Dual quaternion-based visual servoing for grasping moving objects

Cristiana De Farias; Maxime Adjigble; Brahim Tamadazte; Rustam Stolkin; Naresh Marturi

doi:10.1109/CASE49439.2021.9551631

Dual quaternion-based visual servoing for grasping moving objects

Cristiana De Farias^*, Maxime Adjigble, Brahim Tamadazte, Rustam Stolkin, Naresh Marturi

^*Corresponding author for this work

Metallurgy and Materials

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Citations (Scopus)

1 Downloads (Pure)

Abstract

This paper presents a new dual quaternion-based formulation for pose-based visual servoing. Extending our previous work on local contact moment (LoCoMo) based grasp planning, we demonstrate grasping of arbitrarily moving objects in 3D space. Instead of using the conventional axis-angle parameterization, dual quaternions allow designing the visual servoing task in a more compact manner and provide robustness to manipulator singularities. Given an object point cloud, LoCoMo generates a ranked list of grasp and pre-grasp poses, which are used as desired poses for visual servoing. Whenever the object moves (tracked by visual marker tracking), the desired pose updates automatically. For this, capitalising on the dual quaternion spatial distance error, we propose a dynamic grasp re-ranking metric to select the best feasible grasp for the moving object. This allows the robot to readily track and grasp arbitrarily moving objects. In addition, we also explore the robot null-space with our controller to avoid joint limits so as to achieve smooth trajectories while following moving objects. We evaluate the performance of the proposed visual servoing by conducting simulation experiments of grasping various objects using a 7-axis robot fitted with a 2-finger gripper. Obtained results demonstrate the efficiency of our proposed visual servoing.

Original language	English
Title of host publication	2021 IEEE 17th International Conference on Automation Science and Engineering (CASE)
Publisher	IEEE
Pages	151-158
Number of pages	8
ISBN (Electronic)	9781665418737, 9781665418720
ISBN (Print)	9781665448093 (PoD)
DOIs	https://doi.org/10.1109/CASE49439.2021.9551631
Publication status	Published - 5 Oct 2021
Event	17th IEEE International Conference on Automation Science and Engineering, CASE 2021 - Lyon, France Duration: 23 Aug 2021 → 27 Aug 2021

Publication series

Name	IEEE International Conference on Automation Science and Engineering
ISSN (Print)	2161-8070
ISSN (Electronic)	2161-8089

Conference

Conference	17th IEEE International Conference on Automation Science and Engineering, CASE 2021
Country/Territory	France
City	Lyon
Period	23/08/21 → 27/08/21

Bibliographical note

Funding Information:
1 Extreme Robotics Laboratory, School of Metallurgy and Materials, University of Birmingham, Edgbaston, B15 2TT, UK. 2 Sorbonne Uni-versité, CNRS UMR 7222, INSERM U1150, ISIR, F-75005, Paris, France. †Corresponding Author: {CXM1029}@student.bham.ac.uk This work was supported by the UK National Centre for Nuclear Robotics (NCNR), part-funded by EPSRC EP/R02572X/1 and in part supported by CHIST-ERA under Project EP/S032428/1 PeGRoGAM.

Publisher Copyright:
© 2021 IEEE.

Keywords

Visualization
Three-dimensional displays
Quaternions
Perturbation methods
Grasping
Visual servoing
Robustness

ASJC Scopus subject areas

Control and Systems Engineering
Electrical and Electronic Engineering

Access to Document

10.1109/CASE49439.2021.9551631

DeFariasC2021Dual
Contains public sector information licensed under the Open Government Licence v3.0. https://www.nationalarchives.gov.uk/doc/open-government-licence/version/3/
Final published version, 2.78 MBLicence: Other (please provide link to licence statement

