DeePOE: Deep Learning for Position and Orientation Estimation

We propose a deep learning framework for solving the problem of position and orientation estimation (DeePOE) of a radio frequency (RF) transmitter using the in-phase
$(I)$
and quadrature-phase
$(Q)$
components of the RF signal data. Our goal is to demonstrate a proof of concept system with an end-to-end implementation in order to overcome the shortcomings of state-of-the-art joint position and orientation estimation systems. The proposed DeePOE framework consists of a convolutional neural network (CNN) which is designed to exploit latent features present within the received raw I/Q signal data. This enables receivers equipped with the DeePOE framework to predict the position and orientation of a transmitter, relative to itself in a predefined coordinate system, solely from physical layer information. DeePOE jointly optimizes the position and orientation estimation objectives using transfer learning, iteratively over the training epochs. In order to validate and refine the DeePOE framework, we perform real-world (indoor and outdoor) experiments using 16 GB of raw I/Q data collected with directional emitters placed in various orientations and at different distances (positions) from both directional and omnidirectional receivers. The framework achieves on average a F
1
score of 0.922 for the task of predicting 12 orientations from the data collected using an omnidirectional antenna. It also yields F
1
score of 0.847 for data collected with a directional antenna which involves predicting 48 orientations. DeePOE achieves on average F
1
score of 0.963 for predicting the transmitter position with respect to the receiver placed at a known location, for all the cases.