Please use this identifier to cite or link to this item:
標題: 結合行為成本與路徑長度之最佳化路徑設計
Optimal Path-planning Using the Behavior Cost and the Path Length
作者: 陳威志
Chen, Wei-Zhi
關鍵字: Optimal Path-planning
Behavior Cost
Path Length
Euclidean distance
出版社: 電機工程學系所
引用: [1] P. E. Hart, N. J. Nilsson, and B. Raphael, ”A formal basis for the heuristic determination of minimum cost path,” IEEE Trans. Syst. Sci.Cybern., vol. SSC-4, no. 2,pp. 100-107,Jul. 1968. [2] C. W. Warren, ”Fast path planning using modified a* method,” in Proc.IEEE Int. Conf. Robotics and Automation, Atlanta, GA, pp.662-667, May 1993 [3] J. C. Latombe, Robot Motion Planning. Boston, MA:Kluwer,1991 [4] O. Takahashi and R. J. Schilling, “Motion planning in a plane using generalized voronoi diagrams,” IEEE Trans. Robot. Autom., vol. 5, no.2, pp. 143-150, Apr. 1989. [5] O. Khatib, “Real-time obstacle avoidance for manipulators and mobile robots,” Int. J. Rob. Res.,vol.5, no.1 ,pp. 90-98, 1986. [6] K. P. Valavanis, T. Hebert, R.Kolluru, N. Tsourveloudis, “Mobile robot navigation in 2-d dynamic environments using an electrostatic potential field,” IEEE Trans. Syst., Man, Cybern. A, Syst., Humans, vol.30, no.2, pp.187-196, Mar. 2000. [7] Allan R. Willms, Simon X. Yang,”An efficient dynamic system for real-time robot-path planning,” IEEE Trans. Syst., Man, Cybern. B, Cybern, vol.36, no.4, August 2006. [8] SUBBARAO KAMBHAMPATI, LARRY S. DAVIS,”Multiresolution Path Planning for Moble Robots,” IEEE Trans. Robot. Autom., vol. RA-2, no.3, Sep. 1986.
摘要: 在自走機器人的應用中,路徑設計為一重要的研究主題。本論文結合行為成本函數與路徑成本函數作為最佳化路徑之總成本,以此希望能使機器人達到我們所希望的行為模式:沿著牆壁一固定距離行走,並閃過障礙物,到達目標地點。首先架構出欲操作機器人之環境地圖,再利用多重解析方式取得一初始路徑。利用此初始路徑,我們可在原解析度的圖中設定一帶狀區域,再於其中得出我們所想要的最佳路徑,以有效降低計算量
Path planning is an important research topic in the autonomous robotapplications. In this thesis, the path is obtained by optimizing the cost function which is composed of the cost of the length of the path and the cost of the desired behavior. It is assumed that the desired behavior of the robot is wall following with obstacle avoiding. First, a map is constructed from theoperational environment. The cost of the desired behavior can then be assigned.A multi-resolution scheme is adopted in finding the optimal path. A map with alower resolution is used to acquire a initial path. Then the final path can be found within a band containing the initial path with the original fine resolution.
其他識別: U0005-2708200721075900
Appears in Collections:電機工程學系所



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