由於台灣颱風及地震等天災頻繁, 意外發生時台灣專業救援人員往往不足而導致無法快速因應. 搜救行動可能會因為災區的對外交通及通訊受阻而產生救援的困難以及地面搜索的效率不足導致延誤時機. WISH計劃提供了一個使用自動駕駛小型遙控直昇機的解決方案可以在人員進入之前先以UAV(Unmanned Aerial Vehicle)進入災區搜集影像等各種資料並以3G無線網路技術以最快的速度傳回地面端做因應, 也能以UAV的高機動性幫助搜索受難生還者.
WISH 直昇機計畫包含兩個部分 : 迅速的超距離無線通訊連線的建立與高解析度圖像即時拍攝。為了達成此目標我們結合了無線隨意網路、第三代行動通訊系統與數位單眼相機在此系統上。同時建置一嵌入式中控系統在直升機上，負責收集各感測器所回傳之數值、控制相機拍照，並將相片與數據傳回地面管制中心。
本論文為WISH 計畫實作的一部分, 負責所有在直昇機上的軟體及軔體, 功能包括
􀂾
驅動所有感測器及擷取數據
􀂾
直昇機自動控制
􀂾
空中攝影
􀂾
以3G傳輸照片及資料至地面
系統整合
最後我們做了一些飛行測試來證明系統可行性,測試結果顯示系統是可行的, 雖然有些地方仍要繼續努力才能使系統更加完善, 不過方向及架構是正確的.

As the frequently natural disasters in Taiwan such as earthquakes and typhoons, the professional rescue personnel are often insufficient and lead to the failure of rapid response. Search and rescue operation may be delayed because the transport and communications of the disaster area have hampered and the ground search is too inefficient. Wireless Image Surveillance Helicopter (WISH) project provided a unmanned aerial vehicle (UAV) solution to use UAV to collect the information of the disaster area such as photographs prior to the staff entering and help the search for survivors with high mobility.
WISH helicopter project consists of two parts : the long range and high speed wireless communication, the real-time high resolution photographs. In order to achieve this goal, we have combined with third generation communication, ad hoc network and Digital single-lens reflex camera in this system. The embedded system have also been built to be a central control system of WISH helicopter. The system is responsible for controlling the helicopter, collecting sensor, controlling the camera to take photographs and then data or photos will be transmitted back to the ground control center.
This thesis is a part of implementation for WISH helicopter and provides the function in the following :
􀂾
Driving all sensors and gathering their data
􀂾
Autonomous control
􀂾
Capturing in the air
􀂾
Communication via 3G wireless communication
􀂾
Components integration
Finally, we made some flight tests to prove the feasibility of the system, and test results showed that the system is feasible. Although some aspects of work should be continued in order to make the system more perfect, but the direction and structure was correct.

[1] “The Predator”, http://www.ga-asi.com/products/predator.php
[2]”The Sikorsky’s Dragon Warrior”, http://www.globalsecurity.org/intell/systems/uav.htm
[3]”CMU Autonomous Helicopter Project”, http://www.cs.cmu.edu/afs/cs/project/chopper/www/
[4]”USC AVATAR project”, http://www-robotics.usc.edu/~avatar/
[5]”WITAS Project”, http://www.ida.liu.se/~patdo/auttek/introduction/index.html
[6]”COMETS Project”, http://www.comets-uavs.org/
[7]”ALIGN Corp.” http://www.align.com.tw/html/en/e_company.htm
[8] Lewis, M.A., Fagg, A.H., Bekey, G.A., “The USC autonomous flying vehicle: an experiment in real-time behavior-based control”, In Proceedings of IEEE International Conference on Robotics and Automation, 1993.
[9] Kim, H. J., & Shim, D. H., A flight control system for aerial robots: Algorithms and experiments. Control Engineering Practice 2003.
[11] La Civita, M., Papageorgiou, G., Messner, W. C., & Kanade, T. , “Design and flight testing of a gain-scheduled H-infinity loop shaping controller for wide-envelope flight of a robotic helicopter”, In Proceedings of the 2003 American Control Conference.
[12] Montgomery, J. F., & Bekey, G. A., “Learning helicopter control through ‘‘teaching by showing’’”, In Proceedings of the IEEE Conference on Decision and Control, 1998.
[13] Buskey, G., Wyeth, G., & Roberts, J., “Autonomous helicopter hover using an artificial neural network”, In Proceedings of the IEEE International Conference on Robotics & Automation, 2001.
[14] “Gphoto2”, http://www.gphoto.org/