State Estimation for HALE UAVs With Deep-Learning-Aided Virtual AOA/SSA Sensors for Analytical Redundancy

Abstract

High-altitudelong-endurance (HALE) unmanned aerial vehicles (UAVs) are employed in a variety of fields because of their ability to fly for a long time at high altitudes, even in the stratosphere. Two paramount concerns exist: enhancing their safety during long-term flight and reducing their weight as much as possible to increase their energy efficiency based on analytical redundancy approaches. In this letter, a novel deep-learning-aided navigation filter is proposed, which consists of two parts: an end-to-end mapping-based synthetic sensor measurement model that utilizes long short-term memory (LSTM) networks to estimate the angle of attack (AOA) and sideslip angle (SSA) and an unscented Kalman filter for state estimation. Our proposed method can not only reduce the weight of HALE UAVs but also ensure their safety by means of an analytical redundancy approach. In contrast to conventional approaches, our LSTM-based method achieves better estimation by virtue of its nonlinear mapping capability.