Autonomous navigation and mapping for inspection of penstocks and tunnels with MAVs

Tolga Özaslan, Giuseppe Loianno, James Keller, Camillo J. Taylor, Vijay Kumar, Jennifer M. Wozencraft, Thomas Hood

Research output: Contribution to journalArticle

Abstract

In this paper, we address the estimation, control, navigation and mapping problems to achieve autonomous inspection of penstocks and tunnels using aerial vehicles with on-board sensing and computation. Penstocks and tunnels have the shape of a generalized cylinder. They are generally dark and featureless. State estimation is challenging because range sensors do not yield adequate information and cameras do not work in the dark. We show that the six degrees of freedom (DOF) pose and velocity can be estimated by fusing information from an inertial measurement unit (IMU), a lidar and a set of cameras. This letter discusses in detail the range-based estimation part while leaving the details of vision component to our earlier work. The proposed algorithm relies only on a model of the generalized cylinder and is robust to changes in shape of the tunnel. The approach is validated through real experiments showing autonomous and shared control, state estimation and environment mapping in the penstock at Center Hill Dam, TN. To our knowledge, this is the first time autonomous navigation and mapping has been achieved in a penstock without any external infrastructure such GPS or external cameras.

Original languageEnglish (US)
Article number7914761
Pages (from-to)1740-1747
Number of pages8
JournalIEEE Robotics and Automation Letters
Volume2
Issue number3
DOIs
StatePublished - Jul 1 2017

Fingerprint

Penstocks
Micro air vehicle (MAV)
Autonomous Navigation
Tunnel
Inspection
Tunnels
Navigation
Camera
State Estimation
Cameras
State estimation
Lidar
Range of data
Units of measurement
Degrees of freedom (mechanics)
Optical radar
Sensing
Infrastructure
Degree of freedom
Dams

Keywords

  • Aerial systems
  • field robots
  • perception and autonomy
  • robotics in hazardous fields

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Human-Computer Interaction
  • Biomedical Engineering
  • Mechanical Engineering
  • Control and Optimization
  • Artificial Intelligence
  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Cite this

Özaslan, T., Loianno, G., Keller, J., Taylor, C. J., Kumar, V., Wozencraft, J. M., & Hood, T. (2017). Autonomous navigation and mapping for inspection of penstocks and tunnels with MAVs. IEEE Robotics and Automation Letters, 2(3), 1740-1747. [7914761]. https://doi.org/10.1109/LRA.2017.2699790

Autonomous navigation and mapping for inspection of penstocks and tunnels with MAVs. / Özaslan, Tolga; Loianno, Giuseppe; Keller, James; Taylor, Camillo J.; Kumar, Vijay; Wozencraft, Jennifer M.; Hood, Thomas.

In: IEEE Robotics and Automation Letters, Vol. 2, No. 3, 7914761, 01.07.2017, p. 1740-1747.

