Seeing Where to Deploy: Metric RGB-Based Traversability Analysis for Aerial-to-Ground Hidden Space Inspection

TL;DR

This paper introduces a metric RGB-based framework for reconstructing and analyzing terrain to identify safe deployment zones for ground robots from aerial views, enabling efficient inspection of hidden spaces.

Contribution

It presents a novel RGB-based geometric-semantic reconstruction method with an embodied motion prior to recover metric scale without LiDAR, facilitating terrain analysis for deployment decisions.

Findings

Reliable deployment zone identification demonstrated on UAV-UGV platform.

Effective metric reconstruction from RGB data in hidden space scenarios.

Confidence-aware traversability maps enable explicit reachability assessment.

Abstract

Inspection of confined infrastructure such as culverts often requires accessing hidden spaces whose entrances are reachable primarily from elevated viewpoints. Aerial-ground cooperation enables a UAV to deploy a compact UGV for interior exploration, but selecting a suitable deployment region from aerial observations requires metric terrain reasoning involving scale ambiguity, reconstruction uncertainty, and terrain semantics. We present a metric RGB-based geometric-semantic reconstruction and traversability analysis framework for aerial-to-ground hidden space inspection. A feed-forward multi-view RGB reconstruction backbone produces dense geometry, while temporally consistent semantic segmentation yields a 3D semantic map. To enable deployment-relevant measurements without LiDAR-based dense mapping, we introduce an embodied motion prior that recovers metric scale by enforcing consistency between predicted camera motion and onboard platform egomotion. From the metrically grounded reconstruction, we construct a confidence-aware geometric-semantic traversability map and evaluate candidate deployment zones under explicit reachability constraints. Experiments on a tethered UAV-UGV platform demonstrate reliable deployment-zone identification in hidden space scenarios.