Shape Control of Elastic Objects Based on Implicit Sensorimotor Models and Data-Driven Geometric Features

Wanyu Ma; Jihong Zhu; David Navarro-Alarcon

doi:10.1007/978-3-030-95892-3_40

Shape Control of Elastic Objects Based on Implicit Sensorimotor Models and Data-Driven Geometric Features

Wanyu Ma^*, Jihong Zhu, David Navarro-Alarcon

^*Corresponding author for this work

Learning & Autonomous Control

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

2 Citations (Scopus)

Abstract

This paper proposes a general approach to design automatic controls to manipulate elastic objects into desired shapes. The object’s geometric model is defined as the shape feature based on the specific task to globally describe the deformation. Raw visual feedback data is processed using classic regression methods to identify parameters of data-driven geometric models in real-time. Our proposed method is able to analytically compute a pose-shape Jacobian matrix based on implicit functions. This model is then used to derive a shape servoing controller. To validate the proposed method, we report a detailed experimental study with robotic manipulators deforming an elastic rod.

Original language	English
Title of host publication	Intelligent Autonomous Systems 16
Subtitle of host publication	Proceedings of the 16th International Conference, IAS-16
Editors	Marcelo H. Ang Jr, Hajime Asama, Wei Lin, Shaohui Foong
Publisher	Springer
Pages	518-531
ISBN (Print)	978-3-030-95891-6
DOIs	https://doi.org/10.1007/978-3-030-95892-3_40
Publication status	Published - 2022
Event	16th International Conference on Intelligent Autonomous Systems, IAS-16 2020 - Virtual, Online Duration: 22 Jun 2021 → 25 Jun 2021

Publication series

Name	Lecture Notes in Networks and Systems
Volume	412 LNNS
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Conference

Conference	16th International Conference on Intelligent Autonomous Systems, IAS-16 2020
City	Virtual, Online
Period	22/06/21 → 25/06/21

Keywords

Deformable objects
Robotics
Shape control
Visual servoing

Access to Document

10.1007/978-3-030-95892-3_40

Cite this

Ma, W., Zhu, J., & Navarro-Alarcon, D. (2022). Shape Control of Elastic Objects Based on Implicit Sensorimotor Models and Data-Driven Geometric Features. In M. H. Ang Jr, H. Asama, W. Lin, & S. Foong (Eds.), Intelligent Autonomous Systems 16 : Proceedings of the 16th International Conference, IAS-16 (pp. 518-531). (Lecture Notes in Networks and Systems; Vol. 412 LNNS). Springer. https://doi.org/10.1007/978-3-030-95892-3_40

Ma, Wanyu ; Zhu, Jihong ; Navarro-Alarcon, David. / Shape Control of Elastic Objects Based on Implicit Sensorimotor Models and Data-Driven Geometric Features. Intelligent Autonomous Systems 16 : Proceedings of the 16th International Conference, IAS-16. editor / Marcelo H. Ang Jr ; Hajime Asama ; Wei Lin ; Shaohui Foong. Springer, 2022. pp. 518-531 (Lecture Notes in Networks and Systems).

@inproceedings{1c20350fdada49239fb9218715f62214,

title = "Shape Control of Elastic Objects Based on Implicit Sensorimotor Models and Data-Driven Geometric Features",

abstract = "This paper proposes a general approach to design automatic controls to manipulate elastic objects into desired shapes. The object{\textquoteright}s geometric model is defined as the shape feature based on the specific task to globally describe the deformation. Raw visual feedback data is processed using classic regression methods to identify parameters of data-driven geometric models in real-time. Our proposed method is able to analytically compute a pose-shape Jacobian matrix based on implicit functions. This model is then used to derive a shape servoing controller. To validate the proposed method, we report a detailed experimental study with robotic manipulators deforming an elastic rod.",

keywords = "Deformable objects, Robotics, Shape control, Visual servoing",

author = "Wanyu Ma and Jihong Zhu and David Navarro-Alarcon",

year = "2022",

doi = "10.1007/978-3-030-95892-3_40",

language = "English",

isbn = "978-3-030-95891-6",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer",

pages = "518--531",

editor = "{Ang Jr}, {Marcelo H.} and Hajime Asama and Wei Lin and Shaohui Foong",

booktitle = "Intelligent Autonomous Systems 16",

note = "16th International Conference on Intelligent Autonomous Systems, IAS-16 2020 ; Conference date: 22-06-2021 Through 25-06-2021",

