(3.236.118.225) 您好!臺灣時間:2021/05/17 09:49
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

: 
twitterline
研究生:粘竺弘
研究生(外文):Zhu-Hong Nian
論文名稱:增強式類神經模糊代理模型輔助之多目標連續型蟻群最佳化模糊控制器於機器人沿牆控制
論文名稱(外文):Reinforcement Neural Fuzzy Surrogate –Assisted Multiobjective Continuous Ant Colony Optimized Fuzzy Controller For Robot Wall-Following Control
指導教授:莊家峰
指導教授(外文):Chia-Feng Juang
口試委員:徐超明丁川康
口試日期:2016-07-19
學位類別:碩士
校院名稱:國立中興大學
系所名稱:電機工程學系所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2016
畢業學年度:104
語文別:英文
論文頁數:53
中文關鍵詞:蟻群最佳化多目標最佳化機器人沿牆控制模糊類神經網路增強式學習模糊控制
外文關鍵詞:ant colony optimizationmutiobjective optimizationrobot wall-following controlfuzzy neural networksreinforcement learningfuzzy control
相關次數:
  • 被引用被引用:0
  • 點閱點閱:128
  • 評分評分:
  • 下載下載:16
  • 收藏至我的研究室書目清單書目收藏:0
這篇論文提出了一個增強式類神經模糊代理模型輔助學習多目標前沿導引連續型蟻群最佳化演算法來設計模糊控制器,並且應用在自主機器人沿牆行走控制上。不同於正常改進的連續型蟻群最佳化(ACO)演算法,在一個多目標最佳化問題裡,只找到一個單一的解, MO-RCACO會尋找出Pareto-optimal的解,而且為了避免過於耗時的多目標進化模糊控制器學習,結合了SONFIN代理模型輔助學習進化模糊控制。這個議題的關鍵是在於用估測Objective-function value的方式,取代原本的學習過程。並且為了增加估測的精確度,增強式學習(RL)也被用來協助估測對模糊控制器上的Objective-function value。最後,模擬和實作的結果驗證了新的方法的成效和效率。

This paper proposes a multiobjective front-guided CACO (MO-FCACO) algorithm designed fuzzy controller (FC) with reinforcement neural-fuzzy surrogate-assisted learning method and applies it to autonomous mobile robot wall-following control task. Unlike the single-objective continuous ant colony optimization (ACO) algorithms that find only a single solution in a multi-objective optimization problem, the MO-FCACO finds Pareto-optimal solutions. This thesis proposes the incorporation of the SONFIN surrogate into the multiobjective evolutionary fuzzy control for the sake of avoiding the time-consuming task of multiobjective evolutionary FC learning. Objective-function value estimation which supersedes the original learning process is the key to tackling this issue. Also, in order to improve the accuracy of estimation, reinforcement learning (RL) is used for objective-function value estimation of an FC. Simulation and experimental results verify the effectiveness and efficiency of the new approach.

Contents
摘要 i
Abstract ii
Contents iii
Chapter 1 Introduction 1
1.1. SurveyLiterature Review 1
1.1.1. Fuzzy Systems and ACO 1
1.1.2. Fuzzy Neural Networks and Reinforcement Learning Control 2
1.1.3. Robot Wall-Following Control 3
1.2 Thesis Organization 4
Chapter 2 Fuzzy Control of Mobile Robot 5
2.1. Fuzzy Controller 5
2.2. Mobile Robot Description 6
2.3 Learning Configuration and Multiobjective Functions 7
Chapter 3 Multi-Objective Continuous Ant Colony Optimization for Fuzzy System Design 10
3.1 Multiobjective Optimization Structure 10
3.2 MO-FCACO for FC Optimization 12
3.2.1 Learning Configuration 12
3.2.2 New Solution Generation 14
3.2.3 Solution Global Updated 16
Chapter 4 Neural-Fuzzy Surrogate-Assisted Multiobjective Evolutionary Fuzzy Control 17
4.1 Neural Fuzzy System 17
4.2 Surrogate-Assisted Learning Configuration 24
Chapter 5 Reinforcement Neural-Fuzzy Surrogate-Aided Learning 30
5.1 Reinforcement Learning-Temporal Difference 30
5.2 Reinforcement Neural-Fuzzy Surrogate-Assisted Learning Configuration 32
Chapter 6 Simulations and Experiments 38
Chapter 7 Conclusion 49
References 50



