Online multi-camera registration for bimanual workspace trajectories

Neil T. Dantam, Hani Ben Amor, Henrik I. Christensen, Mike Stilman

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

We demonstrate that millimeter-level bimanual manipulation accuracy can be achieved without the static camera registration typically required for visual servoing. We register multiple cameras online, converging in seconds, by visually tracking features on the robot hands and filtering the result. Then, we compute and track continuous-velocity relative workspace trajectories for the end-effector. We demonstrate the approach using Schunk LWA4 and SDH manipulators and Logitech C920 cameras, showing accurate relative positioning for pen-capping and object hand-off tasks. Our filtering software is available under a permissive license.1

Original languageEnglish (US)
Title of host publicationIEEE-RAS International Conference on Humanoid Robots
PublisherIEEE Computer Society
Pages588-593
Number of pages6
Volume2015-February
ISBN (Print)9781479971749
DOIs
StatePublished - Feb 12 2015
Externally publishedYes
Event2014 14th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2014 - Madrid, Spain
Duration: Nov 18 2014Nov 20 2014

Other

Other2014 14th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2014
CountrySpain
CityMadrid
Period11/18/1411/20/14

Fingerprint

Cameras
Trajectories
End effectors
Light pens
Visual servoing
Manipulators
Robots

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture
  • Human-Computer Interaction
  • Electrical and Electronic Engineering

Cite this

Dantam, N. T., Ben Amor, H., Christensen, H. I., & Stilman, M. (2015). Online multi-camera registration for bimanual workspace trajectories. In IEEE-RAS International Conference on Humanoid Robots (Vol. 2015-February, pp. 588-593). [7041422] IEEE Computer Society. https://doi.org/10.1109/HUMANOIDS.2014.7041422

Online multi-camera registration for bimanual workspace trajectories. / Dantam, Neil T.; Ben Amor, Hani; Christensen, Henrik I.; Stilman, Mike.

IEEE-RAS International Conference on Humanoid Robots. Vol. 2015-February IEEE Computer Society, 2015. p. 588-593 7041422.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Dantam, NT, Ben Amor, H, Christensen, HI & Stilman, M 2015, Online multi-camera registration for bimanual workspace trajectories. in IEEE-RAS International Conference on Humanoid Robots. vol. 2015-February, 7041422, IEEE Computer Society, pp. 588-593, 2014 14th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2014, Madrid, Spain, 11/18/14. https://doi.org/10.1109/HUMANOIDS.2014.7041422
Dantam NT, Ben Amor H, Christensen HI, Stilman M. Online multi-camera registration for bimanual workspace trajectories. In IEEE-RAS International Conference on Humanoid Robots. Vol. 2015-February. IEEE Computer Society. 2015. p. 588-593. 7041422 https://doi.org/10.1109/HUMANOIDS.2014.7041422
Dantam, Neil T. ; Ben Amor, Hani ; Christensen, Henrik I. ; Stilman, Mike. / Online multi-camera registration for bimanual workspace trajectories. IEEE-RAS International Conference on Humanoid Robots. Vol. 2015-February IEEE Computer Society, 2015. pp. 588-593
@inproceedings{19df91cead944032a168417d28da01dd,
title = "Online multi-camera registration for bimanual workspace trajectories",
abstract = "We demonstrate that millimeter-level bimanual manipulation accuracy can be achieved without the static camera registration typically required for visual servoing. We register multiple cameras online, converging in seconds, by visually tracking features on the robot hands and filtering the result. Then, we compute and track continuous-velocity relative workspace trajectories for the end-effector. We demonstrate the approach using Schunk LWA4 and SDH manipulators and Logitech C920 cameras, showing accurate relative positioning for pen-capping and object hand-off tasks. Our filtering software is available under a permissive license.1",
author = "Dantam, {Neil T.} and {Ben Amor}, Hani and Christensen, {Henrik I.} and Mike Stilman",
year = "2015",
month = "2",
day = "12",
doi = "10.1109/HUMANOIDS.2014.7041422",
language = "English (US)",
isbn = "9781479971749",
volume = "2015-February",
pages = "588--593",
booktitle = "IEEE-RAS International Conference on Humanoid Robots",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Online multi-camera registration for bimanual workspace trajectories

AU - Dantam, Neil T.

AU - Ben Amor, Hani

AU - Christensen, Henrik I.

AU - Stilman, Mike

PY - 2015/2/12

Y1 - 2015/2/12

N2 - We demonstrate that millimeter-level bimanual manipulation accuracy can be achieved without the static camera registration typically required for visual servoing. We register multiple cameras online, converging in seconds, by visually tracking features on the robot hands and filtering the result. Then, we compute and track continuous-velocity relative workspace trajectories for the end-effector. We demonstrate the approach using Schunk LWA4 and SDH manipulators and Logitech C920 cameras, showing accurate relative positioning for pen-capping and object hand-off tasks. Our filtering software is available under a permissive license.1

AB - We demonstrate that millimeter-level bimanual manipulation accuracy can be achieved without the static camera registration typically required for visual servoing. We register multiple cameras online, converging in seconds, by visually tracking features on the robot hands and filtering the result. Then, we compute and track continuous-velocity relative workspace trajectories for the end-effector. We demonstrate the approach using Schunk LWA4 and SDH manipulators and Logitech C920 cameras, showing accurate relative positioning for pen-capping and object hand-off tasks. Our filtering software is available under a permissive license.1

UR - http://www.scopus.com/inward/record.url?scp=84945182762&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84945182762&partnerID=8YFLogxK

U2 - 10.1109/HUMANOIDS.2014.7041422

DO - 10.1109/HUMANOIDS.2014.7041422

M3 - Conference contribution

AN - SCOPUS:84945182762

SN - 9781479971749

VL - 2015-February

SP - 588

EP - 593

BT - IEEE-RAS International Conference on Humanoid Robots

PB - IEEE Computer Society

ER -