Kernel-based visual servoing

Vinutha Kallem, Maneesh Dewan, John P. Swensen, Gregory Hager, Noah J. Cowan

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

Abstract

Traditionally, visual servoing is separated into tracking and control subsystems. This separation, though convenient, is not necessarily well justified. When tracking and control strategies are designed independently, it is not clear how to optimize them to achieve a certain task. In this work, we propose a framework in which spatial sampling kernels - borrowed from the tracking and registration literature -are used to design feedback controllers for visual servoing. The use of spatial sampling kernels provides natural hooks for Lyapunov theory, thus unifying tracking and control and providing a framework for optimizing a particular servoing task. As a first step, we develop kernel-based visual servos for a subset of relative motions between camera and target scene. The subset of motions we consider are 2D translation, scale, and roll of the target relative to the camera. Our approach provides formal guarantees on the convergence/stability of visual servoing algorithms under putatively generic conditions.

Original languageEnglish (US)
Title of host publicationIEEE International Conference on Intelligent Robots and Systems
Pages1975-1980
Number of pages6
DOIs
StatePublished - 2007
Event2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2007 - San Diego, CA, United States
Duration: Oct 29 2007Nov 2 2007

Other

Other2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2007
CountryUnited States
CitySan Diego, CA
Period10/29/0711/2/07

Fingerprint

Visual servoing
Cameras
Sampling
Servomotors
Hooks
Feedback
Controllers

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

Kallem, V., Dewan, M., Swensen, J. P., Hager, G., & Cowan, N. J. (2007). Kernel-based visual servoing. In IEEE International Conference on Intelligent Robots and Systems (pp. 1975-1980). [4399546] https://doi.org/10.1109/IROS.2007.4399546

Kernel-based visual servoing. / Kallem, Vinutha; Dewan, Maneesh; Swensen, John P.; Hager, Gregory; Cowan, Noah J.

IEEE International Conference on Intelligent Robots and Systems. 2007. p. 1975-1980 4399546.

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

Kallem, V, Dewan, M, Swensen, JP, Hager, G & Cowan, NJ 2007, Kernel-based visual servoing. in IEEE International Conference on Intelligent Robots and Systems., 4399546, pp. 1975-1980, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2007, San Diego, CA, United States, 10/29/07. https://doi.org/10.1109/IROS.2007.4399546
Kallem V, Dewan M, Swensen JP, Hager G, Cowan NJ. Kernel-based visual servoing. In IEEE International Conference on Intelligent Robots and Systems. 2007. p. 1975-1980. 4399546 https://doi.org/10.1109/IROS.2007.4399546
Kallem, Vinutha ; Dewan, Maneesh ; Swensen, John P. ; Hager, Gregory ; Cowan, Noah J. / Kernel-based visual servoing. IEEE International Conference on Intelligent Robots and Systems. 2007. pp. 1975-1980
@inproceedings{95e68e12be624dc8a6c3c6a02b085bbb,
title = "Kernel-based visual servoing",
abstract = "Traditionally, visual servoing is separated into tracking and control subsystems. This separation, though convenient, is not necessarily well justified. When tracking and control strategies are designed independently, it is not clear how to optimize them to achieve a certain task. In this work, we propose a framework in which spatial sampling kernels - borrowed from the tracking and registration literature -are used to design feedback controllers for visual servoing. The use of spatial sampling kernels provides natural hooks for Lyapunov theory, thus unifying tracking and control and providing a framework for optimizing a particular servoing task. As a first step, we develop kernel-based visual servos for a subset of relative motions between camera and target scene. The subset of motions we consider are 2D translation, scale, and roll of the target relative to the camera. Our approach provides formal guarantees on the convergence/stability of visual servoing algorithms under putatively generic conditions.",
author = "Vinutha Kallem and Maneesh Dewan and Swensen, {John P.} and Gregory Hager and Cowan, {Noah J.}",
year = "2007",
doi = "10.1109/IROS.2007.4399546",
language = "English (US)",
isbn = "1424409128",
pages = "1975--1980",
booktitle = "IEEE International Conference on Intelligent Robots and Systems",

}

TY - GEN

T1 - Kernel-based visual servoing

AU - Kallem, Vinutha

AU - Dewan, Maneesh

AU - Swensen, John P.

AU - Hager, Gregory

AU - Cowan, Noah J.

PY - 2007

Y1 - 2007

N2 - Traditionally, visual servoing is separated into tracking and control subsystems. This separation, though convenient, is not necessarily well justified. When tracking and control strategies are designed independently, it is not clear how to optimize them to achieve a certain task. In this work, we propose a framework in which spatial sampling kernels - borrowed from the tracking and registration literature -are used to design feedback controllers for visual servoing. The use of spatial sampling kernels provides natural hooks for Lyapunov theory, thus unifying tracking and control and providing a framework for optimizing a particular servoing task. As a first step, we develop kernel-based visual servos for a subset of relative motions between camera and target scene. The subset of motions we consider are 2D translation, scale, and roll of the target relative to the camera. Our approach provides formal guarantees on the convergence/stability of visual servoing algorithms under putatively generic conditions.

AB - Traditionally, visual servoing is separated into tracking and control subsystems. This separation, though convenient, is not necessarily well justified. When tracking and control strategies are designed independently, it is not clear how to optimize them to achieve a certain task. In this work, we propose a framework in which spatial sampling kernels - borrowed from the tracking and registration literature -are used to design feedback controllers for visual servoing. The use of spatial sampling kernels provides natural hooks for Lyapunov theory, thus unifying tracking and control and providing a framework for optimizing a particular servoing task. As a first step, we develop kernel-based visual servos for a subset of relative motions between camera and target scene. The subset of motions we consider are 2D translation, scale, and roll of the target relative to the camera. Our approach provides formal guarantees on the convergence/stability of visual servoing algorithms under putatively generic conditions.

UR - http://www.scopus.com/inward/record.url?scp=51349129639&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51349129639&partnerID=8YFLogxK

U2 - 10.1109/IROS.2007.4399546

DO - 10.1109/IROS.2007.4399546

M3 - Conference contribution

AN - SCOPUS:51349129639

SN - 1424409128

SN - 9781424409129

SP - 1975

EP - 1980

BT - IEEE International Conference on Intelligent Robots and Systems

ER -