Please use this identifier to cite or link to this item:
標題: 以進階型差分演化法設計模糊控制器在六足式機器人沿牆控制
Hexapod Robot Wall-Following Control Using Fuzzy Controller with Advanced Differential Evolution
作者: 陳盈翰
Chen, Ying-Han
關鍵字: 機器人
hexapod robot
Differential Evolution
出版社: 電機工程學系所
引用: [1] C. F. Juang, “Combination of on-line clustering and Q-value based GA for reinforcement fuzzy system design,” IEEE Trans. Fuzzy Systems, vol. 13, no. 3, pp. 289-302, June 2005. [2] R. Alcala, J. Alcala-Fdez, J. Casillas, O. Cordon, and F. Herrera, “Local identification of prototypes for genetic learning of accurate TSK fuzzy rule-based systems,” International Journal of Intelligent Systems, vol. 22, no. 9, pp. 909-941, Sep. 2007. [3] E. G. Mansoori, M. J. Zolghadri, S. D. Katebi, “SGERD: A steady-state genetic algorithm for extracting fuzzy classification rules from data,” IEEE Trans. Fuzzy Systems, vol. 16, no. 4, pp. 1061-1071, Aug. 2008. [4] A. Chatterjee, K. Pulasinghe, K. Watanabe, and K. Izumi, “A particle swarm-optimized fuzzy-neural network for voice-controlled robot systems,” IEEE Trans. Ind. Electron., vol. 52, no. 6, pp. 1478–1489, Dec. 2005. [5] C. F. Juang and C. Lo, “Zero-order TSK-type fuzzy system learning using a two-phase swarm intelligence,” Fuzzy Sets and Systems, vol. 159, no. 21, pp. 2910-2926, Nov. 2008. [6] K. D. Sharma, A. Chatterjee, and A. Rakshit, “A hybrid approach for design of stable adaptive fuzzy controllers employing Lyapunov theory and particle swarm optimization,” IEEE Trans. Fuzzy Systems, vol. 17, no. 2, pp. 329-342, April 2009. [7] F. J. Lin, L. T. Teng, J. W. Lin and S. Y. Chen, “Recurrent functional-link-based fuzzy-neural-network-controlled induction-generator system using improved particle swarm optimization, IEEE Trans. Ind. Electron., vol. 56, no. 5, pp. 1557-1577, May 2009. [8] C. F. Juang, C. M. Hsiao, and C. H. Hsu, “Hierarchical cluster-based multi-species particle swarm optimization for fuzzy system optimization,” IEEE Trans. Fuzzy Systems, vol. 18, no. 1, pp. 14-26, Feb. 2010. [9] Rainer Storn and Kenneth Price, “Differential Evolution – A simple and efficient adaptive scheme for global optimization over continuous spaces,” International Computer Science Institute, 1947. [10]Rainer Storn and Kenneth Price, “Differential Evolution – A simple and efficient Heuristic for Global Optimization over Continuous Spaces,” Journal of Global Optimization, pp.341-359, Nov. 1997. [11]Leandro dos Santos Coelho and Viviana Cocco Mariani, “Combining of Chaotic Differential Evolution and Quadratic Programming for Economic Dispatch Optimization With Valve-Point Effect,” IEEE Transactions on Power Systems, vol.21 no.2, May 2006. [12]Cheng-Hung Chen, Cheng-Jian Lin and Chin-Teng Lin, “Nonlinear System Control Using Adaptive Neural Fuzzy Networks Based on a Modified Differential Evolution,” IEEE Trans. on Systems, vol. 39, no. 4, pp. 459-473,July 2009. [13]C.H. Hsu and C.H. Juang, “Evolutionary Robot Wall-Following Control Using Type-2 Fuzzy Controller with Species-DE Activated Continuous ACO,” IEEE Trans Fuzzy Systems , Dec. 2012.
摘要: 本論文提出了以進階型差分演化演算法(ASDE)來設計模糊控制器(FC)進行六足式機器人的沿牆控制。ASDE使用群組為基礎的概念。在每個世代將向量解依照好壞程度進行分群,ASDE動態的產生以族群為基礎的突變向量或根據以每個世代為基礎的適應機率值經過突變運算產生一般的突變解。ASDE被應用在設計模糊控制器進行機器人的沿牆控制。控制器裡面所有的自由參數都是透過ASDE所學習出來的,以避免費時的手動設計課題。模糊控制器的輸入是三個紅外線感測器所感應到的數值。在往直行走的同時模糊控制器控制六足機器人左邊與右邊的中間腳的改變擺幅角度使機器人有適當的轉彎方向。一個新的成本函數被定義為在對模糊控制器的性能做定量評價。在事先未詳細收集兩個不同的訓練環境地形的輸入與輸出詳細數據下。進行模擬來驗證進化式沿牆學習方法的有效性。跟其他進階型差分演化演算法比較下顯示ASDE在沿牆控制任務中有比較好的性能。
This thesis proposes advanced species differential evolution (ASDE) algorithm designed fuzzy controller (FC) to perform hexapod robot wall following. The ASDE uses the concept of the species (clustering). The solution vectors are clustered into different species based on their performances at each iteration. The ASDE dynamically generates a species-based mutant vector or a general mutant vector in the mutation operation according to an iteration-based adaptive probability value. The ASDE is applied to design an FC for robot wall-following control. All of the free parameters in the FC are learned through ASDE, which avoids the time-consuming manual design task. The FC inputs are three infrared distance sensor values. The FC controls the swing angle changes of the left- and right-middle legs of the hexapod robot to perform a suitable turning direction while moving forward at the same time. A new cost function is defined to quantitatively evaluate the performance an FC. Two different training environments are created for building this wall-following behavior without an exhaustive collection of input-output training pairs in advance. Simulations are conducted to verify the effectiveness of the evolutionary wall-following learning approach. Comparisons with other advanced differential evolution algorithms show that the ASDE achieves better performance in the wall-following control task.
其他識別: U0005-1808201219490300
Appears in Collections:電機工程學系所



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.