以機器視覺為基礎之智慧型自動停車系統研究

Research in Vision-based Intelligent Automatic Parking System

蘇育平(Yu-Ping Su)

指導教授 ： 孫崇訓

淡江大學/工學院/機械與機電工程學系碩士班/碩士(2010年)

https://doi.org/10.6846/TKU.2009.00685

摘要

近年來，智慧型車輛控制的功能研發逐漸受到重視，其中智慧型自動停車的功能就是一個重要的研發方向之ㄧ。本研究將對自走車設計一個智慧性自動路邊停車系統。藉由自走車上之無線攝影機進行影像擷取。影像資訊的偵測是以影像處理演算法(Image Processing Algorithm)計算而得，其中車身角度是以最小平方法(Least Square Method)進行計算。獲得的資訊將在模糊控制器(Fuzzy Controller)中使用。自走車在前進控制過程中，將使自走車與車道線保持平行前進。如此自走車就能夠偵測停車格的前後方邊線作為偵測停車格的依據。在偵測到停車格後，將會執行自動停車程序。模糊控制器中我們考慮了三個輸入變數，導致模糊規則的數量龐大。因此，利用了階層式模糊控制器(Hierarchical Fuzzy Controller)來達到降低模糊規則數及運算量的目的。實驗結果顯示，我們所設計的自動停車系統在環境簡單的情況下，是能夠完成路邊停車的任務，也證明了其可行性與穩定性。

關鍵字

影像處理 ； 最小平方法 ； 模糊控制器 ； 階層式模糊控制器

並列摘要

Recently, The function of intelligent vehicle control is researched and pay attention to. The automatic parallel parking is one of important function. In this thesis, we design an intelligent automatic parallel parking system for mobile robot. Image capture is by wireless camera on the robot. The image Information detection between mobile robot and lane line is calculated by image processing algorithm. Moreover, the angle between robot and horizontal is calculated by least square method. The Information will be used in fuzzy controller. In the course of move forward control, the robot will keep parallel with lane line. Then, the mobile robot can detect the front and rear sidelines of the parking space. After parking space detecting, the mobile robot will execute the automatic parking process. In fuzzy control system, we consider three input variables, and it leads to large fuzzy rules. Thus, we utilize hierarchical fuzzy controller to reduce number of the fuzzy rules and computing requirement. Experimental results show the effectiveness of the proposed automatic parking system, when the environmental complexity is low.

並列關鍵字

Image Processing ； Least Square Method ； Fuzzy Controller ； Hierarchical Fuzzy Controller

參考文獻

[1]李匯宗 (許健平 教授指導)，設計與實作一輛具無線傳輸能力之多功能自走車，國立中央大學資訊工程系碩士論文，2008。

[2] Tzuu-Hseng S. Li, Shih-Jie Chang, and Wei Tong, “Fuzzy Target Tracking Control of Autonomous Mobile Robots by Using Infrared Sensors,” IEEE Trans. on fuzzy system, vol. 12, no. 4, August 2004.

[3]Tzuu-Hseng S. Li, Shih-Jie Chang, and Yi-Xiang Chen, “Implementation of Human-Like Driving Skills by Autonomous Fuzzy Behavior Control on an FPGA-Based Car-Like Mobile Robot,” IEEE Trans. on industrial electronics, Vol. 50, No. 5, pp. 867-880, October 2003.

[4]Mohamed Slim Masmoudi, Willie Tsui, Insop Song, Fakhreddine Karray, Mohamed Masmoudi, and Nabil Derbel, “Implementation of a Real-Time FPGA-Based Intelligent Parallel Parking System,” Journal of Advanced Computational Intelligence and Intelligent Informatics, vol. 12, no. 4, pp. 348-354, June 2007.

[5]Yanan Zhao and Emmanuel G. Collins Jr, “Robust automatic parallel parking in tight spaces via fuzzy logic,” Robotics and Autonomous Systems, No. 51, pp. 111-127, January 2005.