Model-Free Precise in-Hand Manipulation with a 3D-Printed Tactile Gripper

Ben Ward-Cherrier; Nicolas Rojas; Nathan Lepora

doi:10.1109/LRA.2017.2719761

Model-Free Precise in-Hand Manipulation with a 3D-Printed Tactile Gripper

Ben Ward-Cherrier, Nicolas Rojas, Nathan Lepora

Research output: Contribution to journal › Article (Academic Journal)

19 Citations (Scopus)

279 Downloads (Pure)

Abstract

The use of tactile feedback for precision manipulation in robotics still lags far behind human capabilities. This study has two principal aims: 1) to demonstrate in-hand reorientation of grasped objects through active tactile manipulation; and 2) to present the development of a novel TacTip sensor and a GR2 gripper platform for tactile manipulation. Through the use of Bayesian active perception algorithms, the system successfully achieved inhand reorientation of cylinders of different diameters (20, 25, 30, and 35 mm) using tactile feedback. Average orientation errors along manipulation trajectories were below 5° for all cylinders with reorientation ranges varying from 42° to 67°. We also demonstrated an improvement in active tactile manipulation accuracy when using additional training data. Our methods for active tactile manipulation with the GR2 TacTip gripper are model free, can be used to investigate principles of dexterous manipulation, and could lead to essential advances in the areas of robotic tactile manipulation and teleoperated robots.

Original language	English
Article number	7959088
Pages (from-to)	2056-2063
Number of pages	8
Journal	IEEE Robotics and Automation Letters
Volume	2
Issue number	4
Early online date	26 Jun 2017
DOIs	https://doi.org/10.1109/LRA.2017.2719761
Publication status	Published - Oct 2017

Keywords

Dexterous manipulation
force and tactile sensing
grippers and other end-effectors

Access to Document

10.1109/LRA.2017.2719761

Full-text PDF (final published version)
This is the final published version of the article (version of record). It first appeared online via IEEE at http://ieeexplore.ieee.org/document/7959088/ . Please refer to any applicable terms of use of the publisher.
Final published version, 3.11 MBLicence: CC BY

Embargoed Document

Full-text PDF (accepted author manuscript)
Accepted author manuscript, 4.31 MB
Request copy

Fingerprint Dive into the research topics of 'Model-Free Precise in-Hand Manipulation with a 3D-Printed Tactile Gripper'. Together they form a unique fingerprint.

Projects

1 Finished

Tactile Superresolution Sensing

Lepora, N. F.

1/11/15 → 30/06/17

Project: Research

Datasets

Model-free precise in-hand manipulation with a 3d-printed tactile gripper

Lepora, N. F. (Creator), Ward-Cherrier, B. (Creator) & Rojas, N. (Contributor), University of Bristol, 16 Jun 2017

DOI: 10.5523/bris.39s7vsflucpqm2htfr3vo5bg62, http://data.bris.ac.uk/data/dataset/39s7vsflucpqm2htfr3vo5bg62

Dataset

Profiles

Mr Ben Ward-Cherrier

b.ward-cherrier@bristol.ac.uk

Department of Engineering Mathematics - Vice Chancellor's Fellow

Person: Academic

Cite this

Ward-Cherrier, B., Rojas, N., & Lepora, N. (2017). Model-Free Precise in-Hand Manipulation with a 3D-Printed Tactile Gripper. IEEE Robotics and Automation Letters, 2(4), 2056-2063. [7959088]. https://doi.org/10.1109/LRA.2017.2719761

@article{824aea7c7de7432b93242d82d5e3ecdf,

title = "Model-Free Precise in-Hand Manipulation with a 3D-Printed Tactile Gripper",

abstract = "The use of tactile feedback for precision manipulation in robotics still lags far behind human capabilities. This study has two principal aims: 1) to demonstrate in-hand reorientation of grasped objects through active tactile manipulation; and 2) to present the development of a novel TacTip sensor and a GR2 gripper platform for tactile manipulation. Through the use of Bayesian active perception algorithms, the system successfully achieved inhand reorientation of cylinders of different diameters (20, 25, 30, and 35 mm) using tactile feedback. Average orientation errors along manipulation trajectories were below 5° for all cylinders with reorientation ranges varying from 42° to 67°. We also demonstrated an improvement in active tactile manipulation accuracy when using additional training data. Our methods for active tactile manipulation with the GR2 TacTip gripper are model free, can be used to investigate principles of dexterous manipulation, and could lead to essential advances in the areas of robotic tactile manipulation and teleoperated robots.",

keywords = "Dexterous manipulation, force and tactile sensing, grippers and other end-effectors",

author = "Ben Ward-Cherrier and Nicolas Rojas and Nathan Lepora",

year = "2017",

month = oct,

doi = "10.1109/LRA.2017.2719761",

language = "English",

volume = "2",

pages = "2056--2063",

journal = "IEEE Robotics and Automation Letters",

issn = "2377-3766",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

number = "4",

}

TY - JOUR

T1 - Model-Free Precise in-Hand Manipulation with a 3D-Printed Tactile Gripper

AU - Ward-Cherrier, Ben

AU - Rojas, Nicolas

AU - Lepora, Nathan

PY - 2017/10

Y1 - 2017/10

N2 - The use of tactile feedback for precision manipulation in robotics still lags far behind human capabilities. This study has two principal aims: 1) to demonstrate in-hand reorientation of grasped objects through active tactile manipulation; and 2) to present the development of a novel TacTip sensor and a GR2 gripper platform for tactile manipulation. Through the use of Bayesian active perception algorithms, the system successfully achieved inhand reorientation of cylinders of different diameters (20, 25, 30, and 35 mm) using tactile feedback. Average orientation errors along manipulation trajectories were below 5° for all cylinders with reorientation ranges varying from 42° to 67°. We also demonstrated an improvement in active tactile manipulation accuracy when using additional training data. Our methods for active tactile manipulation with the GR2 TacTip gripper are model free, can be used to investigate principles of dexterous manipulation, and could lead to essential advances in the areas of robotic tactile manipulation and teleoperated robots.

AB - The use of tactile feedback for precision manipulation in robotics still lags far behind human capabilities. This study has two principal aims: 1) to demonstrate in-hand reorientation of grasped objects through active tactile manipulation; and 2) to present the development of a novel TacTip sensor and a GR2 gripper platform for tactile manipulation. Through the use of Bayesian active perception algorithms, the system successfully achieved inhand reorientation of cylinders of different diameters (20, 25, 30, and 35 mm) using tactile feedback. Average orientation errors along manipulation trajectories were below 5° for all cylinders with reorientation ranges varying from 42° to 67°. We also demonstrated an improvement in active tactile manipulation accuracy when using additional training data. Our methods for active tactile manipulation with the GR2 TacTip gripper are model free, can be used to investigate principles of dexterous manipulation, and could lead to essential advances in the areas of robotic tactile manipulation and teleoperated robots.

KW - Dexterous manipulation

KW - force and tactile sensing

KW - grippers and other end-effectors

U2 - 10.1109/LRA.2017.2719761

DO - 10.1109/LRA.2017.2719761

M3 - Article (Academic Journal)

VL - 2

SP - 2056

EP - 2063

JO - IEEE Robotics and Automation Letters

JF - IEEE Robotics and Automation Letters

SN - 2377-3766

IS - 4

M1 - 7959088

ER -