Automatic Estimation of Inertial Navigation System Errors for Global Positioning System Outage Recovery

Abstract

This article presents an alternative approach of solving global positioning system (GPS) outages without requiring any prior information about the characteristics of the inertial navigation system (INS) and GPS sensors. INS can be used as a standalone system to bridge the outages during GPS signal loss. Kalman filter (KF) is widely used in INS and GPS integration to present a forceful navigation solution by overcoming the GPS outage problems. Unfortunately, KF is usually criticized for working under predefined models and for its observability problem of hidden state variables, sensor dependency, and linearization dependency. This approach utilizes a genetic neuro-fuzzy system (GANFIS) to predict the INS position and velocity errors during GPS signal blockages suitable for real-time application. The proposed model is able to deal with noise and disturbances in the GPS and INS output data in different dynamic environments compared to other traditional filtering algorithms such as the neural network and neuro fuzzy. Real field test results using the microelectro-mechanical system grade inertial measurement unit with an integrated GPS shows a significant improvement obtained from the integrated GPS/INS system using the GANFIS module compared to traditional methods such as Kalman filtering, particularly during long GPS satellite signal blockage.

Evolutionary optimization in ANFIS for intelligent navigation system

“…Equation (1) can be represented as a feed-forward neural network, which is termed as ANFIS. This connectionist model combines the approximate reasoning of fuzzy logic into a neural network structure [8].…”

“…However, the accuracy of INS degrades with time due to wear and tear of mechanical sensors that exhibit long term error growth [2,3].Both the navigation systems used are subjected to certain errors as mentioned above, thus integration of data from both the systems will provide a better performance than the performance of those as a stand-alone system. The values of GPS can be used to estimate the error in INS with which the position can be estimated during GPS outages [8].…”

Intelligently tuned wavelet parameters for GPS/INS error estimation

“…Utilizing this method ensures that the new population will contain chromosomes with better fitness values than the worst individual in the old population. This permutation will reduce the iteration required for the learning process and ensure good guidance in the complex and nonlinear search space [23,24] . Furthermore, the two best parents from the old population will be copied into the next generation without performing any additional operations to increase the probability of obtaining best fitness values and prevent the learning process from becoming worse compared with that of the previous generation.…”

A Novel Hybrid Approach to Deal with DVL Malfunctions for Underwater Integrated Navigation Systems

“…This kind of approaches is cost saving, but there is the potential risk of cross contamination. There are also other researchers working to find a replacement for the KF [22][23][24][25], and various models have been built to predict the errors of the reference system. Semeniuk and Noureldin [23] proposed an artificial-intelligence-based segmented forward predictor to overcome situations of GPS satellite signals blockage.…”

“…By employing radial basis function neural networks, the predictor provides the INS position and velocity errors. Hasan et al [24] introduced a genetic neuro-fuzzy system to predict the INS errors during the GPS failures. These intelligent algorithms can solve sensor failures without requiring any prior information about the characteristics of the sensors.…”