When considering the proximity environment of a small body, the capability to navigate around it is of paramount importance to enable any onboard autonomous decision-making process. Onboard optical-based navigation is often performed by coupling image processing algorithms with filtering techniques to generate position and velocity estimates, providing compelling navigation performance with cost-effective hardware. These same processes could be addressed with data-driven ones, at the expense of a sufficiently large dataset. To investigate to what extent can these methods substitute traditional ones, in this article, we develop a possible onboard methodology based on segmentation masks, convolutional extreme learning machine architectures, and recurrent neural networks to, respectively, generate simpler image inputs, map single-frame data into position estimates, and process multiple-frame position sequences to generate both position and velocity estimates. Considering the primary of the Didymos binary system as a case study and the possibility to complement optical observations with Light Detection And Ranging (LiDAR) data, we show that recurrent neural networks would bring only limited improvement in position reconstruction for the case considered while they would be beneficial in estimating the velocity, especially when considering complementing LiDAR data.
Onboard State Estimation Around Didymos With Recurrent Neural Networks and Segmentation Maps
IEEE Transactions on Aerospace and Electronic Systems ; 60 , 3 ; 2542-2554
2024-06-01
10597821 byte
Article (Journal)
Electronic Resource
English
Trajectory Options for Hera’s Milani CubeSat Around (65803) Didymos
Springer Verlag | 2021
|Centralized Autonomous Relative Navigation of Multiple Cubesats around Didymos System
Springer Verlag | 2021
|Ground-based radar observations of Didymos
NTRS | 2018
|Co-Orbital Orbits Around the Asteroid 65803 Didymos (1996 GT) (AIAA 2018-0719)
British Library Conference Proceedings | 2018
|