From Monocular SLAM to Autonomous Drone Exploration

TL;DR

This paper presents a vision-based autonomous navigation and exploration system for micro aerial vehicles using a monocular camera and LSD-SLAM, enabling low-weight, low-power MAVs to navigate and explore environments in real-time.

Contribution

It introduces an obstacle mapping and exploration method tailored for semi-dense monocular SLAM, addressing texture-less areas where depth is not directly observed.

Findings

Successful autonomous navigation with a Parrot Bebop MAV

Real-time semi-dense environment reconstruction

Effective obstacle avoidance in texture-less regions

Abstract

Micro aerial vehicles (MAVs) are strongly limited in their payload and power capacity. In order to implement autonomous navigation, algorithms are therefore desirable that use sensory equipment that is as small, low-weight, and low-power consuming as possible. In this paper, we propose a method for autonomous MAV navigation and exploration using a low-cost consumer-grade quadrocopter equipped with a monocular camera. Our vision-based navigation system builds on LSD-SLAM which estimates the MAV trajectory and a semi-dense reconstruction of the environment in real-time. Since LSD-SLAM only determines depth at high gradient pixels, texture-less areas are not directly observed so that previous exploration methods that assume dense map information cannot directly be applied. We propose an obstacle mapping and exploration approach that takes the properties of our semi-dense monocular SLAM system into account. In experiments, we demonstrate our vision-based autonomous navigation and exploration system with a Parrot Bebop MAV.