基於即時影像之多車整合策略控制

Multiple Mobile Vehicles Control Based On Real-time Image

彭俊維(Chun-Wei, Peng)

指導教授 ： 姚立德

國立臺北科技大學/機電學院/機電整合研究所/碩士(2008年)

https://doi.org/10.6841/NTUT.2008.00296

摘要

針對多車整合控制系統，本論文使用一追隨控制系統，只要知道前導車與跟隨車間的若干資訊，即可利用追隨控制數學模型來推算出相對應的控制量，藉此達到在兩車間維持一定的固定距離及固定角度，來完成多車整合控制的目的。在前導車資訊判別上，本文是利用 CMOS 影像感測模組配合自製的LED燈組，使用影像面積量測的方法，可推算出前導車與跟隨車間的相對距離及位置。此方法並不需要複雜的圖形辨識演算法，只利用一些公式就可以推算出相對距離、相對角度及相對車頭角，再利用本文提到的數學控制模型，讓跟隨車得以平滑地追隨移動中的前導車，並根據所設定的條件來完成多車隊形控制的期望，最後，並以實際實驗來證明本文內容之可行性

關鍵字

影像處理 ； 自動導航車

並列摘要

In respect of the multiple mobile vehicles control system, this thesis utilizes a
following control system which can help to maintain a certain distance and fixed angle
between two sequent cars, and therefore achieve the purpose of multi-vehicle
integrated control. As long as some pieces of information regarding the preceding car
and following car are obtained, this following control mathematical model can
calculate the relative control volume. For identifying the information of preceding car,
this thesis utilizes CMOS image sensor module, collocated with self-made LED lights,
to calculate the relative distance and position by image-based measuring. This method
only utilizes some formulas to calculate the relative distance, relative angle and
relative head angle instead of any sophisticated pattern recognition approach.
Furthermore, the mentioned mathematical control model can let the following car
smoothly pursue after the preceding car in moving, and achieve the expectation of
multi-vehicle formation control in accordance with the given conditions. Finally, the
feasibility of contents in this thesis will be proved through practical experiments.

並列關鍵字

Automatic Guided Vehicle

參考文獻

[73] 郭盼容，適用於網路型模糊控制系統之模糊增益調節器，碩士論文，台北科技大學機電整合研究所，台北市，2006年。

[2] P. Veelaert and W. Bogaerts, “Ultrasonic potential field sensor for obstacle avoidance,” IEEE Trans. on Robotics and Automation, vol. 15, no. 4, pp. 774-779, Aug. 1999.

[4] E. M. Petriu, “Automated guided vehicle with absolute encoded guide-path,” IEEE Trans. on Robotics and Automation, vol. 7, no. 4, pp. 562-565, Aug. 1991.

[5] L. X. Wang, and J. M. Mendel, “Generating fuzzy rules by learning from examples,” IEEE Trans. Syst., Man, Cybern., vol. 22, no. 6, pp. 263-268, Nov./Dec. 1992.

[6] D. Nguyen and B. Widrow, “The truck backer-upper: an example of self-learning in neural networks,” in Proc. Int. Joint Conf. on Neural Networks, Washington, DC, pp. 357-363, vol. 2, 1989.