Deep Monocular Hazard Detection for Safe Small Body Landing
This addresses the need for safer and more efficient robotic landings on small bodies by reducing reliance on costly a priori maps, though it is incremental as it builds on existing deep learning techniques.
The paper tackled the problem of hazard detection for small body landings by proposing a deep semantic segmentation approach that predicts landing safety from a single monocular image, achieving precise and accurate performance on real OSIRIS-REx mission imagery.
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.