救護機器人基於擴展卡爾曼濾波的室內定位

時間是一個關鍵問題，當與人誰遇到突然心臟驟停，不幸的是他們大多由於治療在幾分鐘內死亡是無法訪問處理。因此，使用自動體外除顫器（AED）的立即治療必須給予受害人崩潰後的幾分鐘內。儘管AED的非常有用的功能，即使該設備被放置在各種公共場所的今天，AED的實際操作仍需要改善，促使我們開發出機器人來執行這樣重要的任務。真實案例情景表明，它常常是困難的，當恐慌出現狀況，找出附近的AED，把它給受害者和應用它。還需要幾個人都提前熟習AED。為了解決這樣的問題，我們設計並開發了救護機器人，簡稱Ambubot，這使沿AED在心臟驟停突然事件，並有利於各種操作模式從手動到自主運作，以挽救別人的生命。雖然機器人依靠GPS傳感器用於室外定位進行令人滿意的，主要的挑戰之一就是定位機器人在室內環境，如商場和地下交通樞紐。為了幫助Ambubot實現其預定的目標，我們採用的擴展卡爾曼濾波 (Extended Kalman Filter) 用於室內本土化。這種機制使得機器人能夠確定並估計其在任何時候都在未知環境中的位置。我們已經利用Ambubot，其中包括9自由度慣性測量單元（IMU），以支持擴展卡爾曼濾波的性能。我們的實驗成功結果在我們的實現這樣的目的。Ambubot介紹和解釋，各種性能的策略進行了描述和擴展卡爾曼濾波器估計Ambubot的位置的性能，本文明確說明。

關鍵字

定位；本土化；擴展卡爾曼濾波；自主機器人；救護機器人

並列摘要

Time is a critical issue when dealing with people who experience a sudden cardiac arrest and unfortunately most of them die because the treatment within minutes is not accessible. Therefore, an immediate treatment using Automated External Defibrillator (AED) must be administered to the victim within a few minutes after collapsing. Despite the very useful functionality of AED and even though this device is placed in various public areas nowadays, practical operation of AED still requires improvement which mo-tivated us to develop a robot to perform such critical task. Real case scenarios show that it is often difficult to find out the nearby AED when a panic situation occurs. Several people are also required to get familiar with AED in advance. In order to solve such prob-lems, we have designed and developed the Ambulance Robot, shortened as Ambubot, which brings along an AED in a sudden event of cardiac arrest and facilitates various modes of operation from manual to autonomous functioning to save someone’s lives. Whilst the robot performs satisfactory for outdoor localization by relying on the GPS sensor, one of the main challenges was positioning the robot in the indoor environ-ments such as shopping malls and underground transit hubs. To help Ambubot to achieve its prescribed goals, we employed the Extended Kalman Filter for indoor localization. This mechanism enables the robot to determine and estimate its position at all times in unknown environment. We have utilized the Inertial Measurement Unit (IMU) of Ambu-bot, which consists of 9 Degree of Freedom, to bolster performance of Extended Kalman Filter. Our experiments demonstrated successful results for such purpose in our imple-mentation. Ambubot is introduced and explained, various performance strategies are de-scribed and the performance of Extended Kalman Filter estimating the position of Ambu-bot is explicitly described in this dissertation.

並列關鍵字

autonomous robot ； positioning ； localization ； extended Kalman filter ； ambulance robot

參考文獻

[2] Desouza, G.N., Kak, A.C., “Vision for mobile robot navigation: A survey,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol.24, no.2, pp.237-267, Feb. 2002.

[3] Nicosevici, T., Garcia, R., “Automatic visual bag-of-words for online robot naviga-tion and mapping,” Robotics, IEEE Transactions on, vol.28, no.4, pp.886-898, Aug. 2012.

[4] Capisani, L.M., Ferrara, A., “Trajectory planning and second-order sliding mode motion/interaction control for robot manipulators in unknown environments,” In-dustrial Electronics, IEEE Transactions on, vol.59, no.8, pp.3189-3198, Aug. 2012.

[5] Smith, C., Christensen, H., “Robot manipulators,” Robotics and Automation Mag-azine, IEEE, vol.16, no.4, pp.75-83, Dec. 2009.

[6] Chingtham, T.S., Sahoo, G., Ghose, M.K., “An unmanned aerial vehicle as human-assistant robotics system,” Computational Intelligence and Computing Research (ICCIC), 2010 IEEE International Conference on, vol., no., pp.1-6, 28-29 Dec. 2010.

國際替代計量

救護機器人基於擴展卡爾曼濾波的室內定位

未授權

主題瀏覽