Deploying MAVs for autonomous navigation in dark underground mine environments
Document identifier: oai:DiVA.org:ltu-77844
Access full text here:
10.1016/j.robot.2020.103472Keyword: Engineering and Technology,
Electrical Engineering, Electronic Engineering, Information Engineering,
Control Engineering,
Teknik och teknologier,
Elektroteknik och elektronik,
Reglerteknik,
MAVs navigation,
Autonomous tunnel inspection,
Mining aerial robotics,
Robotics and Artificial Intelligence,
Robotik och artificiell intelligensPublication year: 2020Relevant Sustainable Development Goals (SDGs):
The SDG label(s) above have been assigned by OSDG.aiAbstract: Operating Micro Aerial Vehicles (MAVs) in subterranean environments is becoming more and more relevant in the field of aerial robotics. Despite the large spectrum of technological advances in the field, flying in such challenging environments is still an ongoing quest that requires the combination of multiple sensor modalities like visual/thermal cameras as well as 3D and 2D lidars. Nevertheless, there exist cases in subterranean environments where the aim is to deploy fast and lightweight aerial robots for area reckoning purposes after an event (e.g. blasting in production areas). This work proposes a novel baseline approach for the navigation of resource constrained robots, introducing the aerial underground scout, with the main goal to rapidly explore unknown areas and provide a feedback to the operator. The main proposed framework focuses on the navigation, control and vision capabilities of the aerial platforms with low-cost sensor suites, contributing significantly towards real-life applications. The merit of the proposed control architecture is that it considers the flying platform as a floating object, composing a velocity controller on the x, y axes and altitude control to navigate along the tunnel. Two novel approaches make up the cornerstone of the proposed contributions for the task of navigation: (1) a vector geometry method based on 2D lidar, and (2) a Deep Learning (DL) method through a classification process based on an on-board image stream, where both methods correct the heading towards the center of the mine tunnel. Finally, the framework has been evaluated in multiple field trials in an underground mine in Sweden.
Authors
Sina Sharif Mansouri
Luleå tekniska universitet; Signaler och system
Other publications
>>
Christoforos Kanellakis
Luleå tekniska universitet; Signaler och system
Other publications
>>
Dariusz Kominiak
Luleå tekniska universitet; Signaler och system
Other publications
>>
George Nikolakopoulos
Luleå tekniska universitet; Signaler och system
Other publications
>>
Record metadata
Click to view metadata
header:
identifier: oai:DiVA.org:ltu-77844
datestamp: 2021-04-19T12:57:20Z
setSpec: SwePub-ltu
metadata:
mods:
@attributes:
version: 3.7
recordInfo:
recordContentSource: ltu
recordCreationDate: 2020-02-25
identifier:
http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-77844
10.1016/j.robot.2020.103472
2-s2.0-85079573394
titleInfo:
@attributes:
lang: eng
title: Deploying MAVs for autonomous navigation in dark underground mine environments
abstract: Operating Micro Aerial Vehicles (MAVs) in subterranean environments is becoming more and more relevant in the field of aerial robotics. Despite the large spectrum of technological advances in the field flying in such challenging environments is still an ongoing quest that requires the combination of multiple sensor modalities like visual/thermal cameras as well as 3D and 2D lidars. Nevertheless there exist cases in subterranean environments where the aim is to deploy fast and lightweight aerial robots for area reckoning purposes after an event (e.g. blasting in production areas). This work proposes a novel baseline approach for the navigation of resource constrained robots introducing the aerial underground scout with the main goal to rapidly explore unknown areas and provide a feedback to the operator. The main proposed framework focuses on the navigation control and vision capabilities of the aerial platforms with low-cost sensor suites contributing significantly towards real-life applications. The merit of the proposed control architecture is that it considers the flying platform as a floating object composing a velocity controller on the x y axes and altitude control to navigate along the tunnel. Two novel approaches make up the cornerstone of the proposed contributions for the task of navigation: (1) a vector geometry method based on 2D lidar and (2) a Deep Learning (DL) method through a classification process based on an on-board image stream where both methods correct the heading towards the center of the mine tunnel. Finally the framework has been evaluated in multiple field trials in an underground mine in Sweden.
subject:
@attributes:
lang: eng
authority: uka.se
topic:
Engineering and Technology
Electrical Engineering Electronic Engineering Information Engineering
Control Engineering
@attributes:
lang: swe
authority: uka.se
topic:
Teknik och teknologier
Elektroteknik och elektronik
Reglerteknik
@attributes:
lang: eng
topic: MAVs navigation
@attributes:
lang: eng
topic: Autonomous tunnel inspection
@attributes:
lang: eng
topic: Mining aerial robotics
@attributes:
lang: eng
authority: ltu
topic: Robotics and Artificial Intelligence
genre: Research subject
@attributes:
lang: swe
authority: ltu
topic: Robotik och artificiell intelligens
genre: Research subject
language:
languageTerm: eng
genre:
publication/journal-article
ref
note:
Published
4
Validerad;2020;Nivå 2;2020-02-25 (alebob)
name:
@attributes:
type: personal
authority: ltu
namePart:
Mansouri
Sina Sharif
role:
roleTerm: aut
affiliation:
Luleå tekniska universitet
Signaler och system
nameIdentifier:
sinsha
0000-0001-7631-002x
@attributes:
type: personal
authority: ltu
namePart:
Kanellakis
Christoforos
role:
roleTerm: aut
affiliation:
Luleå tekniska universitet
Signaler och system
nameIdentifier: chrkan
@attributes:
type: personal
authority: ltu
namePart:
Kominiak
Dariusz
role:
roleTerm: aut
affiliation:
Luleå tekniska universitet
Signaler och system
nameIdentifier:
darkom
0000-0002-2001-7171
@attributes:
type: personal
authority: ltu
namePart:
Nikolakopoulos
George
role:
roleTerm: aut
affiliation:
Luleå tekniska universitet
Signaler och system
nameIdentifier:
geonik
0000-0003-0126-1897
originInfo:
dateIssued: 2020
publisher: Elsevier
relatedItem:
@attributes:
type: host
titleInfo:
title: Robotics and Autonomous Systems
identifier:
0921-8890
1872-793X
part:
detail:
@attributes:
type: volume
number: 126
@attributes:
type: artNo
number: 103472
physicalDescription:
form: print
typeOfResource: text