Online camera registration for robot manipulation

Neil Dantam, Hani Ben Amor, Henrik Christensen, Mike Stilman

Research output: Chapter in Book/Report/Conference proceedingChapter

1 Citation (Scopus)

Abstract

We demonstrate that millimeter-level manipulation accuracy can be achieved without the static camera registration typically required for visual servoing. We register the camera online, converging in seconds, by visually tracking features on the robot and filtering the result. This online registration handles cases such as perturbed camera positions, wear and tear on camera mounts, and even a camera held by a human. We implement the approach on a Schunk LWA4 manipulator and Logitech C920 camera, servoing to target and pre-grasp configurations. Our filtering software is available under a permissive license (Software available at http://github.com/golems/reflex).

Original languageEnglish (US)
Title of host publicationSpringer Tracts in Advanced Robotics
PublisherSpringer Verlag
Pages179-194
Number of pages16
Volume109
DOIs
StatePublished - 2016
Externally publishedYes

Publication series

NameSpringer Tracts in Advanced Robotics
Volume109
ISSN (Print)16107438
ISSN (Electronic)1610742X

Fingerprint

Cameras
Robots
Visual servoing
Manipulators
Wear of materials

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Artificial Intelligence

Cite this

Dantam, N., Ben Amor, H., Christensen, H., & Stilman, M. (2016). Online camera registration for robot manipulation. In Springer Tracts in Advanced Robotics (Vol. 109, pp. 179-194). (Springer Tracts in Advanced Robotics; Vol. 109). Springer Verlag. https://doi.org/10.1007/978-3-319-23778-7_13

Online camera registration for robot manipulation. / Dantam, Neil; Ben Amor, Hani; Christensen, Henrik; Stilman, Mike.

Springer Tracts in Advanced Robotics. Vol. 109 Springer Verlag, 2016. p. 179-194 (Springer Tracts in Advanced Robotics; Vol. 109).

Research output: Chapter in Book/Report/Conference proceedingChapter

Dantam, N, Ben Amor, H, Christensen, H & Stilman, M 2016, Online camera registration for robot manipulation. in Springer Tracts in Advanced Robotics. vol. 109, Springer Tracts in Advanced Robotics, vol. 109, Springer Verlag, pp. 179-194. https://doi.org/10.1007/978-3-319-23778-7_13
Dantam N, Ben Amor H, Christensen H, Stilman M. Online camera registration for robot manipulation. In Springer Tracts in Advanced Robotics. Vol. 109. Springer Verlag. 2016. p. 179-194. (Springer Tracts in Advanced Robotics). https://doi.org/10.1007/978-3-319-23778-7_13
Dantam, Neil ; Ben Amor, Hani ; Christensen, Henrik ; Stilman, Mike. / Online camera registration for robot manipulation. Springer Tracts in Advanced Robotics. Vol. 109 Springer Verlag, 2016. pp. 179-194 (Springer Tracts in Advanced Robotics).
@inbook{9c218d8dbb73404388709b0ed80a12c4,
title = "Online camera registration for robot manipulation",
abstract = "We demonstrate that millimeter-level manipulation accuracy can be achieved without the static camera registration typically required for visual servoing. We register the camera online, converging in seconds, by visually tracking features on the robot and filtering the result. This online registration handles cases such as perturbed camera positions, wear and tear on camera mounts, and even a camera held by a human. We implement the approach on a Schunk LWA4 manipulator and Logitech C920 camera, servoing to target and pre-grasp configurations. Our filtering software is available under a permissive license (Software available at http://github.com/golems/reflex).",
author = "Neil Dantam and {Ben Amor}, Hani and Henrik Christensen and Mike Stilman",
year = "2016",
doi = "10.1007/978-3-319-23778-7_13",
language = "English (US)",
volume = "109",
series = "Springer Tracts in Advanced Robotics",
publisher = "Springer Verlag",
pages = "179--194",
booktitle = "Springer Tracts in Advanced Robotics",

}

TY - CHAP

T1 - Online camera registration for robot manipulation

AU - Dantam, Neil

AU - Ben Amor, Hani

AU - Christensen, Henrik

AU - Stilman, Mike

PY - 2016

Y1 - 2016

N2 - We demonstrate that millimeter-level manipulation accuracy can be achieved without the static camera registration typically required for visual servoing. We register the camera online, converging in seconds, by visually tracking features on the robot and filtering the result. This online registration handles cases such as perturbed camera positions, wear and tear on camera mounts, and even a camera held by a human. We implement the approach on a Schunk LWA4 manipulator and Logitech C920 camera, servoing to target and pre-grasp configurations. Our filtering software is available under a permissive license (Software available at http://github.com/golems/reflex).

AB - We demonstrate that millimeter-level manipulation accuracy can be achieved without the static camera registration typically required for visual servoing. We register the camera online, converging in seconds, by visually tracking features on the robot and filtering the result. This online registration handles cases such as perturbed camera positions, wear and tear on camera mounts, and even a camera held by a human. We implement the approach on a Schunk LWA4 manipulator and Logitech C920 camera, servoing to target and pre-grasp configurations. Our filtering software is available under a permissive license (Software available at http://github.com/golems/reflex).

UR - http://www.scopus.com/inward/record.url?scp=84948124529&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84948124529&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-23778-7_13

DO - 10.1007/978-3-319-23778-7_13

M3 - Chapter

AN - SCOPUS:84948124529

VL - 109

T3 - Springer Tracts in Advanced Robotics

SP - 179

EP - 194

BT - Springer Tracts in Advanced Robotics

PB - Springer Verlag

ER -