向之估 測,實現自主避障之功能,使機器人能安全行進,(6)利用多重感測數據融合資料作訊號 處理與座標轉換,實現障礙空間圖形化描述(obstacle profiling),精確呈現障礙物空間資 訊。並與其他子計畫整合,使居家機器人能夠實現Robotcup@home 所指定之基礎及進 階競賽項目。第三年則針對適合台灣居家環境之機器人的相關項目進行研發,包含:(1) 提供居家空間多重輔助定位,包含超音波、RFID、以及影像式輔助定位,以校準機器人 位置,提供機器人精確定位,(2)建置即時遠端監控與整合式互動介面,方便使用者透過 遠端連線的方式進行監控,增加居家服務機器人的實用與便利性,(3)以嵌入式統軟硬體 協同設計(Hardware/Software Co-design)觀念,實現各種所提出之演算法,改善機器人定 位、路徑規劃、避障之執行效能,全面提升機器人之導航及避障性能。Item 以SOPC為基礎利用單一攝影機傾斜攝影之移動式機器人物體追蹤與定位系統(行政院國家科學委員會, 2011-07-31) 許陳鑑本計畫擬建置一台以可程式規劃系統晶片(System On Program Chip, SOPC)為基礎,具備 影像物體追蹤(object tracking)、影像式定位(image-based localization)、以及避障功能 (obstacle avoidance)之全方位移動式機器人。作法上係以單一CCD 作傾斜式之攝影(tilt photographing),據以發展出多種以傾斜式攝影為基礎之影像式距離及角度量測系統,藉 由與物體追蹤技術相結合,達到對於目標物之定位(localization),並將相關演算法實現 在可程式規劃系統晶片(System On Program Chip, SOPC)上,達到以SOC 晶片系統即時 處理及控制移動式機器人的目的。三年期之計畫共包含5 個研究子題,分別是:(1)全方 位機器人系統架構與建置,(2) 混合型物體影像追蹤系統,(3)影像式物體定位系統,(4) 模糊避障系統,以及(5) SOPC 系統之實現。 機器人系統架構上,本計畫擬設計一台具有全方位移動能力之機器人,視覺系統則 僅配置單一CCD 作傾斜式攝影,作為影像式距離量測、影像物體追蹤、以及影像式物 體定位等相關系統之基礎;機器人的週邊則配置有超音波感測器、紅外線感測器,利用 多重感測器資料融合技術,建立機器人之模糊避障(fuzzy obstacle avidance)功能。在影像 物體追蹤方面,本計畫擬以粒子濾波器演算法(particle filter, PF)、粒子群最佳化法(particle swarm optimization, PSO),以及單體搜尋法(Nelder-Mead Simplex Search Method, NM)為 基礎,擷取其長處予以整合,開發兩種混合型(Hybrid)目標物體追蹤法,配合特徵為基 礎之物體辨識技術(feature-based methods for object recognition),快速偵測目標物體,再 輔以所開發出來之多種影像式物體定位系統,以獲取所偵測到的目標物體相對於量測系 統的座標位置。在機器人避障系統方面,本計畫擬設計一模糊系統,將多種感測器資訊 融合成障礙物的距離與方向資訊,並透過模糊避障機制來決定機器人的移動方向與旋轉 角度,最後再以SOPC 實現各種相關演算法,利用FPGA 的硬體電路優勢,以軟硬體協 同設計(Hardware/Software Co-design)的技術設計各種硬體加速器電路,提升相關演算法 的執行效率,實現以SOC 晶片系統即時處理及控制移動式機器人的目的。Item 應用於室內自然環境且可與人自然溝通之居家服務機器人--子計畫三:居家服務機器人之即時動態導航與定位學習之設計與實現(II)(行政院國家科學委員會, 2012-07-31) 許陳鑑; 簡忠漢本計畫之主要目的在於研究居家服務機器人即時動態導航與定位之設計與實現,包 含:環境感知、導航(robot navigation)、以及迴避障礙等功能,使居家服務機器人能具有 自主認知與熟習環境的能力,以協助各個子計畫達成希望執行的任務。配合總計畫第 一、二年預定完成RoboCup@home 基礎及進階指定競賽項目的目標,本計畫將以:(1) 多感測器之障礙物偵測系統、(2)感測器資料融合、(3)虛擬環境地圖建立與定位、(4)自 主避障、以及(5)動態路徑規劃等項目為研究重點,完成:(1)建立一多重感知障礙物偵 測系統,整合各種異質感測器之量測資訊,提供可靠之環境障礙物資訊,(2)利用多種數 據融合(sensor fusion)技術實現感測器資料融合,以提供可靠的量測結果,作為建圖、定 位與避障之依據,(3)利用多種地圖建置(map building)與自我定位技術,建立並更新未知 環境之虛擬地圖以及準確估測機器人的姿態,作為機器人自主導航的依據,(4)以多種啟 引式演算法(heuristic)以及演化計算法(evolutionary computation)實現最佳路徑之規劃,使 機器人能據以行動,快速且安全到達目的地,(5)依據多重感知障礙物偵測的結果以及目 標物移動方向之估測,實現自主避障之功能,使機器人能安全行進。並與其他子計畫整 合,使居家機器人能夠完成RoboCup@home 所指定之基礎及進階競賽項目。第三年的 目標主要是要延伸居家服務機器人的功能,針對適合台灣居家環境之機器人的相關項目 進行研發,包含:(1)利用影像式定位法配合目標物特徵辨識技術對障礙物進行偵測,以 確定目標物之空間座標位置,(2)提供居家空間多重輔助定位,包含超音波、RFID、以 及影像式輔助定位,以校準機器人位置,提供機器人精確定位,(3)利用多重感測數據融 合資料實現3D 地圖建立與圖形化介面設計,精確呈現障礙物空間資訊,(4)以嵌入式系 統軟硬體協同設計(Hardware/Software Co-design)觀念實現各種演算法,期使運算速度能 夠大幅提升,達到即時處理之需求,全面提升機器人之導航及避障性能。Item Improved Ultrasonic-Based Localization Using Reflection Method(2009-02-02) Chen-Chien Hsu; Hsin-Chuan Chen; Chien-Yu LaiIn this paper, an ultrasonic-based localization using ultrasonic reflection method is proposed. Experiment environment includes a mobile robot and four poles forming a square around the measuring site. Ultrasonic sensors built on the poles serve as receivers and the mobile robot serves as a transmitter, and all ultrasonic sensors are integrated with their Zig-Bee modules. By the sequential ultrasonic signal transmission between the robot and the poles, the ultrasonic sensors on the poles can then measure the time-of-flight (TOF) without interference to calculate the distance between the receiver and transmitter ends. According to an established two-dimensional coordinate model, position of the robot can be obtained based on the distance measurements. Thanks to Zig-Bee modules, position information of the robot can be instantly conveyed to a remote PC for monitoring the robot and path