Scholarly record

INTELLIGENT FUSION OF DATA IN A LOW-COST INS/GPS INTEGRATED NAVIGATOR

Teodor Lucian Grigorie

Abstract

The work exposes the design and experimental testing results of a low-cost INS/GPS navigator with a data fusion algorithm based on an adaptive neuro fuzzy inference system (ANFIS). In the paper, the structural design of the MEMS-INS/GPS integrated system mechanism and the training procedure of the fuzzy inference system are firstly exposed. Further, the evaluation with experimental data of the integrated navigator based ANFIS algorithm is presented. The integrated navigator proposed scheme works in two different phases: the training phase and the prediction phase. In the training phase, the GPS data are available and the scheme uses training data packages with ten inputs (the IMU outputs (three accelerometers and three gyros), the components of the INS attitude solution (attitude angles - roll, pitch and yaw), the outage time of GPS signal from the navigator clock) and six outputs (the differences between the components of global position and North-East-Down (NED) speed components from INS and GPS navigation solutions). The experimental model of the MEMS-INS/GPS navigator incorporates three miniaturized inertial sensors (two biaxial gyros and a three-axial accelerometer), a GPS module and a dsPIC microcontroller. The inertial sensors data were acquired with a rate of 100 samples/s, while the GPS receiver provided data once per second. To test the proposed integrated navigator, the hardware structure has been boarded on a testing vehicle. In a first step, the experimentally acquired data were used to tune the ANFIS algorithm, while, at the next steps, an evaluation of the obtained integrated navigator has been performed. Three different scenarios were used: 1) open sky detection, with full time available GPS signal; 2) intermittent GPS signal; 3) blockage of the GPS signal (inertial positioning only).

Publication Impact Profile

• Captures
• Mendeley - Readers: 4

PLUMX see details

DOI resolver: doi.org/10.5593/sgem2019/2.2/s09.022

Publication details

Back to publication list