}

Ma, W, Zhu, J & Navarro-Alarcon, D 2022, Shape Control of Elastic Objects Based on Implicit Sensorimotor Models and Data-Driven Geometric Features. in MH Ang Jr, H Asama, W Lin & S Foong (eds), Intelligent Autonomous Systems 16 : Proceedings of the 16th International Conference, IAS-16. Lecture Notes in Networks and Systems, vol. 412 LNNS, Springer, pp. 518-531, 16th International Conference on Intelligent Autonomous Systems, IAS-16 2020, Virtual, Online, 22/06/21. https://doi.org/10.1007/978-3-030-95892-3_40

Shape Control of Elastic Objects Based on Implicit Sensorimotor Models and Data-Driven Geometric Features. / Ma, Wanyu; Zhu, Jihong; Navarro-Alarcon, David.
Intelligent Autonomous Systems 16 : Proceedings of the 16th International Conference, IAS-16. ed. / Marcelo H. Ang Jr; Hajime Asama; Wei Lin; Shaohui Foong. Springer, 2022. p. 518-531 (Lecture Notes in Networks and Systems; Vol. 412 LNNS).

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Shape Control of Elastic Objects Based on Implicit Sensorimotor Models and Data-Driven Geometric Features

AU - Ma, Wanyu

AU - Zhu, Jihong

AU - Navarro-Alarcon, David

PY - 2022

Y1 - 2022

N2 - This paper proposes a general approach to design automatic controls to manipulate elastic objects into desired shapes. The object’s geometric model is defined as the shape feature based on the specific task to globally describe the deformation. Raw visual feedback data is processed using classic regression methods to identify parameters of data-driven geometric models in real-time. Our proposed method is able to analytically compute a pose-shape Jacobian matrix based on implicit functions. This model is then used to derive a shape servoing controller. To validate the proposed method, we report a detailed experimental study with robotic manipulators deforming an elastic rod.

AB - This paper proposes a general approach to design automatic controls to manipulate elastic objects into desired shapes. The object’s geometric model is defined as the shape feature based on the specific task to globally describe the deformation. Raw visual feedback data is processed using classic regression methods to identify parameters of data-driven geometric models in real-time. Our proposed method is able to analytically compute a pose-shape Jacobian matrix based on implicit functions. This model is then used to derive a shape servoing controller. To validate the proposed method, we report a detailed experimental study with robotic manipulators deforming an elastic rod.

KW - Deformable objects

KW - Robotics

KW - Shape control

KW - Visual servoing

UR - http://www.scopus.com/inward/record.url?scp=85128758386&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-95892-3_40

DO - 10.1007/978-3-030-95892-3_40

M3 - Conference contribution

AN - SCOPUS:85128758386

SN - 978-3-030-95891-6

T3 - Lecture Notes in Networks and Systems

SP - 518

EP - 531

BT - Intelligent Autonomous Systems 16

A2 - Ang Jr, Marcelo H.

A2 - Asama, Hajime

A2 - Lin, Wei

A2 - Foong, Shaohui

PB - Springer

T2 - 16th International Conference on Intelligent Autonomous Systems, IAS-16 2020

Y2 - 22 June 2021 through 25 June 2021

ER -

Ma W, Zhu J, Navarro-Alarcon D. Shape Control of Elastic Objects Based on Implicit Sensorimotor Models and Data-Driven Geometric Features. In Ang Jr MH, Asama H, Lin W, Foong S, editors, Intelligent Autonomous Systems 16 : Proceedings of the 16th International Conference, IAS-16. Springer. 2022. p. 518-531. (Lecture Notes in Networks and Systems). doi: 10.1007/978-3-030-95892-3_40

Shape Control of Elastic Objects Based on Implicit Sensorimotor Models and Data-Driven Geometric Features

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this