本篇論文中，我們利用基因演算法與模糊推論控制來實作一個LEGO Mindstorms NXT兩輪自體平衡機器人。為了使狀態響應達到控制目標，基因演算法被應用在尋找合適的狀態回授增益組合。基於LEGO Mindstorms NXT所提供的動態模型，性能評估的指標可以被定為上升時間(Rise Time, RS)、最大超越量(Overshoot, OS)及總誤差量(Integral of Absolute Error, IAE)，因此，基因演算法的適應性函數則會利用這三項性能評估的指標來尋求較佳的響應係數。最後，我們將模糊理論與各個狀態的理論推導結合。為了展現出研究成果，本論文所提出的方法將與現行方法進行比較。

In this thesis, we focus on a fuzzy knowledge-based reasoning control with genetic algorithm (GA) for a LEGO two-wheeled self-balancing robot. To achieve the control objectives with the satisfied states’ responses, a GA is involved to search feasible solution sets of the state feedback gain. Based on the dynamic model provided by LEGO Mindstorms NXT, performance indices of systems’ states can be characterized as rise time (RS), overshoot (OS), and integral of absolute error (IAE). Thus, a GA with a fitness function embracing the three performance indices is thus proposed for searching a set of well response parameters. Furthermore, we employ fuzzy inference reasoning to blend multiple states’ conditions. For demonstration, the proposed approach was compared with some existing works.

目次
第一章 緒論 1
第一節 研究背景 1
第二節 研究目的 2
第三節 論文架構 3
第二章 文獻探討 4
第一節 兩輪自體平衡機器人 4
第二節 模糊理論應用於兩輪平衡機器人探討 7
第三節 基因演算法與系統狀態之參數調整 9
第三章 研究方法 10
第一節 兩輪機器人系統架構 11
一、 系統平衡點模型 13
二、 系統各個角度的模型 15
三、 模糊系統應用 16
第二節 控制器設計 19
一、 狀態回授控制 19
二、 模糊狀態回授控制 20
三、 利用基因演算法選擇回授增益與架構模型 21
第四章 模擬與實驗結果 27
第一節 基因演算法效能差異 28
第二節 各狀態的回授增益值 29
第三節 模糊系統應用與實驗結果 32
一、 13條規則 33
二、 7條規則 34
三、 5條規則 36
四、 3條規則 37
五、 實機測試實驗 39
第五章 結論與建議 42
第一節 結論 42
第二節 建議 42
參考文獻 43
附錄.. 45

Segway. (2015). (http://www.segway.com/)
Intelligent Control Techniques in Mechatronics – Genetic Algorithm (http://www.ro.feri.uni-mb.si/predmeti/int_reg/Predavanja/Eng/3.Genetic%20algorithm/_05.html)
Salerno, A. &; Angeles, J. (2007). A New Family of Two-Wheeled Mobile Robots: Modeling and Controllability, IEEE Trans. Robotics, vol.23, no.1, pp. 169-173
Huang, C.H., Wang, W.J, &; Chiu, C.H. (2011). Design and implementation of fuzzy control on a two-wheel inverted pendulum, IEEE Trans. Ind. Electron., vol. 58, no.7, pp. 2988-3001
Grasser, F., D’Arrigo, A., Colombi, S., &; Rufer, A. C. (2002). JOE: A mobile, inverted pendulum, IEEE Trans. Ind. Electron., vol. 49, no.1, pp. 107-114
Chen, J.Y., Liu, C.H., Chen, C.C., &; Lin, K.C. (2011). Adaptive Fuzzy Control of Two-Wheeled Balancing Vehicle, Paper Presented at Conference of Instrumentation, Computer, Communication and Control, pp. 341-344
Xu, J.X., Guo, Z.Q., &; Lee, T.H. (2013). Design and Implementation of a Takagi-Sugeno-Type Fuzzy Logic Controller on a Two-Wheeled Mobile Robot, IEEE Trans. Ind. Electron, vol. 60, no.12, pp. 5717-5728
Kanada, T., Watanabe, Y., &; Chen, G. (2011). Robust H_2 control for two-wheeled inverted pendulum using LEGO Mindstorms, Paper Presented at Conference of Control, Australia: Melbourne, pp. 136-141
Yamamoto, Y. (2008). NXTway-GS (Self-Balancing Two-Wheeled Robot) Controller Design, The Math Works
Pathak, K., Franch, J., &; Agrawal, S. K. (2005). Velocity and position control of a wheel inverted pendulum by partial feedback linearization, IEEE Trans. Robot., vol. 21, no. 3, pp. 505-513
Ibanez, C.A., Frias, O.G. &; Castanon, M.S. (2005). Lyapunov Based Controller for the Inverted Pendulum Cart System, Nonlinear Dynamic, vol. 40, no. 4, pp. 367-374
Linda, O. &; Manic, M. (2011). Self-Organizing Fuzzy Haptic Teleoperation of Mobile Robot Using Sparse Sonar Data, IEEE Trans. Ind. Electron., vol. 58, no. 8, pp. 3187 - 3195
Gawthrop, P.J. &; McGookin, E. (2004). A LEGO-based control experiment, IEEE Control System, vol. 24. no. 5, pp. 43 - 56
Kim, S.H. &; Jeon W.J. (2009). Introduction for Freshmen to Embedded Systems Using LEGO Mindstorms, IEEE Trans. Education, vol. 52, no. 1, pp. 99 - 108
Kim, Y. (2011). Control System Lab Using a LEGO Mindstorms NXT Motor System, IEEE Trans. Education, vol. 54, no. 3, pp. 452 - 461
Zadeh, L. A. (1965). Fuzzy Set, ScienceDirect. Information and Control Volume 8(Issue 3), pp. 338-353
Takagi, T. &; Sugeno, M. (1985). Fuzzy identification of systems and its applications to modeling and control. IEEE Trans. Systems, Man and Cybernetics, vol. SMC-15, no. 1, pp. 116 - 132
Holland, J. H. (1975). Adaptation in natural and artificial systems: An introductory analysis with applications to biology, control, and artificial intelligence. University of Michigan Press
Juang, Y. T., Chang, Y. T., Huang, C. P. (2008). Design of fuzzy PID controllers using modified triangular membership functions, ScienceDirect. Information Sciences vol. 178, pp. 1325-1333
Wright, A. H. (1991). Genetic algorithms for real parameter optimization. Foundations of genetic algorithms, vol. 1, pp. 205-218
Bramlette, M. F. (1991). Initialization, Mutation and Selection Methods in Genetic Algorithms for Function Optimization. In ICGA, pp. 100-107
Janikow, C. Z., &; Michalewicz, Z. (1991). An experimental comparison of binary and floating point representations in genetic algorithms. In ICGA, pp. 31-36