MonoSpheres: Large-Scale Monocular SLAM-Based UAV Exploration through Perception-Coupled Mapping and Planning

TL;DR

This paper introduces a monocular vision-based exploration method enabling UAVs to safely and efficiently explore large-scale 3D environments by addressing monocular SLAM challenges in mapping and planning.

Contribution

It presents a novel approach that explicitly accounts for monocular SLAM properties in both mapping and planning, enabling large-scale autonomous exploration with a single camera.

Findings

First monocular exploration method demonstrated in real-world outdoor environments.

Effective handling of sparse depth data and large depth uncertainty.

Extensive validation in diverse real-world and simulated environments.

Abstract

Autonomous exploration of unknown environments is a key capability for mobile robots, but it is largely unsolved for robots equipped with only a single monocular camera and no dense range sensors. In this paper, we present a novel approach to monocular vision-based exploration that can safely cover large-scale unstructured indoor and outdoor 3D environments by explicitly accounting for the properties of a sparse monocular SLAM frontend in both mapping and planning. The mapping module solves the problems of sparse depth data, free-space gaps, and large depth uncertainty by oversampling free space in texture-sparse areas and keeping track of obstacle position uncertainty. The planning module handles the added free-space uncertainty through rapid replanning and perception-aware heading control. We further show that frontier-based exploration is possible with sparse monocular depth data when parallax requirements and the possibility of textureless surfaces are taken into account. We evaluate our approach extensively in diverse real-world and simulated environments, including ablation studies. To the best of the authors' knowledge, the proposed method is the first to achieve 3D monocular exploration in real-world unstructured outdoor environments. We open-source our implementation to support future research.