標題: 基於深度影像資訊之救災探勘機器人協同系統的設計與研發(II)
A Study of 3D Depth-Image Based Rescue and Exploration Multi-Robot System(II)
作者: 林昇甫
LIN SHENG-FUU
國立交通大學電機與控制工程學系(所)
關鍵字: 3D場景重建;救災搜索機器人;機器人定位;路徑規劃;3D reconstruction;rescuers-searching robot;localization of robot;path planning of robot
公開日期: 2009
摘要: 本計畫提出了一個具有深度資訊影像之救災探勘機器人計畫,提供在倒塌的建築物中搜尋受困者的功能並且協助搜救人員進入救援受難者的功能。本計畫主要包含3D場景重建、機器人定位、機器人可行路徑判斷以及路徑規劃。透過3D場景重建可以知道倒塌的建築物內部的情況藉以幫助救難人員了解倒塌的建築物內部情況,而機器人定位則是幫助理解機器人行進的方向、角度以協助建立路徑,機器人可行路徑判斷有助於機器人朝正確的方向前進,最後再透過路徑規劃規劃出適合搜救人員進入的最短路徑。如果多隻機器人可進行探勘,則可藉著彼此之間的資訊傳輸與協同合作,避免相同區域重複探勘,進而增加探勘搜索效率。 本計畫的第一年進度至今已完成系統部份架構,制定系統規格。在3D場景重建部份,已經完成了結合兩張簡單場景的影像註冊。在機器人定位部份,已分別將軸編碼器以及姿態感測器與機器人平台做結合。在機器人可行路徑判斷部份,已完成距離資料分析。在路徑規劃部分,已完成TSK形式模糊類神經網路的架構。第二年(明年)裡,3D場景重建部份,預計以三維雷射掃描取得的三維座標資料,進行表面重建的工作。在機器人定位部份,預計完成救援機器人的絕對定位系統,最後採用資料融合的技術將相對定位系統與絕對定位系統整合,來做最後的定位估計。在可行進路徑判斷系統中,目標除了障礙物的防碰撞機制外,最主要是將路徑圖表示出來。在路徑規劃部份,預計將路徑紀錄的結果建立成路徑樹。接下來完成查詢路徑環境並測試之。
This proposal proposes a study of 3D depth-image based rescue and exploration multi-robot system. It provides function of searching the trapped people and helping rescuers enter to relive the victims. This project mainly includes 3D reconstruction、localization of robot、motion planning of robot and path planning. By 3D reconstruction, rescuers can be informed of the inner condition of collapsed building; however, localization helps us record moving direction and angle of robots and build the paths. Motion planning helps robots moving toward the right direction and finally mapping out the shortest path suitable for rescuers to enter through path planning. If many robots are used, re-exploration for same section can be avoided by information transmission and cooperation among robots, and the performance can be improved effectively. So far, the progress at the first year of this project contains building partial structure of the system and defining the system’s specification. In 3D reconstruction part, the registration of two images of simple environment is accomplished. In localization of robot part, the integration of encoder and inertial measurement unit between the robot are done respectively. In motion planning of robot part, the analysis of the range data is completed. In path planning part, the structure of TSK-typed neuro-fuzzy system is established. Next year, in 3D reconstruction part, our object is to complete the surface reconstruction based on the 3D coordinate data gained from the range finder. In localization of robot part, our task is to finish the passive localization system and integrate it with the relative localization system to fulfill the localization estimation. In motion planning of robot part, besides the anti-collision function, our goal is to diagram the path map. In the path planning part, we will use the record of all paths to establish the path tree, and build up the path-inquiring environment and testify it.
官方說明文件#: NSC98-2221-E009-127
URI: http://hdl.handle.net/11536/101727
https://www.grb.gov.tw/search/planDetail?id=1908507&docId=316434
顯示於類別:研究計畫


文件中的檔案:

  1. 982221E009127.PDF

若為 zip 檔案,請下載檔案解壓縮後,用瀏覽器開啟資料夾中的 index.html 瀏覽全文。