Deep Monocular Hazard Detection for Safe Small Body Landing

TL;DR

This paper introduces a deep learning-based safety mapping method for small body landings that predicts landing safety directly from a single image, reducing dependence on detailed pre-existing terrain maps.

Contribution

It presents a novel safety mapping approach using deep semantic segmentation on monocular images, enabling real-time hazard detection without high-fidelity prior maps.

Findings

Achieved precise safety mapping on real OSIRIS-REx imagery.

Reduced reliance on extensive pre-mission terrain mapping.

Demonstrated effectiveness in small body landing scenarios.

Abstract

Hazard detection and avoidance is a key technology for future robotic small body sample return and lander missions. Current state-of-the-practice methods rely on high-fidelity, a priori terrain maps, which require extensive human-in-the-loop verification and expensive reconnaissance campaigns to resolve mapping uncertainties. We propose a novel safety mapping paradigm that leverages deep semantic segmentation techniques to predict landing safety directly from a single monocular image, thus reducing reliance on high-fidelity, a priori data products. We demonstrate precise and accurate safety mapping performance on real in-situ imagery of prospective sample sites from the OSIRIS-REx mission.