MAGINS: Neural Network Inertial Navigation System Corrected by Magnetic Information

Abstract

Recently, the neural network has become a popular technology for pedestrian inertial navigation to avoid the errors caused by the integral part of traditional inertial navigation system and also performs better than Pedestrian Dead Reckoning(PDR). However, researchers who leverage the neural network all discard the magnetic information due to the instability of magnetic field. On account of low-cost inertial measurement unit(IMU), relying on the gyroscope and the accelerometer only will inevitably produce horizontal angular deviation. This small angular deviation will be magnified as the trajectory length increases, and finally, cause positioning drift. Through many experiments and analyses, we discovered that there is a correlation between the magnetic information and the pedestrian’s body direction under a stable magnetic field. Based on the discovery, MAGINS, a neural network inertial navigation system corrected by magnetic information was designed. A data set of motion information including IMU data and real positions was created and utilized to train a network model as the basis of our system. For the sake of the stable and available magnetic information, we designed an algorithm to quantitatively detect the stability of the magnetic field. The heading of navigation can be corrected according to the stability and the correlation mentioned above. The experiment result shows that MAGINS can detect the stability of the magnetic field precisely, and correct the heading properly since the magnetic information will not produce accumulated errors. The positioning effect of MAGINS is better than other pedestrian inertial navigation systems only based on neural network.