Research output: Contribution to journalArticle

Özaslan, T, Loianno, G, Keller, J, Taylor, CJ, Kumar, V, Wozencraft, JM & Hood, T 2017, 'Autonomous navigation and mapping for inspection of penstocks and tunnels with MAVs', IEEE Robotics and Automation Letters, vol. 2, no. 3, 7914761, pp. 1740-1747. https://doi.org/10.1109/LRA.2017.2699790
Özaslan, Tolga ; Loianno, Giuseppe ; Keller, James ; Taylor, Camillo J. ; Kumar, Vijay ; Wozencraft, Jennifer M. ; Hood, Thomas. / Autonomous navigation and mapping for inspection of penstocks and tunnels with MAVs. In: IEEE Robotics and Automation Letters. 2017 ; Vol. 2, No. 3. pp. 1740-1747.
@article{3c854a3fe5b44f23bf0b8345d8b67db8,
title = "Autonomous navigation and mapping for inspection of penstocks and tunnels with MAVs",
abstract = "In this paper, we address the estimation, control, navigation and mapping problems to achieve autonomous inspection of penstocks and tunnels using aerial vehicles with on-board sensing and computation. Penstocks and tunnels have the shape of a generalized cylinder. They are generally dark and featureless. State estimation is challenging because range sensors do not yield adequate information and cameras do not work in the dark. We show that the six degrees of freedom (DOF) pose and velocity can be estimated by fusing information from an inertial measurement unit (IMU), a lidar and a set of cameras. This letter discusses in detail the range-based estimation part while leaving the details of vision component to our earlier work. The proposed algorithm relies only on a model of the generalized cylinder and is robust to changes in shape of the tunnel. The approach is validated through real experiments showing autonomous and shared control, state estimation and environment mapping in the penstock at Center Hill Dam, TN. To our knowledge, this is the first time autonomous navigation and mapping has been achieved in a penstock without any external infrastructure such GPS or external cameras.",
keywords = "Aerial systems, field robots, perception and autonomy, robotics in hazardous fields",
author = "Tolga {\"O}zaslan and Giuseppe Loianno and James Keller and Taylor, {Camillo J.} and Vijay Kumar and Wozencraft, {Jennifer M.} and Thomas Hood",
year = "2017",
month = "7",
day = "1",
doi = "10.1109/LRA.2017.2699790",
language = "English (US)",
volume = "2",
pages = "1740--1747",
journal = "IEEE Robotics and Automation Letters",
issn = "2377-3766",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - Autonomous navigation and mapping for inspection of penstocks and tunnels with MAVs

AU - Özaslan, Tolga

AU - Loianno, Giuseppe

AU - Keller, James

AU - Taylor, Camillo J.

AU - Kumar, Vijay

AU - Wozencraft, Jennifer M.

AU - Hood, Thomas

PY - 2017/7/1

Y1 - 2017/7/1

N2 - In this paper, we address the estimation, control, navigation and mapping problems to achieve autonomous inspection of penstocks and tunnels using aerial vehicles with on-board sensing and computation. Penstocks and tunnels have the shape of a generalized cylinder. They are generally dark and featureless. State estimation is challenging because range sensors do not yield adequate information and cameras do not work in the dark. We show that the six degrees of freedom (DOF) pose and velocity can be estimated by fusing information from an inertial measurement unit (IMU), a lidar and a set of cameras. This letter discusses in detail the range-based estimation part while leaving the details of vision component to our earlier work. The proposed algorithm relies only on a model of the generalized cylinder and is robust to changes in shape of the tunnel. The approach is validated through real experiments showing autonomous and shared control, state estimation and environment mapping in the penstock at Center Hill Dam, TN. To our knowledge, this is the first time autonomous navigation and mapping has been achieved in a penstock without any external infrastructure such GPS or external cameras.

AB - In this paper, we address the estimation, control, navigation and mapping problems to achieve autonomous inspection of penstocks and tunnels using aerial vehicles with on-board sensing and computation. Penstocks and tunnels have the shape of a generalized cylinder. They are generally dark and featureless. State estimation is challenging because range sensors do not yield adequate information and cameras do not work in the dark. We show that the six degrees of freedom (DOF) pose and velocity can be estimated by fusing information from an inertial measurement unit (IMU), a lidar and a set of cameras. This letter discusses in detail the range-based estimation part while leaving the details of vision component to our earlier work. The proposed algorithm relies only on a model of the generalized cylinder and is robust to changes in shape of the tunnel. The approach is validated through real experiments showing autonomous and shared control, state estimation and environment mapping in the penstock at Center Hill Dam, TN. To our knowledge, this is the first time autonomous navigation and mapping has been achieved in a penstock without any external infrastructure such GPS or external cameras.

KW - Aerial systems

KW - field robots

KW - perception and autonomy

KW - robotics in hazardous fields

UR - http://www.scopus.com/inward/record.url?scp=85034096772&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85034096772&partnerID=8YFLogxK

U2 - 10.1109/LRA.2017.2699790

DO - 10.1109/LRA.2017.2699790

M3 - Article

VL - 2

SP - 1740

EP - 1747

JO - IEEE Robotics and Automation Letters

JF - IEEE Robotics and Automation Letters

SN - 2377-3766

IS - 3

M1 - 7914761

ER -