透過您的圖書館登入
IP:3.14.141.228
  • 學位論文

多台自動引導車目標跟隨及避障功能之設計與實現

Design and Implementation of Human Following and Obstacle Avoidance on Multiple Automatic Guided Vehicles

指導教授 : 林沛群

摘要


自動引導車(Automated Guided Vehicle, AGV)是現時常見於倉庫內協助搬運貨物的工具。它們收到程式指示後,會跟隨地上的磁性或光學導引帶行駛至指定的地方取貨/卸貨。不同於傳統軌道,導引帶容易安裝及拆卸,對工作環境影響甚少。因此,自動引導車也適合與工人在同一個工作環境下工作。 然而,自動引導車的活動範圍最終還是受導引帶所限。本研究著重於在自動引導車上增設一個跟隨特定目標的模組,讓自動引導車除了跟隨導引帶外,也具備跟隨工人的能力。本研究開發的新一代跟隨模組沿用低成本的紅外線收發射器作為跟隨人的基礎。經過重新設計後的跟隨裝置,在偵測特定目標的位置表現變得更穩定及準確。除了跟隨特定目標外,模組也具備避障功能。本研究重新設計了避障系統的感測器運用及演算法,讓模組可以在更多複雜的環境亦能同時進行避障及跟隨的任務。最後,本研究設計了自訂的紅外線信號傳輸協定,讓多個跟隨模組能夠被應用在多台自動引導車,並將紅外線信號的干擾減至最低。因此,多台自動引導車能夠跟隨著個別的特定目標。唯有達至這點,跟隨模組方可真正能被應用到真實工作環境內。而本研究亦可被視為將跟隨模組商業化至自動引導車上的基礎。

並列摘要


Automatic Guided Vehicles (AGVs) are apparatus capable of transporting goods to designated positions. The most commonly used AGVs follow guide tapes, which are either magnetic or colored as if invisible rails to wherever they are instructed. Unlike rails, they do the least disturbance to the working environment and are easy to install or remove, and that is why it is not surprising to see AGVs sharing the same working environment with humans. Yet, AGVs are always restrained by guide tapes. This thesis aims to study the feasibility of enabling AGVs to follow humans instead of guide tapes. The human following module (the module) developed previously from our team can be deployed on a two-wheeled vehicle and have it followed the specific target and avoided obstacles at the same time. The fundamental idea of the former design utilizing low-cost infrared sensors as main components to achieve human following is further developed in this thesis. By redesigning the human tracking device, a part of the module, the performance of human bearing tracking is enhanced with higher stability and accuracy. The sensor system and algorithm for obstacle avoidance are modified to be more adaptive to various complex environments. The customized infrared transmitters utilized for building a bonded relationship with the infrared receivers on the AGVs allow multiple modules/AGVs working in the same environment cohesively. Achieving stable performances on human following and obstacles avoidance with low-cost sensors on multiple AGVs could be regarded as a solid foundation for the commercialization of human following AGVs.

參考文獻


[42] 蔡佳宏, "距離感測器於輪型機器人之應用," 碩士論文, 機械工程學系, 國立臺灣大學, 台北, 2011.
[40] 溫詠仁, "輪型機器人智慧化跟隨與召喚之設計與實現," 碩士論文, 機械工程學系, 國立臺灣大學, 台北, 2011.
[11] C.-H. Chao, B.-Y. Hsueh, M.-Y. Hsiao, S.-H. Tsai, and T.-H. S. Li, "Fuzzy target tracking and obstacle avoidance of mobile robots with a stereo vision system," International Journal of Fuzzy Systems, vol. 11, no. 3, pp. 183-191, 2009.
[6] C. Ackerman and L. Itti, "Robot steering with spectral image information," IEEE Transactions on Robotics, vol. 21, no. 2, pp. 247-251, 2005.
[7] T. B. Moeslund, A. Hilton, and V. Kruger, "A survey of advances in vision-based human motion capture and analysis," Computer Vision and Image Understanding, vol. 104, no. 2-3, pp. 90-126, Nov-Dec 2006.

延伸閱讀