簡易檢索 / 詳目顯示

研究生: 石顏彰
Shih, Yan-Jhang
論文名稱: 特徵提取型同時定位與建圖演算法及其在FPGA之實現
FPGA-Based Realization for Feature Extracting Simultaneous Localization and Mapping
指導教授: 許陳鑑
Hsu, Chen-Chien
王偉彥
Wang, Wei-Yen
學位類別: 碩士
Master
系所名稱: 電機工程學系
Department of Electrical Engineering
論文出版年: 2015
畢業學年度: 103
語文別: 中文
論文頁數: 66
中文關鍵詞: 同時定位及建圖粒子濾波器卡爾曼濾波器移動式機器人FPGA
英文關鍵詞: SLAM, Particle Filter, Kalman Filter, Mobile robot, FPGA
論文種類: 學術論文
相關次數: 點閱:149下載:17
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報
  • FastSLAM 為解決同時定位與建圖的有效方法,但由於地標數過多,容易造成運算量過於龐大而導致系統發散。原始的快速同時定位及建圖(Fast Simultaneous Location and Mapping, FastSLAM)收斂效果好,但會因為地標數目增加所造成誤差的累積,而導致系統發散,論文中透過向量比對機制,使得特徵變化較大的感測資訊被保留下來,減少與現有地標比對的機會,且使得資料關聯的結果較為準確,最後更利用準確的地標更新機器人的位置以提升定位精準度。為了驗證論文所提出方法可以確實有效提升精確度以及降低其運算量,將會利用傳統FastSLAM與本論文所提出之特徵提取型SLAM以多種不同地圖進行模擬並比較其結果。同時,本論文也使用FPGA晶片將此改良同時定位及建圖實現於硬體電路以縮短運算時間,並增加其演算法之運用性。

    FastSLAM is an effective method to solve simultaneous localization and mapping. However, when the number of landmarks increases, more comparisons of the current measurements with all the existing landmarks in particles will be compared and the accuracy of the estimated location of the robot and landmark decreases because of incorrect data association. In order to solve this problem, this thesis presents an enhanced architecture for FastSLAM called Feature Extracting SLAM (FESLAM), where current measurement is filtered to extract special measurement to avoid getting unnecessary and wrong landmarks. To further refine the robot pose, we use triangulation and set on maximum likelihood mapping framework. Simulation results show the proposed approach has a better performance in terms of better localization and mapping than those obtained by the traditional SLAM algorithms. To further reduce the computation time, the improved SLAM system algorithm is realized on FPGA circuit using a DE2i-150 to verify the practicability of the proposed algorithm. Experimental results show the execution efficiency of FESLAM is significantly improved by the full hardware design for embedded applications.

