A neural-KF hybrid sensor fusion scheme for INS/GPS/odometer integrated land vehicular navigation system

Yung Cheng Lin, Yun Wen Huang, Kai-Wei Chiang

研究成果: Paper同行評審

摘要

Integrated GPS/INS systems provide an enhanced navigation system that has superior performance in comparison with either system operating in stand-alone mode as it can overcome each of their limitations. The high cost and government regulations prevent the wider inclusion of high quality IMUs to augment GPS as a commercialized navigation system in many navigation applications. The progress in MEMS technology enables complete inertial units on a chip, composed of multiple integrated MEMS accelerometers and gyroscopes. In addition to their compact and portable size, the price of MEMS based is far less than those high quality IMUs as well, however, due to the lightweight and fabrication process, MEMS sensors have large bias instability and noise, which consequently affect the obtained accuracy from MEMS-based IMUs. Introducing auxiliary velocity update in the body frame, (e.g. non-holonomic constraint and odometer signal) is an option to solve the problem. The Kalman filter approach has been widely recognized as the standard optimal estimation tool for current INS/GPS integration scheme, however, it does have limitations, which have been reported by several researchers. Consequently, the development of alternative INS/GPS integration scheme has received more attention and the common goal is to reduce the impact of remaining limiting factors and improve the positioning accuracy and attitude accuracy during GPS outage. Artificial intelligence (AI), also known as machine intelligence, is defined as the intelligence exhibited by anything manufactured (i.e. artificial) by humans or other sentient beings or systems. The goal of applying artificial intelligent technologies is to provide intelligence and robustness in the complex and uncertain systems. Indeed, the incorporation of AI techniques in the navigation applications becomes necessary due to the limitations of conventional Kalman filter approach. Therefore, this article explores the idea of incorporating different artificial intelligent techniques to develop an alternative multi-sensor data fusion scheme for MEMS/GPS/Odometer integrated system to overcome the limitations of conventional approaches and enhance the accuracy of attitude estimation.

原文English
頁面2174-2181
頁數8
出版狀態Published - 2006 十二月 1
事件Institute of Navigation - 19th International Technical Meeting of the Satellite Division, ION GNSS 2006 - Fort Worth, TX, United States
持續時間: 2006 九月 262006 九月 29

Other

OtherInstitute of Navigation - 19th International Technical Meeting of the Satellite Division, ION GNSS 2006
國家/地區United States
城市Fort Worth, TX
期間06-09-2606-09-29

All Science Journal Classification (ASJC) codes

  • 電氣與電子工程
  • 電腦科學應用
  • 軟體

指紋

深入研究「A neural-KF hybrid sensor fusion scheme for INS/GPS/odometer integrated land vehicular navigation system」主題。共同形成了獨特的指紋。

引用此