Deep Learning for Spacecraft Pose Estimation from Photorealistic Rendering

Abstract

On-orbit proximity operations in space rendezvous, docking and debris removal require precise and robust 6D pose estimation under a wide range of lighting conditions and against highly textured background, i.e., the Earth. This paper investigates leveraging deep learning and photorealistic rendering for monocular pose estimation of known uncooperative spacecrafts. We first present a simulator built on Unreal Engine 4, named URSO, to generate labeled images of spacecrafts orbiting the Earth, which can be used to train and evaluate neural networks. Secondly, we propose a deep learning framework for pose estimation based on orientation soft classification, which allows modelling orientation ambiguity as a mixture of Gaussians. This framework was evaluated both on URSO datasets and the ESA pose estimation challenge. In this competition, our best model achieved 3rd place on the synthetic test set and 2nd place on the real test set. Moreover, our results show the impact of several architectural and training aspects, and we demonstrate qualitatively how models learned on URSO datasets can perform on real images from space.

* Adding more related work and references

References in corpus (3)

• An Analysis of Deep Neural Network Models for Practical Applications
• DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks
• Deep-6DPose: Recovering 6D Object Pose from a Single RGB Image

Cited by in corpus (4)

• Satellite Pose Estimation Challenge: Dataset, Competition Design and Results
• A Survey on Deep Learning-Based Monocular Spacecraft Pose Estimation: Current State, Limitations and Prospects
• Accelerating AI and Computer Vision for Satellite Pose Estimation on the Intel Myriad X Embedded SoC
• Hardware-accelerated Mars Sample Localization via deep transfer learning from photorealistic simulations