원문정보
초록
영어
This article presents a new structure for solving global positioning system (GPS) outages for long periods without requiring any prior information about the characteristics of the inertial navigation system (INS) and GPS. Kalman filter (KF) is widely used in INS and GPS integration to present a forceful navigation solution by overcoming the GPS outage problems. However, KF is usually criticized for working under predefined models and for its observability problem of hidden state variables, sensor dependency, and linearization dependency. Therefore, this article proposes a dynamic adaptive neuro-fuzzy inference system (DANFIS) to predict the INS error during GPS outages based on the current and previous raw INS data. The proposed integrated system is evaluated using a real field test data. The performance of the proposed technique is also compared with the traditional artificial intelligence (AI) technique and KF. The results showed great improvements in positioning and especially in velocity for MEMS grade IMU and for different length of GPS outages.
목차
1. Introduction
2. Dynamic Adaptive Neuro-fuzzy Inference System
2.1 ANFIS Structure
2.2 Adaptive Fuzzy System Training Algorithm [10, 22]
3. Methodology
3.1 DANFIS Architecture
4. Results and Discussion
5. Conclusions
Acknowledgements
References