粒子最佳化與模糊控制於輪型機器人之自動導航應用; Automatic Navigation of a Wheeled Mobile Robot Using Particle Swarm Optimization and Fuzzy Control

NCUIR > College of Electrical Engineering & Computer Science > Graduate Institute of Electrical Engineering > Electronic Thesis & Dissertation > Item 987654321/48459

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/48459

Title:	粒子最佳化與模糊控制於輪型機器人之自動導航應用;Automatic Navigation of a Wheeled Mobile Robot Using Particle Swarm Optimization and Fuzzy Control
Authors:	劉詩群;Shih-Chun Liu
Contributors:	電機工程研究所
Keywords:	自動導航;輪型機器人;模糊控制;粒子最佳化;Automatic Navigation;Particle Swarm Optimization;Fuzzy Control
Date:	2011-07-18
Issue Date:	2012-01-05 14:55:22 (UTC+8)
Abstract:	本文旨在為提供輪型機器人一個適合的自動導航方法，並配合感測器偵測周遭環境建構平面地圖，以使用者決定目標點並經由輪型機器人完成，自動導航的方法根據感測器的不同也會有所差異，如何研究出兼具避障與最短路徑也是目前非常重要的議題粒子最佳化常用於搜尋最佳解的問題，與基因演算法有許多相似之處，但在參數設定與收斂速度上更優異，不需要複雜的數學式也使得此演算法很容易實現在硬體上，本研究以輪型機器人行走所需要的角度與距離長度當作問題的維度，經由不斷的疊代後找出最佳路線；另外針對此導航方法所會遇到的盲點提出利用模糊控制的解決方法，改進輪型機器人在遇到某些特殊狀況時會來回移動的問題。在模擬與實驗中，以軟體模擬所提出的導航方法，設計出許多不同的障礙物場景並且觀察結果，最後再以電腦與輪型機器人完成一個跨平台的架構，驗證此方法的可行性。 This paper develops a approach of Navigation for a wheeled mobile robot(WMR). Next, the local map is constructed by using a sensor.The WMR will arrive at the destination which is assigned by users. Additionally, it is very important how to find the collision-free and the shortest path for the WMR. Particle Swarm Optimization(PSO) is usually applied for optimization problems, but the convergence speed and the parameter setting are better than those of the GA. It’s easy for implementation, and the turn angle and the forward distance as main factors of problem. Finally , the best path after many times of iteration can be obtained. In addition, Fuzzy Conrol is used to solve special condition under which, WMR may be stuck in the same road. In this work, experimental results are given to demonstrate the feasibility of this method
Appears in Collections:	[Graduate Institute of Electrical Engineering] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	587	View/Open

社群 sharing

Loading...