Object exploration using vision and active touch

Chuanyu Yang; Nathan Lepora

doi:10.1109/IROS.2017.8206542

Object exploration using vision and active touch

Chuanyu Yang, Nathan Lepora

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

9 Citations (Scopus)

420 Downloads (Pure)

Abstract

Achieving object exploration with passive vision and active touch has been under investigation for thirty years. We build upon recent progress in biomimetic active touch that combines perception via Bayesian evidence accumulation with controlling the tactile sensor using perceived stimulus location. Here, passive vision is combined with active touch by providing a visual prior for each perceptual decision, with the precision of this prior setting the relative contribution of each modality. The performance is examined on an edge following task using a tactile fingertip (the TacTip) mounted on a robot arm. We find that the quality of exploration is a U-shaped function of the relative contribution of vision and touch; moreover, multi-modal performance is more robust, completing the contour when touch alone fails. The overall system has several parallels with biological theories of perception, and thus plausibly represents a robot model of visuo-tactile exploration in humans.

Original language	English
Title of host publication	2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2017)
Subtitle of host publication	Proceedings of a meeting held 24-28 September 2017, Vancouver, British Columbia, Canada
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	6363-6386
Number of pages	8
ISBN (Electronic)	9781538626825
ISBN (Print)	9781538626832
DOIs	https://doi.org/10.1109/IROS.2017.8206542
Publication status	Published - Feb 2018
Event	Intelligent Robots and Systems - Vancouver, Canada Duration: 25 Sept 2017 → …

Publication series

Name
ISSN (Print)	2153-0866

Conference

Conference	Intelligent Robots and Systems
Abbreviated title	IROS
Country/Territory	Canada
City	Vancouver
Period	25/09/17 → …

Access to Document

10.1109/IROS.2017.8206542

Full-text PDF (accepted author manuscript)
This is the author accepted manuscript (AAM). The final published version (version of record) is available online via IEEE at http://ieeexplore.ieee.org/document/8206542/ . Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 2.1 MB

Handle.net

Persistent link

Tactile Superresolution Sensing
Lepora, N. F. (Principal Investigator)
1/11/15 → 30/06/17
Project: Research

Object exploration using vision and active touch
Pestell, N. (Creator), Giannaccini, M. E. (Creator), Ward-Cherrier, B. (Creator), Roscow, E. (Creator), Aquilina, K. (Creator), Cramphorn, L. (Creator) & Lepora, N. (Creator), University of Bristol, 26 Jul 2017
DOI: 10.5523/bris.u5035xp7vnbd2m2n1f3o7fg7g, http://data.bris.ac.uk/data/dataset/u5035xp7vnbd2m2n1f3o7fg7g
Dataset

Cite this

Yang, C., & Lepora, N. (2018). Object exploration using vision and active touch. In 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2017): Proceedings of a meeting held 24-28 September 2017, Vancouver, British Columbia, Canada (pp. 6363-6386). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/IROS.2017.8206542

@inproceedings{d31f18984e9d44d09632aac147b5b39e,

title = "Object exploration using vision and active touch",

abstract = "Achieving object exploration with passive vision and active touch has been under investigation for thirty years. We build upon recent progress in biomimetic active touch that combines perception via Bayesian evidence accumulation with controlling the tactile sensor using perceived stimulus location. Here, passive vision is combined with active touch by providing a visual prior for each perceptual decision, with the precision of this prior setting the relative contribution of each modality. The performance is examined on an edge following task using a tactile fingertip (the TacTip) mounted on a robot arm. We find that the quality of exploration is a U-shaped function of the relative contribution of vision and touch; moreover, multi-modal performance is more robust, completing the contour when touch alone fails. The overall system has several parallels with biological theories of perception, and thus plausibly represents a robot model of visuo-tactile exploration in humans.",

author = "Chuanyu Yang and Nathan Lepora",

year = "2018",

month = feb,

doi = "10.1109/IROS.2017.8206542",

language = "English",

isbn = "9781538626832",

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

pages = "6363--6386",

booktitle = "2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2017)",

address = "United States",

note = "Intelligent Robots and Systems, IROS ; Conference date: 25-09-2017",

}

Yang, C & Lepora, N 2018, Object exploration using vision and active touch. in 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2017): Proceedings of a meeting held 24-28 September 2017, Vancouver, British Columbia, Canada. Institute of Electrical and Electronics Engineers (IEEE), pp. 6363-6386, Intelligent Robots and Systems, Vancouver, Canada, 25/09/17. https://doi.org/10.1109/IROS.2017.8206542

Object exploration using vision and active touch. / Yang, Chuanyu; Lepora, Nathan.
2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2017): Proceedings of a meeting held 24-28 September 2017, Vancouver, British Columbia, Canada. Institute of Electrical and Electronics Engineers (IEEE), 2018. p. 6363-6386.

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Object exploration using vision and active touch

AU - Yang, Chuanyu

AU - Lepora, Nathan

PY - 2018/2

Y1 - 2018/2

N2 - Achieving object exploration with passive vision and active touch has been under investigation for thirty years. We build upon recent progress in biomimetic active touch that combines perception via Bayesian evidence accumulation with controlling the tactile sensor using perceived stimulus location. Here, passive vision is combined with active touch by providing a visual prior for each perceptual decision, with the precision of this prior setting the relative contribution of each modality. The performance is examined on an edge following task using a tactile fingertip (the TacTip) mounted on a robot arm. We find that the quality of exploration is a U-shaped function of the relative contribution of vision and touch; moreover, multi-modal performance is more robust, completing the contour when touch alone fails. The overall system has several parallels with biological theories of perception, and thus plausibly represents a robot model of visuo-tactile exploration in humans.

AB - Achieving object exploration with passive vision and active touch has been under investigation for thirty years. We build upon recent progress in biomimetic active touch that combines perception via Bayesian evidence accumulation with controlling the tactile sensor using perceived stimulus location. Here, passive vision is combined with active touch by providing a visual prior for each perceptual decision, with the precision of this prior setting the relative contribution of each modality. The performance is examined on an edge following task using a tactile fingertip (the TacTip) mounted on a robot arm. We find that the quality of exploration is a U-shaped function of the relative contribution of vision and touch; moreover, multi-modal performance is more robust, completing the contour when touch alone fails. The overall system has several parallels with biological theories of perception, and thus plausibly represents a robot model of visuo-tactile exploration in humans.

U2 - 10.1109/IROS.2017.8206542

DO - 10.1109/IROS.2017.8206542

M3 - Conference Contribution (Conference Proceeding)

SN - 9781538626832

SP - 6363

EP - 6386

BT - 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2017)

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - Intelligent Robots and Systems

Y2 - 25 September 2017

ER -

Yang C, Lepora N. Object exploration using vision and active touch. In 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2017): Proceedings of a meeting held 24-28 September 2017, Vancouver, British Columbia, Canada. Institute of Electrical and Electronics Engineers (IEEE). 2018. p. 6363-6386 Epub 2017 Dec 14. doi: 10.1109/IROS.2017.8206542

Object exploration using vision and active touch

Abstract

Publication series

Conference

Access to Document

Handle.net

Fingerprint

Projects

Tactile Superresolution Sensing

Datasets

Object exploration using vision and active touch

Cite this