應用視覺辨識與模糊方法設計之車輛側向控制系統

本文旨在應用視覺辨識與模糊方法設計車輛的側向控制系統。車輛側向控制系統主要運用在車道維持上，將攝影機獲取的畫面經過邊緣檢測與座標轉換得到實際中的車道中心偏移量。當車輛偏離車道線時，側向控制器主動介入轉向的控制，確保車輛穩定的行駛於車道中心。首先是建立原型車的數學模式，原型車結合視訊開發平台、數位控制器和無線傳輸模組，控制其行進於模擬車道，收集系統的動態資料，進行側向系統模式鑑別，根據所得到的三種區域的動態模式，應用模糊推論整合成全域的數學模式。其次進行控制法則設計，控制系統是以線性矩陣不等性的方法求出穩態控制的解，使得在速度改變的情況下，原型車能完成自動導向的控制操作。相較於先前研究，本文是以影像處理的方法量測車輛偏移車道中心之位移與速度等動態資料，用之於模式鑑別，使得鑑別後的模式更通用於實際的控制情形，最後由實驗結果比較狀態回授控制與傳統PD控制。

關鍵字

側向控制；自行車模式；系統鑑別；視覺辨識；線性矩陣不等式

並列摘要

In this thesis, a vision-based fuzzy lateral control system is invesitagted. The objective of vehicle lateral control is to maintain vehicle traveling along the center of lane for the driving safety. When a vehicle deviates from the lane mark, the lateral controller automatically intervenes in the control of direction change, ensuring that the vehicle drives stably along the central of a lane. To this end, the lane images are captured by the camera installed on the vehicle. The actual deviation can be obtained by the image processing. The first step is to build the mathematical model of the experimental vehicle, which is composed of a visual development platform, digital controller and a wireless transmission module. In the experimental process, the prototype is controlled to move in simulated lanes while collecting the dynamic informations for system indentification. Integrated with the three local models, which are obtained by varying the speed of the vehicle, a set of fuzzy implications are implemented to represent the global system dynamics. Based on this model, the control system is analyzed and synthesized by means of linear matrix inequality. The obtained solution ensures the stable control and operation of automatic navigation under changing velocity. Compared with previous work, the proposed study used image processing to measure displacement and velocity involved in vehicle deviation, making the identified model more applicable to actual control situations. At last, the effectiveness of the proposed control scheme is validated by the expermental results and comparisons with the conventional PD control.

並列關鍵字

lateral control ； bicycle model ； system identification ； image processing ； Linear Matrix Inequalities

參考文獻

[22] 戴凱易，「以視覺辨識設計之車輛側向控制系統」，碩士論文，國立虎尾科技大學電機工程研究所，2014年7月。

[21] 洪昌嘉，「應用T-S模糊模式設計之車輛側向系統」，碩士論文，國立虎尾科技大學電機工程研究所，2012年7月。

[27] T.H. Chang, C.S. Hsu, C. Wang, and L.K. Yang , “Onboard Measurement and Warning Module for Irregular Vehicle Behavior,” IEEE Transactions on Intelligent Transportation Systems, vol. 9, no. 3, September 2008.

[2] R.E. Benton and D. Smith, “A static-output-feedback design procedure for robust emergency lateral control of a highway vehicle,” IEEE Transactions on Control Systems Technology, vol. 13, no. 4, pp. 618-623, 2005.

[3] S.B. Choi, “The design of a look-down feedback adaptive controller for the lateral control of front-wheel-steering autonomous highway vehicles,” IEEE Transactions on Vehicular Technology, vol. 49, no.6, pp. 2257-2269, 2000.

國際替代計量

應用視覺辨識與模糊方法設計之車輛側向控制系統

未授權

主題瀏覽