Autonomous visual mapping and exploration with a micro aerial vehicle

Lionel Heng, Dominik Honegger, Gim Hee Lee, Lorenz Meier, Petri Tanskanen, Friedrich Fraundorfer, Marc Pollefeys

Research output: Contribution to journalArticle

Abstract

Cameras are a natural fit for micro aerial vehicles (MAVs) due to their low weight, low power consumption, and two-dimensional field of view. However, computationally-intensive algorithms are required to infer the 3D structure of the environment from 2D image data. This requirement is made more difficult with the MAV's limited payload which only allows for one CPU board. Hence, we have to design efficient algorithms for state estimation, mapping, planning, and exploration. We implement a set of algorithms on two different vision-based MAV systems such that these algorithms enable the MAVs to map and explore unknown environments. By using both self-built and off-the-shelf systems, we show that our algorithms can be used on different platforms. All algorithms necessary for autonomous mapping and exploration run on-board the MAV. Using a front-looking stereo camera as the main sensor, we maintain a tiled octree-based 3D occupancy map. The MAV uses this map for local navigation and frontier-based exploration. In addition, we use a wall-following algorithm as an alternative exploration algorithm in open areas where frontier-based exploration under-performs. During the exploration, data is transmitted to the ground station which runs large-scale visual SLAM. We estimate the MAV's state with inertial data from an IMU together with metric velocity measurements from a custom-built optical flow sensor and pose estimates from visual odometry. We verify our approaches with experimental results, which to the best of our knowledge, demonstrate our MAVs to be the first vision-based MAVs to autonomously explore both indoor and outdoor environments.

LanguageEnglish
Pages654-675
Number of pages22
JournalJournal of field robotics
Volume31
Issue number4
DOIs
StatusPublished - 2014

Fingerprint

Antennas
Micro air vehicle (MAV)
Cameras
Optical flows
Sensors
State estimation
Velocity measurement
Program processors
Navigation
Electric power utilization
Planning

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science Applications

Cite this

Heng, L., Honegger, D., Lee, G. H., Meier, L., Tanskanen, P., Fraundorfer, F., & Pollefeys, M. (2014). Autonomous visual mapping and exploration with a micro aerial vehicle. Journal of field robotics, 31(4), 654-675. DOI: 10.1002/rob.21520

Autonomous visual mapping and exploration with a micro aerial vehicle. / Heng, Lionel; Honegger, Dominik; Lee, Gim Hee; Meier, Lorenz; Tanskanen, Petri; Fraundorfer, Friedrich; Pollefeys, Marc.

In: Journal of field robotics, Vol. 31, No. 4, 2014, p. 654-675.

Research output: Contribution to journalArticle

Heng, L, Honegger, D, Lee, GH, Meier, L, Tanskanen, P, Fraundorfer, F & Pollefeys, M 2014, 'Autonomous visual mapping and exploration with a micro aerial vehicle' Journal of field robotics, vol 31, no. 4, pp. 654-675. DOI: 10.1002/rob.21520
Heng L, Honegger D, Lee GH, Meier L, Tanskanen P, Fraundorfer F et al. Autonomous visual mapping and exploration with a micro aerial vehicle. Journal of field robotics. 2014;31(4):654-675. Available from, DOI: 10.1002/rob.21520
Heng, Lionel ; Honegger, Dominik ; Lee, Gim Hee ; Meier, Lorenz ; Tanskanen, Petri ; Fraundorfer, Friedrich ; Pollefeys, Marc. / Autonomous visual mapping and exploration with a micro aerial vehicle. In: Journal of field robotics. 2014 ; Vol. 31, No. 4. pp. 654-675
@article{5f7363245bb1456f8392780b73bf1402,
title = "Autonomous visual mapping and exploration with a micro aerial vehicle",
abstract = "Cameras are a natural fit for micro aerial vehicles (MAVs) due to their low weight, low power consumption, and two-dimensional field of view. However, computationally-intensive algorithms are required to infer the 3D structure of the environment from 2D image data. This requirement is made more difficult with the MAV's limited payload which only allows for one CPU board. Hence, we have to design efficient algorithms for state estimation, mapping, planning, and exploration. We implement a set of algorithms on two different vision-based MAV systems such that these algorithms enable the MAVs to map and explore unknown environments. By using both self-built and off-the-shelf systems, we show that our algorithms can be used on different platforms. All algorithms necessary for autonomous mapping and exploration run on-board the MAV. Using a front-looking stereo camera as the main sensor, we maintain a tiled octree-based 3D occupancy map. The MAV uses this map for local navigation and frontier-based exploration. In addition, we use a wall-following algorithm as an alternative exploration algorithm in open areas where frontier-based exploration under-performs. During the exploration, data is transmitted to the ground station which runs large-scale visual SLAM. We estimate the MAV's state with inertial data from an IMU together with metric velocity measurements from a custom-built optical flow sensor and pose estimates from visual odometry. We verify our approaches with experimental results, which to the best of our knowledge, demonstrate our MAVs to be the first vision-based MAVs to autonomously explore both indoor and outdoor environments.",
author = "Lionel Heng and Dominik Honegger and Lee, {Gim Hee} and Lorenz Meier and Petri Tanskanen and Friedrich Fraundorfer and Marc Pollefeys",
year = "2014",
doi = "10.1002/rob.21520",
language = "English",
volume = "31",
pages = "654--675",
journal = "Journal of field robotics",
issn = "1556-4959",
publisher = "John Wiley and Sons Inc.",
number = "4",

