碩士 / 國立成功大學 / 航空太空工程學系碩博士班 / 100 / Subject：Navigation Using SLAM Vision Technology
Student：Ken-Yen Lee
Advisor：Jiun-Haur Tarn
This thesis, does research about the solution for the navigation problem in mobile robotics by adopting Simultaneous Localization and Mapping (SLAM) algorithm. The algorithm uses only a single camera without odometry information. Estimations of vehicle motion and landmarks’ bearings are computed within a standard Extended Kalman Filter frame work. For prediction, IMU information is utilized to propagate the nonlinear vehicle kinematic equations. And the innovations are obtained from the differences between predictions and the measured landmarks’ bearings. Therefore, the proposed SLAM algorithms can be used as a navigation solution when GPS service is degraded or temporarily unavailable. For real-time implementation of the adopted MonoSLAM, we put together a C++ program with graphical user interface. In which we use library from OpneGL for graphical object. Also the Harris Corner Detection and Lucas-Kanade feature tracking algorithm from OpenCV library are integrated for keeping correct landmark correspondences as the vehicle moves through the scene. The proposed SLAM programs is simulated on a table-top personal computer, and subsequently tested in an open room, then an outdoor environment. For tests performed in the outdoor environment, vehicle trajectories from SLAM algorithms are compared with the on-board GPS information and excel.
Keyword：SLAM, Visual System, Feature Tracking.
| Identifer | oai:union.ndltd.org:TW/100NCKU5295030 |
| Date | January 2012 |
| Creators | Ken-YenLee, 李庚諺 |
| Contributors | Jiun-Haur Tarn, 譚俊豪 |
| Source Sets | National Digital Library of Theses and Dissertations in Taiwan |
| Language | zh-TW |
| Detected Language | English |
| Type | 學位論文 ; thesis |
| Format | 77 |
Page generated in 0.0193 seconds