A vision based ensemble approach to velocity estimation for miniature rotorcraft

Jonathan Andersh, Anoop Cherian, Berenice F Mettler May, Nikolaos P Papanikolopoulos

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Successful operation of a miniature rotorcraft relies on capabilities including automated guidance, trajectory following, and teleoperation; all of which require accurate estimates of the vehicle’s body velocities and Euler angles. For larger rotorcraft that operate outdoors, the traditional approach is to combine a highly accurate IMU with GPS measurements. However, for small scale rotorcraft that operate indoors, lower quality MEMS IMUs are used because of limited payload. In indoor applications GPS is usually not available, and state estimates based on IMU measurements drift over time. In this paper, we propose a novel framework for state estimation that combines a dynamic flight model, IMU measurements, and 3D velocity estimates computed from an onboard monocular camera using computer vision. Our work differs from existing approaches in that, rather than using a single vision algorithm to update the vehicle’s state, we capitalize on the strengths of multiple vision algorithms by integrating them into a meta-algorithm for 3D motion estimation. Experiments are conducted on two real helicopter platforms in a laboratory environment for different motion types to demonstrate and evaluate the effectiveness of our approach.

Original languageEnglish (US)
Pages (from-to)123-138
Number of pages16
JournalAutonomous Robots
Volume39
Issue number2
DOIs
StatePublished - Aug 23 2015

Fingerprint

Global positioning system
Flight dynamics
Motion estimation
State estimation
Remote control
Helicopters
Computer vision
MEMS
Cameras
Trajectories
Experiments

Keywords

  • Rotorcraft state estimation
  • Sensor fusion
  • Visual motion estimation

Cite this

A vision based ensemble approach to velocity estimation for miniature rotorcraft. / Andersh, Jonathan; Cherian, Anoop; Mettler May, Berenice F; Papanikolopoulos, Nikolaos P.

In: Autonomous Robots, Vol. 39, No. 2, 23.08.2015, p. 123-138.

Research output: Contribution to journalArticle

@article{0f3342f3e60143939923fb5bb04bae66,
title = "A vision based ensemble approach to velocity estimation for miniature rotorcraft",
abstract = "Successful operation of a miniature rotorcraft relies on capabilities including automated guidance, trajectory following, and teleoperation; all of which require accurate estimates of the vehicle’s body velocities and Euler angles. For larger rotorcraft that operate outdoors, the traditional approach is to combine a highly accurate IMU with GPS measurements. However, for small scale rotorcraft that operate indoors, lower quality MEMS IMUs are used because of limited payload. In indoor applications GPS is usually not available, and state estimates based on IMU measurements drift over time. In this paper, we propose a novel framework for state estimation that combines a dynamic flight model, IMU measurements, and 3D velocity estimates computed from an onboard monocular camera using computer vision. Our work differs from existing approaches in that, rather than using a single vision algorithm to update the vehicle’s state, we capitalize on the strengths of multiple vision algorithms by integrating them into a meta-algorithm for 3D motion estimation. Experiments are conducted on two real helicopter platforms in a laboratory environment for different motion types to demonstrate and evaluate the effectiveness of our approach.",
keywords = "Rotorcraft state estimation, Sensor fusion, Visual motion estimation",
author = "Jonathan Andersh and Anoop Cherian and {Mettler May}, {Berenice F} and Papanikolopoulos, {Nikolaos P}",
year = "2015",
month = "8",
day = "23",
doi = "10.1007/s10514-015-9430-7",
language = "English (US)",
volume = "39",
pages = "123--138",
journal = "Autonomous Robots",
issn = "0929-5593",
publisher = "Springer Netherlands",
number = "2",

}

TY - JOUR

T1 - A vision based ensemble approach to velocity estimation for miniature rotorcraft

AU - Andersh, Jonathan

AU - Cherian, Anoop

AU - Mettler May, Berenice F

AU - Papanikolopoulos, Nikolaos P

PY - 2015/8/23

Y1 - 2015/8/23

N2 - Successful operation of a miniature rotorcraft relies on capabilities including automated guidance, trajectory following, and teleoperation; all of which require accurate estimates of the vehicle’s body velocities and Euler angles. For larger rotorcraft that operate outdoors, the traditional approach is to combine a highly accurate IMU with GPS measurements. However, for small scale rotorcraft that operate indoors, lower quality MEMS IMUs are used because of limited payload. In indoor applications GPS is usually not available, and state estimates based on IMU measurements drift over time. In this paper, we propose a novel framework for state estimation that combines a dynamic flight model, IMU measurements, and 3D velocity estimates computed from an onboard monocular camera using computer vision. Our work differs from existing approaches in that, rather than using a single vision algorithm to update the vehicle’s state, we capitalize on the strengths of multiple vision algorithms by integrating them into a meta-algorithm for 3D motion estimation. Experiments are conducted on two real helicopter platforms in a laboratory environment for different motion types to demonstrate and evaluate the effectiveness of our approach.

AB - Successful operation of a miniature rotorcraft relies on capabilities including automated guidance, trajectory following, and teleoperation; all of which require accurate estimates of the vehicle’s body velocities and Euler angles. For larger rotorcraft that operate outdoors, the traditional approach is to combine a highly accurate IMU with GPS measurements. However, for small scale rotorcraft that operate indoors, lower quality MEMS IMUs are used because of limited payload. In indoor applications GPS is usually not available, and state estimates based on IMU measurements drift over time. In this paper, we propose a novel framework for state estimation that combines a dynamic flight model, IMU measurements, and 3D velocity estimates computed from an onboard monocular camera using computer vision. Our work differs from existing approaches in that, rather than using a single vision algorithm to update the vehicle’s state, we capitalize on the strengths of multiple vision algorithms by integrating them into a meta-algorithm for 3D motion estimation. Experiments are conducted on two real helicopter platforms in a laboratory environment for different motion types to demonstrate and evaluate the effectiveness of our approach.

KW - Rotorcraft state estimation

KW - Sensor fusion

KW - Visual motion estimation

UR - http://www.scopus.com/inward/record.url?scp=84937522351&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84937522351&partnerID=8YFLogxK

U2 - 10.1007/s10514-015-9430-7

DO - 10.1007/s10514-015-9430-7

M3 - Article

VL - 39

SP - 123

EP - 138

JO - Autonomous Robots

JF - Autonomous Robots

SN - 0929-5593

IS - 2

ER -