Path Planning For A Mobile Robot Using Ant Colony Optimization
碩士 === 明志科技大學 === 電機工程研究所 === 100 === Abstract This thesis aims to find an optimal path planning strategy for mobile robot by using the Ant Colony Optimization (ACO) algorithms. First, the obstacle existed between the starting point and the end point in a known environment is recognized, then apply...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2012
|
Online Access: | http://ndltd.ncl.edu.tw/handle/33325901616048423018 |
id |
ndltd-TW-099MIT00442023 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-099MIT004420232015-10-13T20:51:35Z http://ndltd.ncl.edu.tw/handle/33325901616048423018 Path Planning For A Mobile Robot Using Ant Colony Optimization 應用蟻群演算法於移動式機器人之路徑規劃 Peng, Cisiang 彭啟翔 碩士 明志科技大學 電機工程研究所 100 Abstract This thesis aims to find an optimal path planning strategy for mobile robot by using the Ant Colony Optimization (ACO) algorithms. First, the obstacle existed between the starting point and the end point in a known environment is recognized, then apply the ACO to search optimal path with the capability to avoid collision with the obstacle for a mobile robot. From comparisons between the ACO algorithms and the Genetic Algorithms (GA), it can be found that the ACO algorithms provide better convergence in searching the optimal path. The Sentinel Robot and Constellation Navigated System are combined to confirm the simulated path planning solution, and ensure the robot to move according to the optimal path correctly and demonstrate the ability to avoid the obstacle smoothly. The goal of economizing the energy consumption and enhancing the searching efficiency of an optimal path for a mobile robot can then be reached. Keywords: Ant colony optimization, Genetic algorithms, optimal path planning, mobile robot. Chang, Chiader Lin, Sijhao 張嘉德 林錫昭 2012 學位論文 ; thesis 77 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 明志科技大學 === 電機工程研究所 === 100 === Abstract
This thesis aims to find an optimal path planning strategy for mobile robot by using the Ant Colony Optimization (ACO) algorithms. First, the obstacle existed between the starting point and the end point in a known environment is recognized, then apply the ACO to search optimal path with the capability to avoid collision with the obstacle for a mobile robot. From comparisons between the ACO algorithms and the Genetic Algorithms (GA), it can be found that the ACO algorithms provide better convergence in searching the optimal path. The Sentinel Robot and Constellation Navigated System are combined to confirm the simulated path planning solution, and ensure the robot to move according to the optimal path correctly and demonstrate the ability to avoid the obstacle smoothly. The goal of economizing the energy consumption and enhancing the searching efficiency of an optimal path for a mobile robot can then be reached.
Keywords: Ant colony optimization, Genetic algorithms, optimal path planning, mobile robot.
|
author2 |
Chang, Chiader |
author_facet |
Chang, Chiader Peng, Cisiang 彭啟翔 |
author |
Peng, Cisiang 彭啟翔 |
spellingShingle |
Peng, Cisiang 彭啟翔 Path Planning For A Mobile Robot Using Ant Colony Optimization |
author_sort |
Peng, Cisiang |
title |
Path Planning For A Mobile Robot Using Ant Colony Optimization |
title_short |
Path Planning For A Mobile Robot Using Ant Colony Optimization |
title_full |
Path Planning For A Mobile Robot Using Ant Colony Optimization |
title_fullStr |
Path Planning For A Mobile Robot Using Ant Colony Optimization |
title_full_unstemmed |
Path Planning For A Mobile Robot Using Ant Colony Optimization |
title_sort |
path planning for a mobile robot using ant colony optimization |
publishDate |
2012 |
url |
http://ndltd.ncl.edu.tw/handle/33325901616048423018 |
work_keys_str_mv |
AT pengcisiang pathplanningforamobilerobotusingantcolonyoptimization AT péngqǐxiáng pathplanningforamobilerobotusingantcolonyoptimization AT pengcisiang yīngyòngyǐqúnyǎnsuànfǎyúyídòngshìjīqìrénzhīlùjìngguīhuà AT péngqǐxiáng yīngyòngyǐqúnyǎnsuànfǎyúyídòngshìjīqìrénzhīlùjìngguīhuà |
_version_ |
1718051514801455104 |