    目錄 摘   要 i ABSTRACT ii 致   謝 iii 表目錄 vi 圖目錄 vii 第一章 緒論 1 1.1 研究背景與動機 1 1.2 論文架構 5 第二章 文獻探討 6 2.1 卡爾曼濾波器 6 2.2 蒙地卡羅定位 8 2.3 同時定位與建圖演算法 11 2.3.1快速同時定位與建圖演算法(FastSLAM 1.0) 13 2.3. 2快速同時定位與建圖演算法(FastSLAM 2.0) 16 第三章 基於高計算效率、低運算成本同時定位及建圖演算法 23 第四章 硬體設計平台 33 4.1 DE2-70多媒體開發平台 33 4.2 D5M擷取模組 36 第五章 同時定位與建圖演算法之硬體電路設計 39 5.1 硬體電路架構 39 5.2 FESLAM演算法硬體電路設計 40 5.2.1 初始化模組 41 5.2.2 預測模組 42 5.2.3 特徵提取模組 44 5.2.4 相似性模組 46 5.2.5 地標更新與新增模組 48 5.2.6 三角定位模組 49 5.2.7 重新取樣模組 51 5.3 其他應用模組 53 5.3.1 隨機亂數模組 53 5.3.2 RAM 54 第六章 模擬與實驗結果 55 6.1 改良型SLAM演算法之模擬結果 56 6.1.1 傳統演算法與改良型演算法模擬圖 56 6.1.2 傳統演算法與改良型演算法精確度 57 6.2 軟硬體設計之SLAM演算法效能比較結果 60 第七章 結論 61 7.1 結論 62 參考文獻 63   表目錄 表2- 1 圖2- 3之圖示說明 8 表5- 1 初始化模組訊號說明表 41 表5- 2 預測模組訊號說明表 43 表5- 3 特徵提取模組訊號說明表 45 表5- 4 相似性模組訊號說明表 46 表5- 5 地標更新與新增模組訊號說明表 48 表5- 6 三角定位模組訊號說明表 50 表5- 7 重新取樣模組訊號說明表 52 表5- 8 隨機亂數模組輸出入訊號說明表 54 表5- 9 RAM訊號腳位說明表 54 表6 - 1 實驗之筆電規格 54 表6 - 2參數表 56 表6 - 3平均誤差 57 表6 - 4全軟體以及全硬體設計之各模組比較實驗結果 60 錯誤! 找不到參照來源。 61   圖目錄 圖1 - 1 機器人導航分類 2 圖2 - 1 EKF SLAM演算示意圖 8 圖2 - 2 粒子濾波器流程圖 11 圖2- 3 SLAM演算法示意圖 11 圖2- 4FastSLAM 1.0之流程圖 20 圖2- 5FastSLAM 2.0流程圖 20 圖3 - 1 轉角特徵提取演算法 22 圖3 - 2 曲率特徵提取演算法 26 圖3 - 3 三角定位示意圖 27 圖3 - 4 FESLAM流程圖 30 圖4 - 1 DE2i-150開發板實體圖 38 圖4 - 2 DE2i-150模組方塊圖 38 圖4 - 3 Capacitive Multi-Touch LCD with Camera模組 (MTLC) 40 圖4 - 4 MTLC Block Diagram 41 圖5 - 1同時定位與建圖系統架構圖 43 圖5 - 2 特徵提取型同時定位與建圖之狀態控制圖 43 圖5 - 3初始化模組訊號圖 42 圖5 - 4初始化模組之硬體架構圖 43 圖5 - 5預測模組訊號圖 44 圖5 - 6預測模組之硬體架構圖 44 圖5 - 7特徵提取模組訊號圖 45 圖5 - 8特徵提取模組之硬體架構圖 46 圖5 - 9 相似性模組訊號圖 47 圖5 - 10 相似性模組之硬體架構圖 50 圖5 - 11 地標更新與新增模組訊號圖 51 圖5 - 12 地標更新與新增模組之硬體架構圖 52 圖5 - 13三角定位模組訊號圖 53 圖5 - 14 三角定位模組之硬體架構圖 53 圖5 - 15 重新取樣模組訊號圖 53 圖5 - 16 重新取樣模組之硬體架構圖 53 圖5 - 17 隨機亂數模組訊號圖 54 圖5 - 18 RAM之邏輯符號圖 56 圖6 - 1探索連續直角之未知環境下地標建立模擬圖 57 圖6 - 2探索未知室內環境下地標建立模擬圖 58 圖6 - 3 定位誤差 59 圖6 - 4 各SLAM演算法的執行時間 60 圖6 - 4 各SLAM演算法的執行時間 62

