基於分類之避障路徑規劃與實現

Classification based Obstacle Avoidance Path Planning and Implementation

馬志豪(Jhih-Hao Ma)

指導教授 ： 楊智旭 ； 楊棧雲

淡江大學/工學院/機械與機電工程學系碩士班/碩士(2010年)

https://doi.org/10.6846/TKU.2010.00850

摘要

本研究之目的是以分類理論為基礎，來建立一個機器人之避障路徑規劃與實現，藉由所研發之安全平滑路徑規畫為基礎，以樂高機器人驗證所發展的路徑規畫及實際導航。本研究之路徑規畫結合Voronoi結構劃分與支向機分類器，使規劃路徑具備安全平滑之特性。系統藉由影像擷取、影像處理、路徑規劃、配合模糊回授控制進行機器人導航，用以驗證各種障礙物配置之變化，並藉以探討系統各項參數之影響。實驗顯示我們所發展之即時系統成功地反應不同障礙物之變化，找出最佳之安全平滑路徑，所發展之機器人控制也盡可能地適應所規畫之路徑，從起點走向終點，最後以反覆試驗藉統計學之ANOVA分析其在各條件下各導航結果之差異，以探討系統重現性，經實作測試，結果成效良好。

關鍵字

支向機 ； Voronoi結構劃分 ； 路徑規劃 ； 導航機器人 ； 模糊控制

並列摘要

The path planning of mobile robots to avoid obstacles in the configuration space is an important topic in the field of robotics. Merging Voronoi tessellation and support vector machine (SVM), we have developed theoretically a method to provide an optimized safe and smooth path in our previous study. The paper re-examines the method and constructs practically a framework of path following system for a mobile robot to realize and implement the theoretical development. The system comprises sub-systems of image acquisition, and processing, path planning, and fuzzy inference for feedback calibration of the path following of the mobile robot. With the small scale real system, experiments can take place practically for validation. The paper describes mainly the establishment of the real system. Plentiful experimental results are also included in the paper for evidence of the success of the proposed developments, not only the algorithmic path planning but also the applied robotic path following. Despite the changes of the obstacle configuration, the mobile robot demonstrates the excellent capability of reaching its goal by following the planned path safely and smoothly. A series of quantitative analysis is then followed for investigating influence of the system factors using ANOVA analysis.

並列關鍵字

SVM ； Voronoi Tessellation ； Path Planning ； Guiding Robot ； Fuzzy Control

參考文獻

[9] 周峰毅，安全平滑之機器人路徑規劃—基於大邊限支向機的研究，碩士論文，淡江大學機械與機電學系，民國九十六年

[44] 蔡爾傑，兩輪移動機器人之控制與驅動設計，淡江大學機械與機電工程學系碩士論輪，民國九十四年六月

[1] A. Zelinsky and I. Dowson, “Continuous smooth path execution for an autonomous guided vehicle,” TENCON '92. Technology Enabling Tomorrow : Computers, Communications and Automation towards the 21st Century, 1992 IEEE Region 10 International Conference, 871-875 vol. 2, Melbourne. 11-13 Nov., Australia, 1992.

[2] T. Fraichard and M. Ahuactzin, “Smooth path planning for cars,” ICRA 2001: 3722-3727, Proceedings of the 2001 IEEE International Conference on Robotics and Automation, ICRA 2001, May 21-26, Seoul, Korea, 2001.

[4] V. N. Vapnik, “Statistical Learning Theory,” John Wiley & Sons, New York, 1998.