Adaptive tuning of a Kalman filter via neural network for integrated global positioning/inertial navigation systems
碩士 === 明志科技大學 === 機電工程研究所 === 97 === This study integrates global positioning system (GPS) and inertial navigation system (INS) by means of Kalman filtering (KF). Due to inadequacy related to KF-based GPS/INS integration, relatively poor positioning accuracy could be resulted during long GPS outages...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | zh-TW |
| Published: |
2009
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/66885553926385469968 |
| Summary: | 碩士 === 明志科技大學 === 機電工程研究所 === 97 === This study integrates global positioning system (GPS) and inertial navigation system (INS) by means of Kalman filtering (KF). Due to inadequacy related to KF-based GPS/INS integration, relatively poor positioning accuracy could be resulted during long GPS outages. To overcome this problem, covariance matrices that are applied in KF and associated with the system noise are tuned over time via neural network method. Therefore, the study highlights the use of neural network techniques to the adaptation of the initial statistical assumption of the KF caused by possible changes in sensor noise characteristics. The proposed system is implemented on a vehicle so that the desired positioning accuracy can be examined. It is found that the adaptive mechanism can help improve the positioning accuracy of the integrated GPS/INS system during long GPS outages.
|
|---|