Title
From monocular SLAM to autonomous drone exploration
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 semidense 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 semidense monocular SLAM system into account. In experiments, we demonstrate our vision-based autonomous navigation and exploration system with a Parrot Bebop MAV.
Year
DOI
Venue
2017
10.1109/ECMR.2017.8098709
2017 European Conference on Mobile Robots (ECMR)
Keywords
Field
DocType
autonomous drone exploration,microaerial vehicles,MAVs,power capacity,autonomous navigation,use sensory equipment,low- power consuming,low-cost consumer-grade quadrocopter,monocular camera,navigation system,LSD-SLAM,MAV trajectory,semidense reconstruction,high gradient pixels,dense map information,obstacle mapping,exploration approach,semidense monocular SLAM system,exploration system,Parrot Bebop MAV
Computer vision,Obstacle,Computer science,Simulation,Visualization,Navigation system,Pixel,Drone,Artificial intelligence,Simultaneous localization and mapping,Trajectory,Payload
Conference
ISBN
Citations 
PageRank 
978-1-5386-1097-8
2
0.37
References 
Authors
14
5
Name
Order
Citations
PageRank
Lukas von Stumberg1203.70
Vladyslav C. Usenko2528.53
Jakob Engel390630.16
Jörg Stückler462446.80
Daniel Cremers58236396.86