[1]C. F. Juang, “Temporal problems solved by dynamic fuzzy network based on genetic algorithm with variable-length chromosomes,” Fuzzy Sets and Systems, vol. 142, no. 2, pp. 199-219, March 2004.
[2]A. Ratnaweera, S. K. Halgamuge, and H. C. Watson, “Self-organizing hierarchical particle swarm optimizer with time-varying acceleration coefficients,” IEEE Trans. Evol. Comput, vol. 8, no. 3, pp. 240-255, Jun. 2004.
[3]C. F. Juang, “A hybrid of genetic algorithm and particle swarm optimization for recurrent network design,” IEEE Trans. Syst, Man, Cybern. B, Cybern., vol. 34, no. 2, pp. 997-1006, Apr. 2004.
[4]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.
[5]H. Li, Q. Zhang, E. Tsang and J. A. Ford, “Hybrid estimation of distribution algorithm for multiobjective knapsack problem,” EvoCOP, pp. 145-154, 2004.
[6]K. Deb, A. Pratap, S. Agarwal, and T. Meyarivan, “A fast and elitist multiobjective genetic algorithm: NSGAII,” IEEE Trans. Evol. Comput, vol. 6, no. 2, April 2002.
[7]E. Zitzler, M. Laumanns, and L. Thiele, “SPEA2: Improving the strength Pareto evolutionary algorithm,” Comput. Eng. Netw. Lab, Swiss Federal Inst. Technol, Zurich, Tech. Rep. 103, 2001.
[8]C. A. Coello Coello, G. T. Pulido, and M. S. Lechuga, “Handling multiple objectives with particle swarm optimization,” IEEE Trans. Evol. Comput, vol. 8, no. 3, pp. 256-279, June 2004.
[9]M. Daneshyari and G. G. Yen, “Cultural-based multiobjective particle swarm optimization,” IEEE Trans. Syst. Man, and Cybernetics, vol. 41, no. 2, pp. 553-567, April 2011.
[10]C. H. Hsu and C. F. Juang, “Multi-objective continuous-ant-colony-optimized FC for robot wall-following control,” IEEE Computational Intelligence Magazine, vol. 8, no. 3, pp. 28-40, Aug. 2013.
[11]C. F. Juang, T. L. Jeng, and Y. C. Chang, “An interpretable fuzzy system learned through online rule generation and multi-objective ACO with a mobile robot control application,” in Press, IEEE Trans. Cyber, 2016.
[12]C. F. Hsu and C. F. Juang, “Evolutionary robot wall-following control using type-2 fuzzy controller with species-DE activated continuous ACO,” IEEE Trans. Syst, vol. 21, no. 1, pp. 100-112, Feb. 2013.
[13]C. F. Lu, C. H. Hsu, and C. F. Juang, “Coordinated control of flexible AC transmission system devices using an evolutionary fuzzy lead-lag controller with advanced continuous ant colony optimization,” IEEE Trans. Power Systems, vol. 28, no. 1, pp. 385 - 392,Feb. 2013.
[14]K. Socha and M. Dorigo, “Ant colony optimization for continuous domain, ” European Journal of Operational Research, vol. 185, pp. 1155-1173, 2008.
[15]R. R. Bush and F. Mosteller, Stochastic Models for Learning [M]. New York :Wiley ,1955.
[16]H. Hagras, V. Callaghan, and M. Colley, “Learning and adaptation of an intelligent mobile robot navigator operating in unstructured environment based on a novel online Fuzzy-Genetic system,” Fuzzy Sets and Systems, vol.141, pp. 107-160, 2004.
[17]M. Mucientes and J. Casillas, “Quick design of fuzzy controller with good interpretability in mobiles robotics,” IEEE Trans. Fuzzy Syst, vol. 15, no. 4, pp. 636-651, Aug. 2007.
[18]Y. Zhou and M. J. Er, “An evolutionary approach toward dynamic self-generated fuzzy inference systems,” IEEE Trans. Syst, Man, Cybern. B, Cybern., vol. 38, no. 4, pp. 963-969, Aug. 2008.
[19]C. F. Juang and C. H. Hsu, “Reinforcement ant optimized fuzzy controller for mobile-robot wall-following control,” IEEE Trans. Ind. Electron, vol. 56, no. 10, pp. 3931-3940, Oct. 2009.
[20]G. Antonelli, S. Chiaverini, and G. Fusco, “A fuzzy-logic-based approach for mobile robot path tracking,” IEEE Trans. Fuzzy Syst, vol. 15, no. 2, pp. 211-221, Apr. 2007.
[21]C. Y. Tsai and K. T. Song, “Visual tracking control of a wheeled mobile robot with system model and velocity quantization robustness,” IEEE Trans. Cont. Syst. Tech., vol. 17, no. 3, pp. 520-527, May 2009.
[22]A. Zhu and S. X. Yang, “Neurofuzzy-based approach to mobile robot navigation in unknown environments,” IEEE Trans. Syst, Man, Cybern. C, Appl. Rev., vol. 37, no. 4, pp. 610-621, July 2007.
[23]C. Luo and S. X. Yang, “A bioinspired neural network for real-time concurrent map building and complete coverage robot navigation in unknown environments,” IEEE Trans. Neural Networks, vol. 19, no. 7, pp. 1279-1298, July 2008.
[24]F. Cupertino, V. Giordano, D. Naso, and L. Delfine, “Fuzzy control of a mobile robot,” IEEE Robot. Autom. Mag, vol. 13, no. 4, pp. 74–81, Dec. 2006.
[25] C. F. Juang and Y. C. Chang, “Evolutionary-group-based particle- swarm-optimized fuzzy controller with application to mobile-robot navigation in unknown environments,” IEEE Trans. Fuzzy Syst, vol. 19, no. 2, pp. 379-392, April 2011.
[26]A. Chatterjee, K. Pulasinghe, K. Watanabe, and K. Izumi, “A particleswarm-optimized fuzzy-neural network for voice-controlled robot systems,” IEEE Trans. Ind. Electron, vol. 52, no. 6, pp. 1478–1489, Dec. 2005.
[27]A. Zhu and S. X. Yang, “Neurofuzzy-based approach to mobile robot navigation in unknown environments,” IEEE Trans. Syst. Man, Cybern. C, Appl. Rev., vol. 37, no. 4, pp. 610–621, Jul. 2007.
[28]C. F. Juang “An online self-constructing neural fuzzy inference network and its applications,” IEEE Trans. Syst, vol. 6, no. 1, Feb.1998.
[29]S. J. Bradtke and A. G. Barto“ Linear least-squares algorithms for temporal difference learning,” Machine Learning, pp.22,33-57, 1996


QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top