本研究提出 DNA 演化模糊系統及 Q-Learning 之適應性學習方法，以訓練移 動機器人適應其複雜的環境。而 Q-Learning 是在增強式學習中一種常用的演算 法，能讓控制系統具有很好的判斷能去尋找較佳的策略，並且搭配 DNA 遺傳演 化法之適應函數，來演化模糊系統的權重值，使移動機器人能有較佳的行走角 度。此外，本研究所設計的適應函數有考慮最短路徑的問題，因此透過每一代 的演化，使得移動機器人能夠行走出較佳的路徑，並且不需要使用導航攝影機 來給定目標物及機器人的座標資訊進而求出最短路徑，所以本研究所提出的整 合性演算法能夠降低成本問題。
本研究所提出的整合性演算法雖然能夠讓某一環境成功的執行目標物搜 尋，但儘此於障礙物的位置是固定不變的，也就是說，一條演化較佳的 DNA 染 色體，即使將障礙物的位置改變之後，此 DNA 染色體不需要讓移動機器人學 習，也能夠成功的閃避障礙物而達成目標物的搜尋，因此本研究尚有許多環境 的未知變數沒有考慮到，使得 DNA 染色體的演化功能發揮的有限，所以本研究 建 議 去 探 討 如 何 讓 D N A 染 色 體 針 對 未 知 的 環 境 發 揮 到 最 大 效 能 。
參考文獻
[1] L. A. Zadeh, “Fuzzy sets”, IEEE Trans. Information and Control 8, pp. 338-353, 1965
[2] L.X. Wang and J.M. Mendel, “Fuzzy Basis Functions, Universal Approximation, and Orthogonal Least Squares Learning,” IEEE Trans. Neural Networks., vol. 3, no. 5, pp. 807-814, 1992.
[3] C.H. Wang, W.Y. Wang, T.T. Lee, and P.S. Tseng, “Fuzzy B-spline Membership Function (BMF) and Its Applications in Fuzzy-Neural Control,” IEEE Trans. Syst.
Man, Cyber., vol. 25, no. 5, pp.841-851, 1995.
[4] L.X. Wang, Adaptive fuzzy systems and control: design and stability analysis, Englewood Cliffs,NJ: Prentice-Hall, 1994.
[5] Y. D. Kwon, J. M. Won and J. S. Lee, “Control of Mobile Robot by using Evolutionary Fuzzy Controller”, IEEE International Conference on Evolutionary Computation., South Korea, 1998, pp. 422-427.
[6] P. Phokharatkual and S. Phaiboon, “Mobile Robot Control Using Type-2 Fuzzy L o g i c S y s t e m ” , I E E E C o n f e r e n c e o n R o b o t i c s , A u t o m a t i o n a n d Mechatronics., Singapore, Dec. 2004, pp. 296-299.
[7] H. A. Hagras, “A Hierarchical Type-2 Fuzzy Logic ControlArchitecture for A u t o n o m o u s M o b i l e R o b o t s ” , I E E E T r a n s . F u z z y S y s t e m s . , v o l . 12, no. 4, pp. 524-539, Aug, 2004.
[8] C. F. Juang, “A TSK-Type Recurrent Fuzzy Network for Dynamic Systems Processing by Neural Network and Genetic Algorithms”, IEEE Trans. Fuzzy Systems., vol. 10, no. 2, pp.155-170, 2002.
[9] W.A. Farag, V.H. Quintana, and G. Lamberttorres, “A Genetic-Based Neuro-Fuzzy Approach for Modeling and Control of Dynamical Systems,” IEEE Trans.
Neural Networks., vol. 9, no. 5, pp. 756-767, Sept. 1998.
[10] C. H. Wang, H.L. Liu, and C.T. Lin, “Dynamic Optimal Learning Rates of a Certain Class of Fuzzy Neural Networks and its Applications with Genetic Algorithm,” IEEE Trans. Syst. Man, Cyber. Part B., vol. 31, no. 3, pp.467 –475, June 2001.
[11] Y. Yuan, and H. Zhuang, “A Genetic Algorithm for Generating Fuzzy Classification Rules,” IEEE Trans. Fuzzy Sets and Systems., vol. 84, no. 1, pp.
1-19, November, 1996.
