• 沒有找到結果。

結論與未來展望

5.1 結論

本論文以粒子濾波器為基礎設計估測機器人位置的方法,並結合以環境比對 方式估測機器人朝向角的方法,發展出一個有效的機器人自我定位系統。在位置 估測方面,由里程計的資訊可以先對機器人的位置做預測,接著再加入由雷射掃 描儀的距離資料產生的環境線段組的資訊,並藉由粒子濾波器計算出估測的機器 人位置座標。在朝向角估測上,將雷射掃描儀所得到的環境距離資料以線段擷取 的方法擷取成線段組,再將此線段組結合機器人位置座標的資訊與機器人內建的 環境地圖做比對,根據比對的結果來估測機器人的朝向角。從繞行環境的實驗結 果可以得知,機器人在繞行過程當中其行走路徑皆與所設定的軌跡相符合,而機 器人要能依照設定的軌跡移動,必須根據定位系統對其目前姿態的估測結果來決 定行進的方向,如果定位系統所估測出來的機器人姿態接近實際的情況,則機器 人便能確實的依照設定軌跡而繞行。所以從實驗結果顯示的機器人移動路徑,我 們可以驗證設計的定位系統是有效的。

5.2 未來展望

目前所設計的定位系統仍有許多值得進一步探討的地方:

1.在環境特徵擷取方面目前是以牆面作為環境特徵來進行地圖比對,未來若能加 入其它的環境特徵,如牆角、門等,將可使地圖比對的結果更為精確,提高定 位系統的準確度。

2.在機器人運動控制方面,因為目前所使用的控制方式是判斷機器人與目標點之 間的夾角,當夾角大於設定範圍時才修正機器人前進的朝向角,如此會造成機

器人在偏離設定軌跡時無法即時修正返回設定軌跡的情況產生。所以未來如果 能對於機器人系統設計一個運動控制器,使得當機器人根據定位系統的姿態估 測得知其已偏離設定軌跡時便能即時修正其運動方向,將可讓機器人行走的軌 跡與設定的軌跡更加符合。

3.目前的定位系統在加上運動控制的改善後,將可運用於在室內以牆面為主要結 構環境中的巡邏機器人的應用上。

參考文獻

[1] G. Dudek and C. Zhang, “Vision-based robot localization without explicit object models,” in Proceedings of IEEE International Conference on Robotics and Automation, Minneapolis, Minnesota, USA, 1996, pp. 76-81.

[2] A. Elfes, “Sonar-based real-world mapping and navigation,” IEEE Journal of Robotics and Automation, vol. RA-3, no. 3, pp. 249-265, 1987

[3] I. J. Cox, “Blanche-an experiment in guidance and navigation of an autonomous robot vehicle,” IEEE Transactions on Robotics and Automation: a publication of the IEEE Robotics and Automation Society, vol. 7, no. 2, pp. 193-204, 1991 [4] F. Lu and E. Milios, “Robot pose estimation in unknown environments by

matching 2D range scans,” Journal of Intelligent & Robotic Systems, vol. 18, no. 3, pp. 249-275, 1997

[5] Gijeong Jang, Sungho Lee, Inso Kweon, “Color landmark based self-localization for indoor mobile robots,”in Proceedings of IEEE International Conference on Robotics and Automation, Washington, DC, USA, 2002, pp. 1037-1042.

[6]J. Ryde, H. Hu, “Fast Circular Landmark Detection for Cooperative Localisation and Mapping,”in Proceedings of IEEE International Conference on Robotics and Automation, Barcelona, Spain, 2005, pp. 2745-2750.

[7]L. Iocchi, D. Mastrantuono, and D. Nardi. “A probabilistic approach to Hough localization,” In Proceedings of IEEE International Conference on Robotics and Automation, Seoul, Korea, 2001, pp. 4250-4255.

[8] D. Fox, W. Burgard,Frank Dellaert, and S. Thrun, “Monte Carlo Localiation for Mobile Robots,”in Proceedings of IEEE International Conference on Robotics and Automation, Detroit, Michigan, 1999, pp. 1322-1328.

[9] P. Jensfelt, “Approaches to Mobile Robot Localization in Indoor Environments,”

Doctoral Thesis, Royal Institute of Technology, Sweden, 2001.

[10] M. Sanjeev Arulampalam, Simon Maskell, Neil Gordon, and Tim Clapp, “A Tutorial on Particle Filters for Online Nonlinear/Non-Gaussian Bayesian

Tracking”, IEEE Transactions on Signal Processing, vol. 50, no. 2 February 2002.

[11] SICK, “Telegrams for Operating/Configuring the LMS 2xx Laser Measurement Systems,” 2003.

[12] S. Thrun , W. Burgard, and D. Fox, Probabilistic Robotics, MIT Press, Cambridge, MA, 2005.

[13] Hee Jin Sohn, and Byung Kook Kim, “A Robust Localization Algorithm for Mobile Robots with Laser Range Finders,”in Proceedings of IEEE International Conference on Robotics and Automation, Barcelona, Spain, 2005, pp. 3545-3550.

[14] W. Burgard, A.B. Cremers, D. Fox, D. Hähnel, G. Lakemeyer, D. Schulz, W. Steiner, and S. Thrun., “Experiences with an interactive museum tour-guide robot,” Artificial Intelligence,vol. 114 , Issue 1-2:1-55, 1999.

[15] A. Doucet, J. F. G. de Freitas, and N. J. Gordon, “Sequential Monte Carlo Methods in Practice,” New York: Springer-Verlag, 2001.

[16]J.S. Liu and R. Chen, “Sequential Monte Carlo Methods for Dynamical Systems,”

Journal of the American Statistical Association, vol. 93, pp. 1032-1044, 1998.

[17]P. Jensfelt and H. I. Christensen, “Pose Tracking Using Laser Scanning and Minimalistic Environmental Models,” In Proceedings of IEEE International Conference on Robotics and Automation, Seoul, Korea, 2001, pp. 138-147.

[18]Dongheui Lee, Woojin Chung and Munsang Kim, “Probabilistic Localization of the Service Robot by Map Matching Algorithm,” International Conference on Control, Automation and Systems, Jeonbuk, Korea, 2002.

[19] 邱黃正憲,“多機器人合作感測定位與環境地圖建立,” 國立交通大學電機 與控制工程研究所碩士論文,2003.

[20] 林鎮源, “移動式機器人之行為融合控制器設計,” 國立交通大學電機與控 制工程研究所碩士論文,2005.

[21] 孫柏秋, “基於行為模式之多機器人協調控制,” 國立交通大學電機與控制 工程研究所碩士論文,2005.

[22] Ching-Chih Tsai, Yu-Sheng Huang, Yu-Chiao Wang, Ssu-Min Hu, “Design and Implementation of a Nursing-Care Walking Assistant for the Elderly,”

Proceedings of 2005 CACS Automatic Control Conference, Tainan, Taiwan, Nov 18-19, 2005.