planning. Extensive experiments conducted have shown a satisfactory accuracy of the coordinates of the mobile robot can be obtained via the proposed localization scheme.Item 2-Dimenional Localization Based on Tilt Photographing of a Single CCD Camera(2009-02-12) Ming-Yu Cheng; Chen-Chien Hsu; Pei-Jun LeeThis paper provides an image-based localization method based on tilt photographing of a single CCD camera. Image captured by the CCD camera is pre-processing to locate the target object in the picture in terms of pixel count deviation from the CCD camera. By using an established formula based on relationship between tilt angle of the CCD camera and distance, coordinate of the target object can be calculated. Experiment results have demonstrated that the feasibility of the proposed approach with satisfactory accuracy in determining the position of the target object.Item Distance and Angle Measurement of Distant Objects on an Oblique Plane Based on Pixel Number Variation of CCD Images(Institute of Electrical and Electronics Engineers (IEEE), 2011-05-01) Chen-Chien Hsu; Ming-Chih Lu; Yin-Yu LuThis paper presents an image-based system for measuring target objects on an oblique plane based on pixel number variation of charge-coupled device images for digital cameras by referencing to two arbitrarily designated points in the image frame. Based on an established relationship between the displacement of the camera movement along the photographing direction and the variation in pixel counts between the reference points in the images, photographic distance and incline angle for objects lying on an oblique plane can be calculated via the proposed method. As a real-case application of the proposed approach, 2-D localization of target objects in robot soccer competitions is also demonstrated to show the effectiveness of the proposed approach. To allow the use of widely available digital zoom cameras for ranging and localization by the proposed method, a parameter equivalent to the displacement due to the camera movement is also investigated and derived in this paper.Item Image-Based System for Measuring Objects on an Oblique Plane and It Applications in Two-Dimensional Localization(IEEE Sensors Council, 2012-06-01) Ming-Chih Lu; Chen-Chien Hsu; Yin-Yu LuThis paper presents an image-based framework for measuring target objects on an oblique plane by using a single charge-coupled device camera and two laser projectors mounted in parallel beside the camera. Because of the alignment of the laser beams, which form in parallel with the optical axis of the camera, laser-projected spots in the image can be processed to establish relationships between distance and pixel counts of the projected spots in the image. Based on simple geometrical derivations without complex image processing, the proposed approach can successfully measure the photographic distance, the distance between two arbitrary points on the oblique surface, and the incline angle of the oblique surface. Thanks to its ranging capability, the proposed image-based measuring system is further applied to localize objects on a ground surface in addition to depth measurement. To demonstrate the feasibility of the proposed approach for practical applications, we propose a surveillance framework under which a pan-tilt-zoom camera tracks objects in an environment according to the 2-D localization results obtained via the proposed method. Experimental results have demonstrated the effectiveness of the proposed approach in distance measurement, as well as localization of objects on an oblique plane.