}

TY - JOUR

T1 - Autonomous visual mapping and exploration with a micro aerial vehicle

AU - Heng,Lionel

AU - Honegger,Dominik

AU - Lee,Gim Hee

AU - Meier,Lorenz

AU - Tanskanen,Petri

AU - Fraundorfer,Friedrich

AU - Pollefeys,Marc

PY - 2014

Y1 - 2014

N2 - Cameras are a natural fit for micro aerial vehicles (MAVs) due to their low weight, low power consumption, and two-dimensional field of view. However, computationally-intensive algorithms are required to infer the 3D structure of the environment from 2D image data. This requirement is made more difficult with the MAV's limited payload which only allows for one CPU board. Hence, we have to design efficient algorithms for state estimation, mapping, planning, and exploration. We implement a set of algorithms on two different vision-based MAV systems such that these algorithms enable the MAVs to map and explore unknown environments. By using both self-built and off-the-shelf systems, we show that our algorithms can be used on different platforms. All algorithms necessary for autonomous mapping and exploration run on-board the MAV. Using a front-looking stereo camera as the main sensor, we maintain a tiled octree-based 3D occupancy map. The MAV uses this map for local navigation and frontier-based exploration. In addition, we use a wall-following algorithm as an alternative exploration algorithm in open areas where frontier-based exploration under-performs. During the exploration, data is transmitted to the ground station which runs large-scale visual SLAM. We estimate the MAV's state with inertial data from an IMU together with metric velocity measurements from a custom-built optical flow sensor and pose estimates from visual odometry. We verify our approaches with experimental results, which to the best of our knowledge, demonstrate our MAVs to be the first vision-based MAVs to autonomously explore both indoor and outdoor environments.

AB - Cameras are a natural fit for micro aerial vehicles (MAVs) due to their low weight, low power consumption, and two-dimensional field of view. However, computationally-intensive algorithms are required to infer the 3D structure of the environment from 2D image data. This requirement is made more difficult with the MAV's limited payload which only allows for one CPU board. Hence, we have to design efficient algorithms for state estimation, mapping, planning, and exploration. We implement a set of algorithms on two different vision-based MAV systems such that these algorithms enable the MAVs to map and explore unknown environments. By using both self-built and off-the-shelf systems, we show that our algorithms can be used on different platforms. All algorithms necessary for autonomous mapping and exploration run on-board the MAV. Using a front-looking stereo camera as the main sensor, we maintain a tiled octree-based 3D occupancy map. The MAV uses this map for local navigation and frontier-based exploration. In addition, we use a wall-following algorithm as an alternative exploration algorithm in open areas where frontier-based exploration under-performs. During the exploration, data is transmitted to the ground station which runs large-scale visual SLAM. We estimate the MAV's state with inertial data from an IMU together with metric velocity measurements from a custom-built optical flow sensor and pose estimates from visual odometry. We verify our approaches with experimental results, which to the best of our knowledge, demonstrate our MAVs to be the first vision-based MAVs to autonomously explore both indoor and outdoor environments.

UR - http://www.scopus.com/inward/record.url?scp=84902137736&partnerID=8YFLogxK

U2 - 10.1002/rob.21520

DO - 10.1002/rob.21520

M3 - Article

VL - 31

SP - 654

EP - 675

JO - Journal of field robotics

T2 - Journal of field robotics

JF - Journal of field robotics

SN - 1556-4959

IS - 4

ER -