Pose estimation of chaotic motion of Didymos' moon using CNN-based image processing algorithm

Kaluthantrige, Aurelio and Feng, Jinglang and Gil-Fernández, Jesús (2023) Pose estimation of chaotic motion of Didymos' moon using CNN-based image processing algorithm. In: 12th International Conference on Guidance, Navigation & Control Systems (GNC), 2023-06-12 - 2023-06-16.

[thumbnail of Kaluthantrige-etal-ICGNCS-2023-Pose-estimation-of-chaotic-motion-of-Didymos-moon]
Preview
 Text. Filename: Kaluthantrige_etal_ICGNCS_2023_Pose_estimation_of_chaotic_motion_of_Didymos_moon.pdf
Accepted Author Manuscript
Download (1MB)| Preview

Abstract

The Close Observation Phase (COP) is the proximity operation of the European Space Agency (ESA)’s Hera mission with the objective of obtaining high-resolution images of the target asteroid Didymos and its moon Dimorphos. The relative attitude of Dimorphos with respect to the spacecraft is not solved as the implemented feature tracking navigation technique requires closer distances and prior knowledge of the angular velocity of the target. In this work we estimate the continuous six degree of freedom pose (position and attitude) of Dimorphos during the COP using a Convolutional Neural Networks (CNN)-based Image Processing (IP) algorithm. For the attitude, we implement an appearance-based method that consists of two stages. In the first stage, we use CNNs with the images captured by the spacecraft on-board camera to regress a set of keypoints segmenting Dimorphos from its background. In the second stage, we use Neural Networks (NN) to map these keypoints to the four quaternions representing the relative rotation matrix of Dimorphos with respect to the spacecraft. The estimated keypoints are also used to estimate the position of the centroid of Dimorphos and its relative distance with respect to the spacecraft, which together provides the relative position vector of the spacecraft.

CORE (COnnecting REpositories)