    [1] iRobot的自動吸塵機器人-Roomb, URL: http://www.roomba.com.tw/
    [2] 健康照護型機器人Jibo,
    URL:https://www.indiegogo.com/projects/jibo-world-s-first-family-robot-4-800-pre-sold
    [3] Dr. Robot 的住家保全機器人- Sentinel,
    URL:http://www.pitotech.com.tw/show_product.php?btype=7<ype=401&id=401
    [4] T. Bailey and H. Durrant-Whyte, “Simultaneous localization and mapping: part II,” IEEE Robot Autom. Mag., vol. 13, no. 3, pp. 108-117, 2006.
    [5] J. J. Leonard and H. J. S. Feder, “A computationally efficient method for large-scale concurrent mapping and localization,” in Proc. Ninth International Symposium on Robotics Research (ISRR’99), 2000, pp. 169-176.
    [6] J. Guivant, E. Nebot, and S. Baiker, “Localization and map building using laser range sensors in outdoor applications,” Journal of Robotic Systems, vol. 17, no. 10, pp. 565-583, 2000.
    [7] S. B. Williams, P. Newman, G. Dissanayake, and H. F. Durrant-Whyte, “Autonomous underwater simultaneous localisation and map building,” in Proc. IEEE International Conference on Robotics and Automation (ICRA), San Francisco, 2000, vol. 2, pp. 1793-1798.
    [8] G. Dissanayake, S. B. Williams, H. Durrant-Whyte, and T. Bailey, “Map management for efficient simultaneous localization and mapping (SLAM),” Autonomous Robots, vol. 12, pp. 267-286, 2002.
    [9] G. Welch and G. Bishop, “An introduction to the Kalman filter,” SIGGRAPH, Los Angeles, CA , 2001.
    [10] R. C. Smith and P. Cheeseman, “On the representation and estimation of spatial uncertainty,” International Journal of Robotics, vol. 5, pp. 56-58, 1986.
    [11] M. Montemerlo, S. Thrun, D. Koller, and B. Wegbreit, “FastSLAM: A factored solution to the simultaneous localization and mapping problem,” in Proc. AAAI National Conference on Artificial Intelligence, 2002, pp. 593-598.
    [12] K. Murphy, “Bayesian map learning in dynamic environments,” Neural Information Proceedings System, vol. 12, pp. 1015-1021, 2000.
    [13] L. Pedraza, D. Rodriguez-Losada, F. Matia, “Extending the limits of feature-based SLAM with B-splines,” IEEE Trans. on Robotics, vol. 25, pp. 353-366, April 2009.
    [14] S. B. Williams, G. Dissanayake, and H. F. Durrant-Whyte, “An efficient approach to the simultaneous localisation and mapping problem,” in Proc. IEEE International Conference on Robotics and Automation, Washington, USA, 2002, pp. 406-411.
    [15] G. Dissanayake, S. B. Williams, H. F. Durrant-Whyte, and T. Bailey, “Map management for efficient simultaneous localization and mapping (SLAM),” Autonomous Robots, vol. 12, no. 3, pp. 267-286, 2002.
    [16] Q. Liping, H. Shuiqing, and Q. Yongyin, “An SLAM algorithm based on improved UKF,” in Proc. IEEE International Conference on Control and Decision Conference (CCDC), Taiyuan, 2012, pp. 4154-4157.
    [17] A. Chatterjee, “Differential evolution tuned fuzzy supervisor adapted, extended Kalman filtering for SLAM problems in mobile robots,” Robotica, vol. 27, pp. 411-423, 2009.
    [18] A. Chatterjee and F. Matsuno, “A neuro-fuzzy assisted extended Kalman filter based approach for Simultaneous Localization and Mapping (SLAM) problems,” IEEE Trans. on Fuzzy Systems, vol. 15, pp. 984-997, 2007.
    [19] A. Chatterjee and F. Matsuno, “A Geese PSO tuned fuzzy supervisor for EKF based solutions of simultaneous localization and mapping (SLAM) problems in mobile robots,” Expert Systems with Applications, vol. 37, pp. 5542-5548, 2010.
    [20] A. Stentz, D. Fox, and M. Montemerlo, “FastSLAM: A factored solution to the simultaneous localization and mapping problem with unknown data association,” in Proc. AAAI National Conference on Artificial Intelligence, 2003, pp. 593-598.
    [21] G. Dissanayake, P. Newman, H. F. Durrant-Whyte, S. Clark, and M. Csobra, “An experimental and theoretical into simultaneous localization and map building (SLAM),” Lecture Notes in Control and Information Sciences, Experimental Robotics VI, 2000, pp. 265-274.
    [22] K. Murphy, “Bayesian map learning in dynamic environments,” Neural Information Proceedings System, vol. 12, pp. 1015-1021, 2000.
    [23] M. Montemerlo, S. Thrun, D. Koller, and B. Wegbreit, “FastSLAM 2.0: An improved particle filtering algorithm for simultaneous localization and mapping that provably converges,” in Proc. International Joint Conference on Artificial Intelligence, 2003, pp. 1151-1156.
    [24] M. Montemerlo and S. Thrun, “Simultaneous localization and mapping with unknown data association using FastSLAM,” in Proc. IEEE Int. Conf. Robotics and Automation, 2003, pp. 1985-1991.
    [25] C. K. Yang, C. C. Hsu, and T. T. Wang “Computationally efficient algorithm for simultaneous localization and mapping,” in Proc. Networking, Sensing and Control, 2013, pp. 328-332.
    [26] Altera多媒體發展平台DE2i-150網址,
    URL:http://www.terasic.com.tw/cgi-bin/page/archive.pl?Language=English&CategoryNo=11&No=529
    [27] Terasic Corporation, URL:http://www.terasic.com.tw/tw/
    [28] Terasic Corporation, My_First_FPGA, Document Version 1.0, 2013.
    [29] Terasic Corporation, My_First_ NiosII, Document Version 1.0, 2013.
    [30] Terasic Corporation, DE2i-150 Win7 User Manual, Document Version 1.0, 2014.
    [31] MTLC相機及顯示模組網址,URL:http://www.terasic.com.tw/cgi-bin/page/archive.pl?Language=Taiwan&CategoryNo=85&No=901
    [32] Terasic Corporation, MTLC_User_Manual, Document Version 1.0, 2014.
    [33] S. Suranthiran and S. Jayasuriya, “Effective Fusion of Distorted Multi-sensor Data,” in Proc. Intelligent Control, 2003, pp. 444-449.
    [34] Z. Junhua1 and Wangwei, “The Extraction of Fractional-order Curvature Attributes and Applications in the Structure Interpretation,” in Proc. Artificial Intelligence and Computational Intelligence, 2000, pp. 123–126.

    下載圖示
    QR CODE