本研究應用模糊理論結合決策樹演算法之控制法則，設計製作具備防撞及超車功能之自走車，以自走車上裝載超音波及紅外線感測器，分別偵測車體四周之環境及地面之導軌，模擬駕駛者在道路駕駛車輛的情境，並能達到超車或減速防撞的目的。本自走車系統主要包括四大模組:動力及驅動模組、環境感測模組、數據傳輸模組、微處理器控制模組，並另以PC透過數據傳輸監控、記錄，及操控自走車。控制法則之設計，乃根據操作自走車的實作經驗，調整環境訊號的權重，以決定要執行超車或減速的防撞指令。按照模糊決策樹的辨別，可區分為五個可能路況，分別是:路徑追蹤(case0)、減速防撞(case1)、左側超車(case2)、路徑追蹤及減速防撞(case3)、左側及右側超車(case4)。藉由實驗驗證顯示本研究所設計之模糊決策樹控制器，能有效使自走車達到超車與防撞的目的。

This research is to design a controller, combining the fuzzy theory and the algorithm of decision tree, and to build up a robot car, using ultrasonic and infrared sensors to detect the environment and follow the ground track, respectively, for the purpose of simulating road driving situation and achieving the objectives of car passing or collision avoidance. The robot car includes four major modules, the power and motor drive, the environment detection, the data communication, the micro-processor and data processing modules. Further, a remote PC with the controller is used to monitor, to record data from, and to generate control command to the robot car through communication module. The control law is designed by combining the fuzzy logic with the decision tree using the experimental data from running the robot car and the weighed signals from the environment sensors to formulate rules and threshold conditions for car passing or collision avoidance by slowing down. Five possible situations are identified on the fuzzy decision tree, which are road tracking (case0), slow down (case1), left passing (case2), road tracking and slow down (case3), left and right passing (case4). The results of ground experiments show that the fuzzy decision tree controller designed in this research can conceptually achieve the research objectives.

[1] Zadeh, L.A., “Information and Control,” Fuzzy Set, 8, 338-353(1965)

[2] Mon, D.L., Cheng C. H. and Lin J. C., “Evaluating Weapon System Using Fuzzy Analytic Hierarchy Process Based on Entropy Weight,” Fuzzy Sets and Systems, 62, 127-134(1994)

[3] Cheng, C.H., “A New Approach for Fuzzy Numbers by Distance Method,” Fuzzy Sets and Systems, 95, 307-317(1998).
[4] 鄭景俗1 廖述賢2 張自立2 “基於模糊層級分析觀念及距離法模糊數排序評估武器系統”國立雲林科技大學資訊管理系所2國防大學國防管理學院資源管理研究所, 2003
[5] Chen, H.-M. and S.-Y. Ho,”designing an Optimal Evolutionary Fuzzy Tree for Data Mining”, Proceeding of the 2001 Genetic and Evolutionary Computation Conference, In San Francisco, California, pp, 934-950, 2001
[6] 蕭方智,“應用階層式粒子群方法於模糊決策樹之研究”,元智大學工業與工程管理研究所，2004
[7] P. Rusu, E. M. Petriu, T. E. Whalen, and A. Cornell, and H. J.W. Spoelder,“Behavior-based neuro-fuzzy controller for mobile robot navigation,”, IEEE Transactions on Instrumentation and Measurement, vol. 52, Issue 4, Aug. 2003, pp.1335 – 1340

[8] Simon X. Yang, Hao Li and Max Meng. “Fuzzy control of a behavior-based mobile robot,” The 12th IEEE International Conference on Fuzzy Systems, vol. 1, 25-28 May 2003, pp.319 – 324

[9] X. Yang, M. Moallem, and R.V. Patel, “An improved fuzzy logic based navigation system for mobile robots,” Proceedings of the 2003 IEEE/RSJ Intl. Conference on Intelligent Robots and Systems, October 2003, pp.1709 - 1717
[10] Simon X Yang, Hao Li, and Peter X. Liu, “An embedded fuzzy controller for a behavior-based mobile robot with guaranteed performance,” IEEE Transactions on fuzzy systems, vol. 12, no.4, August 2004, pp. 436 – 446