[12] T.L. Seng, M.B. Khalid, and R. Yusof, "Tuning of a Neuro-Fuzzy Controller by
Genetic Algorithm," IEEE Trans. Syst. Man, Cyber. Part B., vol. 29, no. 2, pp.226-236, 1999.
[13] Y. G. Leu, “DNA-Based Evolution Fuzzy-Neural Networks,” 2005 The 13th National Conference on Fuzzy Theory and Its Applications.
[14] T. Yoshikawa, T. Furuhashi, and Y. Uchikawa, “DNA Coding Method and a Mechanism of Development for Acquisition of Fuzzy Control Rules,” IEEE International Conference on Fuzzy Systems., Japan, 1996 , pp.2194-2200.
[15] T. Yoshikawa, T. Furuhashi, and Y. Uchikawa, “Emergence of Effective Fuzzy Rules for Controlling Mobile Robots using DNA Coding Method,” IEEE International Conference on Evolutionary Computation., Japan, 1996, pp.
581-586,.
[16] T. Yoshikawa, T. Furuhashi, and Y. Uchikawa, “The Effects of Combination of DNA Coding Method with Pseudo-Bacterial GA,” Proceedings of IEEE International Conference on Evolutionary Computation., Japan, 1997, pp.
285-290,.
[17] Y.S Ding and L.H. Ren, “A new DNA-Based Evolutionary Algorithm with Application to the Design of Fuzzy Controllers,” Proceedings of the 2002 Congress on Evolutionary Computation., Shanghai, 2002, pp.1982-1987.
[18] L.H. Ren and Y.S Ding, “Design of Fuzzy Control System by a new DNA-Based Immune Genetic Algorithm,” IEEE International Conference on Fuzzy Systems., Shanghai, 2001, pp. 244-247.
[19] Y.S Ding and L.H. Ren, “DNA Genetic Algorithm for Design of the Generalized Membership-Type Takagi-Sugeno Fuzzy Control System,” IEEE International Conference on Systems, Man, and Cybernetics., Shanghai, 2000, pp.3862-3867.
[20] C. Wagner and H. Hagras, “A Genetic Algorithm Based Architecture for Evolving Type-2 Fuzzy Logic Controllers for Real World Autonomous Mobile Robots,” IEEE International Conference on Fuzzy Systems., London, 2007, pp.
1-6.
[21] B. Andersson, P. Svesson, M. Nordahl, and P. Nordin, “On-Line Evolution of Control for a Four-Legged Robot using Genetic Programming,” in Real-World Applications of Evolutionary Computing. ser. Lecture Notes inComputer Science., S. Cagnoni et al., Eds. Berlin, Germany: Springer-Verlag, 2000, pp. 319–326.
[22] D. V. Djonin and V. Krishnamurthy, “Q-Learning Algorithms for Constrained Markov Decision Processes With Randomized Monotone Policies: Application to
2170-2181, May. 2007.
[23] G.S. Yang, E. K. Chen, and C.W. An, “Mobile Robot Navigation using Neural Q-Learning,” International Conference on Machine Learning and Cybernetics., Shanghai, 2004, pp. 48-52.
[24] D.E. Goldberg , Genetic Algorithm in Search Optimization and Machine Learning. Reading , MA: Addison-Wesley, 1989.
[25] A. Homaifar and E. McCormick, “Simultaneous Design of Membership Functions and Rule Sets for Fuzzy Controllers using Genetic Algorithms,” IEEE Trans. Fuzzy Syst., vol. 3, no. 2, pp. 129-139, Apr. 1995.
[26] C. J. Watkins and P. Dayan, “Q-Learning”. Machine Learning, vol 8, no.3, pp.
279-292, March 1992.
[27] M.N. Ahmadabadi and M. Asadpur, “Expertness Based Cooperative Q-Learning,”
IEEE Trans. Systems, Man, and Cybernetics-part B: Cybernetics., vol. 32, no. 1, pp. 66-76, Feb. 2002.
[28] E.H. Mamdani and S. Assilian, “An Experiment in Linguistic Synthesis with a Fuzzy Logic Controller,” Int. Journal of Man-Machine Studies, vol. 7, no. 1, pp.
1-13, 1975.
[29] 王文俊，“認識 Fuzzy-第二版＂，全華科技圖書出版社，Oct. 1997。