Cite this

De Farias, C., Adjigble, M., Tamadazte, B., Stolkin, R., & Marturi, N. (2021). Dual quaternion-based visual servoing for grasping moving objects. In 2021 IEEE 17th International Conference on Automation Science and Engineering (CASE) (pp. 151-158). Article 9551631 (IEEE International Conference on Automation Science and Engineering). IEEE. https://doi.org/10.1109/CASE49439.2021.9551631

@inproceedings{80ef0474043547329292d79b5d01a395,

title = "Dual quaternion-based visual servoing for grasping moving objects",

abstract = "This paper presents a new dual quaternion-based formulation for pose-based visual servoing. Extending our previous work on local contact moment (LoCoMo) based grasp planning, we demonstrate grasping of arbitrarily moving objects in 3D space. Instead of using the conventional axis-angle parameterization, dual quaternions allow designing the visual servoing task in a more compact manner and provide robustness to manipulator singularities. Given an object point cloud, LoCoMo generates a ranked list of grasp and pre-grasp poses, which are used as desired poses for visual servoing. Whenever the object moves (tracked by visual marker tracking), the desired pose updates automatically. For this, capitalising on the dual quaternion spatial distance error, we propose a dynamic grasp re-ranking metric to select the best feasible grasp for the moving object. This allows the robot to readily track and grasp arbitrarily moving objects. In addition, we also explore the robot null-space with our controller to avoid joint limits so as to achieve smooth trajectories while following moving objects. We evaluate the performance of the proposed visual servoing by conducting simulation experiments of grasping various objects using a 7-axis robot fitted with a 2-finger gripper. Obtained results demonstrate the efficiency of our proposed visual servoing.",

keywords = "Visualization, Three-dimensional displays, Quaternions, Perturbation methods, Grasping, Visual servoing, Robustness",

author = "{De Farias}, Cristiana and Maxime Adjigble and Brahim Tamadazte and Rustam Stolkin and Naresh Marturi",

note = "Funding Information: 1 Extreme Robotics Laboratory, School of Metallurgy and Materials, University of Birmingham, Edgbaston, B15 2TT, UK. 2 Sorbonne Uni-versit{\'e}, CNRS UMR 7222, INSERM U1150, ISIR, F-75005, Paris, France. †Corresponding Author: {CXM1029}@student.bham.ac.uk This work was supported by the UK National Centre for Nuclear Robotics (NCNR), part-funded by EPSRC EP/R02572X/1 and in part supported by CHIST-ERA under Project EP/S032428/1 PeGRoGAM. Publisher Copyright: {\textcopyright} 2021 IEEE.; 17th IEEE International Conference on Automation Science and Engineering, CASE 2021 ; Conference date: 23-08-2021 Through 27-08-2021",

year = "2021",

month = oct,

day = "5",

doi = "10.1109/CASE49439.2021.9551631",

language = "English",

isbn = "9781665448093 (PoD)",

series = "IEEE International Conference on Automation Science and Engineering",

publisher = "IEEE",

pages = "151--158",

booktitle = "2021 IEEE 17th International Conference on Automation Science and Engineering (CASE)",

}

De Farias, C, Adjigble, M, Tamadazte, B, Stolkin, R & Marturi, N 2021, Dual quaternion-based visual servoing for grasping moving objects. in 2021 IEEE 17th International Conference on Automation Science and Engineering (CASE)., 9551631, IEEE International Conference on Automation Science and Engineering, IEEE, pp. 151-158, 17th IEEE International Conference on Automation Science and Engineering, CASE 2021, Lyon, France, 23/08/21. https://doi.org/10.1109/CASE49439.2021.9551631

Dual quaternion-based visual servoing for grasping moving objects. / De Farias, Cristiana; Adjigble, Maxime; Tamadazte, Brahim et al.
2021 IEEE 17th International Conference on Automation Science and Engineering (CASE). IEEE, 2021. p. 151-158 9551631 (IEEE International Conference on Automation Science and Engineering).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Dual quaternion-based visual servoing for grasping moving objects

