Terrain-Relative Navigation with Neuro-Inspired Elevation Encoding

Kristen Michaelson, Felix Wang, Renato Zanetti

Abstract: Abstract—Terrain-relative autonomous navigation is a challenging task. In traditional approaches, an elevation map is carried onboard and compared to measurements of the terrain below the vehicle. These methods are computationally expensive, and it is impractical to store high-quality maps of large swaths of terrain. In this article, we generate position measurements using NeuroGrid, a recently-proposed algorithm for computing position information from terrain elevation measurements. We incorporate NeuroGrid into an inertial navigation scheme using a novel measurement rejection strategy and online covariance computation. Our results show that the NeuroGrid filter provides highly accurate state information over the course of a long trajectory. Index Terms—kalman filter, inertial navigation, terrain-relative navigation, neuro-inspired
Published in: 2023 IEEE/ION Position, Location and Navigation Symposium (PLANS)
April 24 - 27, 2023
Hyatt Regency Hotel
Monterey, CA
Pages: 851 - 857
Cite this article: Michaelson, Kristen, Wang, Felix, Zanetti, Renato, "Terrain-Relative Navigation with Neuro-Inspired Elevation Encoding," 2023 IEEE/ION Position, Location and Navigation Symposium (PLANS), Monterey, CA, April 2023, pp. 851-857. https://doi.org/10.1109/PLANS53410.2023.10139925
Full Paper: ION Members/Non-Members: 1 Download Credit
Sign In