Accurate Indoor Positioning Based on Learned Absolute and Relative Models

To improve the accuracy of indoor positioning systems it can be useful to combine different types of sensor data. This paper describes deep learning methods both for estimating absolute positions and for performing pedestrian dead reckoning, and then how to combine the resulting estimates using weighted least squares optimization. The positioning model is based on a custom neural network which uses measurements of received signal strength indication from one instant of time as input. The model for estimating relative positions is on the other hand based on inertial sensors, the accelerometer, magnetometer and gyroscope. The position estimates are then combined using a least squares approach with weights based on the standard deviations of errors in predictions from the used models.