碩士 / 國立臺灣海洋大學 / 電機工程學系 / 104 / The thesis aims to develop an indoor image-code-based localization system. The idea differs from some currently existing systems (such as commercial sweeping robots) using tags on the ceiling to locate, in that we set code image on the ground. As long as the system running on the coded-area, it can locate itself and gain the orientation data by capturing the image of ground and analyze it. Compared to the sweeping robots using the ceiling tags, we can lower the possibility of temporary localization loss due to blocking obstacles (such as tables and chairs, etc).
As system starts running, the self-designed light control device will adjust the illumination, use camera to catch the image and transfer to Raspberry Pi for image processing. After removing certain noise in the image, the designed code-reading algorithm is used to obtain the coordinate of its position. Furthermore, based-on the localization methodology, we can navigate a robot. For navigation purposes, when the robot receives the coordinate of the next destination, it will analyze the relation between target point and starting point to get the navigation angle and distance. Finally the planning path algorithm will drive servo to reach the goal.
| Identifer | oai:union.ndltd.org:TW/104NTOU5442061 |
| Date | January 2016 |
| Creators | Hung, Sheng-Hsiang, 洪聖翔 |
| Contributors | Cheng, Chih-Yung, 鄭智湧 |
| Source Sets | National Digital Library of Theses and Dissertations in Taiwan |
| Language | zh-TW |
| Detected Language | English |
| Type | 學位論文 ; thesis |
| Format | 52 |
Page generated in 0.0161 seconds