[11] S. Khatoon, “Behavior coordination of autonomous mobile robot navigation by neuro-fuzzy system,” Proceedings of the IEEE 31st Annual Northeast Bioengineering Conference, April 2-3, 2005, pp.58 – 62

[12] N. Kubota, T. Morioka, F. Kojima, and T. Fukuda,” Perception-based genetic algorithm for a mobile robot with fuzzy controllers,” Evolutionary 68

[13] Computation, 1999. CEC 99. Proceedings of the 1999 Congress on vol 1,6-9 July 1999, pp.397-404 R. A. Brooks. “A robust layered control system for a mobile robot,” IEEE Journal of Robotics and Automation, vol.2, no.7, pp.14-23, 1986
[14] Kai-Tai Song and Liang-Hwang Sheen,“Fuzzy-nero control design for obstacle avoidance of a mobile robot”,IEEE Int. Conf.On Fuzzy System,Vol.12.NO.4 pp447-465,August 2004
[15] 許哲源，“自走車之驅動控制與避障規劃”，國立成功大學工程科學系碩士論文，2002
[16] 陳巧茵，“小型自走車以超音波避障之研究”，國立成功大學工程工程學系碩士論文，2002
[17] Iluminada Baturone, Francisco J. Moreno-Velo, Sandiago Sanchez-Solano, and Anibal Ollero,”Automatic Design of Fuzzy Controller for Car-Like Autonomous Robots”,IEEE Trans. On Fuzzy System, Vol. 12.No.4pp447-465, August 2004

[18] Tzuu Hseng S.Li, and Shih-Jie Chang, “Autonomous Fuzzy Parking Control of a Car-Like Mobile Robot”,IEEE Trans. On Fuzzy System, Vol.33, No.4,pp451-465, July 2003
[19] Akira Ohata, and Masahiro Mio,“Parking Control Base Nonlinear Trajectory Control For Low Speed Vehicles“,IECON Int. Conf.Vol1,pp107-112, October 1991
[20] 蘇裕記，“以FPGA晶片實現智慧型車庫停車控制系統”，國立成功大學電機工程系碩士論文，1999
[21] 簡卓建，“應用模糊控制於自走車路徑導引避障之整合設計”，國立成功大學航空太空工程研究所碩士論文，2003
[22] 王建清，“無線遙控智慧型自走車之設計製作應用於平形泊車實驗”，國立成功大學航空太空工程研究所碩士論文，2005
[23] G.G Rigatos, S.G. Tzafestas and G.J.Evangelidis, “Reactive Parking Control of Nonholonomolic Vehicles Via a Fuzzy Learning Automaton”, IEEE Proc.-Control Theory Apply, Vol.48, No.2, pp169-179, March 2001

[24] Ching-Wen Cheng, shih-Jie Chang, and Tzuu-Hseng S.Li,“Parallel-Parking Control of Autonomous Mobile Robot”,IECON Int.Conf, Vol 1.3, pp1305-1310,Nov. 1997
[25] Y.K.Lo,A.Brad,C.W.Wong and M.L.Ho“Automatic Parallel Parking,” Intelligent Trans. System, Vol.2 pp12-15, Oct. 2003
[26] 李宗勳，“應用FPGA晶片實現車型機器人之智慧路邊停車控制之研究”， 國立成功大學電機工程系碩士論文，1999
[27] 陳意翔，“具智慧型停車功能車型機器人之設計與實現” ， 國立成功大學電機工程系碩士論文，2001
[28] 張世傑，“用於車型機器人之模糊停車控制控制法的設計與實現”， 國立成功大學電機工程系碩士論文，2002
[29] Simon X. Yang, Ho Li,Max, Q.H. Meng, and Peter X.Liu “An Embedded Fuzzy Controller for a Behavior-Base Mobil Robot With Guaranteed Performance,” IEEE, Trans. On Fuzzy system, Vol.112, No.4,pp436-446, August 2004

[30] Tzuu –Hseng S.Li, Member, IEEE, Shieh-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
[31] 魏光群，“無線導引微晶片控制巡蹤自走車之研製”， 國立成功大學航空太空工程研究所碩士論文，2003
[32] 江正偉，“智慧型避障追蹤電動車控制系統之設計與研究”， 國立成功大學航空太空工程研究所碩士論文，2000