Abstract
Terrain-aided navigation (TAN) is a technology that estimates the position of the vehicle by comparing the altitude measured by an altimeter and height from the digital elevation model (DEM). The particle filter (PF)-based TAN has been commonly used to obtain stable real-time navigation solutions in cases where the unmanned aerial vehicle (UAV) operates at a high altitude. Even though TAN performs well on rough and unique terrains, its performance degrades in flat and repetitive terrains. In particular, in the case of PF-based TAN, there has been no verified technique for deciding its terrain validity. Therefore, this study designed a Rao-Blackwellized PF (RBPF)-based TAN, used long short-term memory (LSTM) networks to endure flat and repetitive terrains, and trained the noise covariances and measurement model of RBPF. LSTM is a modified recurrent neural network (RNN), which is an artificial neural network that recognizes patterns from time series data. Using this, this study tuned the noise covariances and measurement model of RBPF to minimize the navigation errors in various flight trajectories. This paper designed a TAN algorithm based on combining RBPF and LSTM and confirmed that it can enable a more precise navigation performance than conventional RBPF based TAN through simulations.
Highlights
Aircraft safety requires highly reliable navigation information
This study aimed to suggest a design with more improved performance than the conventional Rao-Blackwellized PF (RBPF) based terrain-aided navigation (TAN) in various terrains by utilizing deep learning techniques that use time series data, which are called long short-term memory (LSTM) networks
To verify the design of the learned LSTM-RBPF, this study applied the design to new test data, To
Summary
Aircraft safety requires highly reliable navigation information. Traditionally, the inertial navigation system and global positioning system (INS/GPS) integrated navigation algorithm has been widely used [1]. GPS cannot operate independently and is vulnerable to jamming. To overcome such weakness, the terrain-aided navigation (TAN) techniques can be used. TAN is a navigation technology that estimates the aircraft’s precise position by comparing the altitude measured by an altimeter with the uploaded digital elevation data (DEM). To acquire precise position information using TAN, nonlinear estimation problems must be solved in real-time. The extended Kalman filter (EKF)-based TAN algorithms have solved these problems through regional linearization [2]. Because of the highly nonlinear characteristics of the terrain, the EKF-based TAN algorithm can diverge due to linearization. Recent studies have suggested that the TAN techniques that use the Bayesian estimate method, such as particle filter (PF) and point mass filter (PMF), can prevent the problem [3,4,5,6,7]
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call