AU - De Farias, Cristiana

AU - Adjigble, Maxime

AU - Tamadazte, Brahim

AU - Stolkin, Rustam

AU - Marturi, Naresh

N1 - Funding Information: 1 Extreme Robotics Laboratory, School of Metallurgy and Materials, University of Birmingham, Edgbaston, B15 2TT, UK. 2 Sorbonne Uni-versité, CNRS UMR 7222, INSERM U1150, ISIR, F-75005, Paris, France. †Corresponding Author: {CXM1029}@student.bham.ac.uk This work was supported by the UK National Centre for Nuclear Robotics (NCNR), part-funded by EPSRC EP/R02572X/1 and in part supported by CHIST-ERA under Project EP/S032428/1 PeGRoGAM. Publisher Copyright: © 2021 IEEE.

PY - 2021/10/5

Y1 - 2021/10/5

N2 - This paper presents a new dual quaternion-based formulation for pose-based visual servoing. Extending our previous work on local contact moment (LoCoMo) based grasp planning, we demonstrate grasping of arbitrarily moving objects in 3D space. Instead of using the conventional axis-angle parameterization, dual quaternions allow designing the visual servoing task in a more compact manner and provide robustness to manipulator singularities. Given an object point cloud, LoCoMo generates a ranked list of grasp and pre-grasp poses, which are used as desired poses for visual servoing. Whenever the object moves (tracked by visual marker tracking), the desired pose updates automatically. For this, capitalising on the dual quaternion spatial distance error, we propose a dynamic grasp re-ranking metric to select the best feasible grasp for the moving object. This allows the robot to readily track and grasp arbitrarily moving objects. In addition, we also explore the robot null-space with our controller to avoid joint limits so as to achieve smooth trajectories while following moving objects. We evaluate the performance of the proposed visual servoing by conducting simulation experiments of grasping various objects using a 7-axis robot fitted with a 2-finger gripper. Obtained results demonstrate the efficiency of our proposed visual servoing.

AB - This paper presents a new dual quaternion-based formulation for pose-based visual servoing. Extending our previous work on local contact moment (LoCoMo) based grasp planning, we demonstrate grasping of arbitrarily moving objects in 3D space. Instead of using the conventional axis-angle parameterization, dual quaternions allow designing the visual servoing task in a more compact manner and provide robustness to manipulator singularities. Given an object point cloud, LoCoMo generates a ranked list of grasp and pre-grasp poses, which are used as desired poses for visual servoing. Whenever the object moves (tracked by visual marker tracking), the desired pose updates automatically. For this, capitalising on the dual quaternion spatial distance error, we propose a dynamic grasp re-ranking metric to select the best feasible grasp for the moving object. This allows the robot to readily track and grasp arbitrarily moving objects. In addition, we also explore the robot null-space with our controller to avoid joint limits so as to achieve smooth trajectories while following moving objects. We evaluate the performance of the proposed visual servoing by conducting simulation experiments of grasping various objects using a 7-axis robot fitted with a 2-finger gripper. Obtained results demonstrate the efficiency of our proposed visual servoing.

KW - Visualization

KW - Three-dimensional displays

KW - Quaternions

KW - Perturbation methods

KW - Grasping

KW - Visual servoing

KW - Robustness

UR - http://www.scopus.com/inward/record.url?scp=85117049289&partnerID=8YFLogxK

U2 - 10.1109/CASE49439.2021.9551631

DO - 10.1109/CASE49439.2021.9551631

M3 - Conference contribution

AN - SCOPUS:85117049289

SN - 9781665448093 (PoD)

T3 - IEEE International Conference on Automation Science and Engineering

SP - 151

EP - 158

BT - 2021 IEEE 17th International Conference on Automation Science and Engineering (CASE)

PB - IEEE

T2 - 17th IEEE International Conference on Automation Science and Engineering, CASE 2021

Y2 - 23 August 2021 through 27 August 2021

ER -

Dual quaternion-based visual servoing for grasping moving objects

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this