Vision Foundation Models for Domain Generalisable Cross-View Localisation in Planetary Ground-Aerial Robotic Teams

TL;DR

This paper introduces a novel deep learning approach for planetary rover localisation in aerial maps, utilizing semantic segmentation, synthetic data, and particle filters for improved accuracy in challenging environments.

Contribution

It proposes a dual-encoder neural network leveraging foundation models and synthetic data to bridge the domain gap for cross-view localisation in planetary robotics.

Findings

Achieves accurate rover localisation over complex trajectories.

Utilizes synthetic data and semantic segmentation to improve real-world performance.

Provides a new dataset of real-world rover trajectories and synthetic image pairs.

Abstract

Accurate localisation in planetary robotics enables the advanced autonomy required to support the increased scale and scope of future missions. The successes of the Ingenuity helicopter and multiple planetary orbiters lay the groundwork for future missions that use ground-aerial robotic teams. In this paper, we consider rovers using machine learning to localise themselves in a local aerial map using limited field-of-view monocular ground-view RGB images as input. A key consideration for machine learning methods is that real space data with ground-truth position labels suitable for training is scarce. In this work, we propose a novel method of localising rovers in an aerial map using cross-view-localising dual-encoder deep neural networks. We leverage semantic segmentation with vision foundation models and high volume synthetic data to bridge the domain gap to real images. We also contribute a new cross-view dataset of real-world rover trajectories with corresponding ground-truth localisation data captured in a planetary analogue facility, plus a high volume dataset of analogous synthetic image pairs. Using particle filters for state estimation with the cross-view networks allows accurate position estimation over simple and complex trajectories based on sequences of ground-view images.