Bayesian tactile object recognition: learning and recognising objects using a new inexpensive tactile sensor

Tadeo Corradi; Peter Hall; Pejman Iravani

doi:10.1109/ICRA.2015.7139744

Bayesian tactile object recognition: learning and recognising objects using a new inexpensive tactile sensor

Tadeo Corradi, Peter Hall, Pejman Iravani

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

20 Citations (SciVal)

385 Downloads (Pure)

Abstract

We present a Bayesian approach to tactile object recognition that improves on state-of-the-art in using single-touch events in two ways. First by improving recognition accuracy from about 90\% to about 95\%, using about half the number of touches. Second by reducing the number of touches needed for training from about 200 to about 60. In addition, we use a new tactile sensor that is less than one tenth of the cost of widely available sensors. The paper describes the sensor, the likelihood function used with the Naive Bayes classifier, and experiments on a set of ten real objects. We also provide preliminary results to test our approach for its ability to generalise to previously unencountered objects.

Original language	English
Title of host publication	2015 IEEE International Conference on Robotics and Automation (ICRA)
Publisher	IEEE
Pages	3909-3914
Number of pages	6
ISBN (Electronic)	978-1-4799-6923-4
DOIs	https://doi.org/10.1109/ICRA.2015.7139744
Publication status	Published - 2 Jul 2015
Event	IEEE Interational Conference on Robotics and Automation (ICRA) 2015 - Washington, Seattle, USA United States Duration: 26 May 2015 → 30 May 2015

Publication series

Name	Proceedings / IEEE International Conference on Robotics and Automation.
Publisher	IEEE
ISSN (Print)	1050-4729

Conference

Conference	IEEE Interational Conference on Robotics and Automation (ICRA) 2015
Country/Territory	USA United States
City	Seattle
Period	26/05/15 → 30/05/15

Keywords

tactile sensing
object recognition
Bayesian
Robotics

Access to Document

10.1109/ICRA.2015.7139744

Bayesian Tactile Object RecognitionSubmitted manuscript, 1.85 MB

Cite this

Bayesian tactile object recognition: learning and recognising objects using a new inexpensive tactile sensor. / Corradi, Tadeo; Hall, Peter; Iravani, Pejman.
2015 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2015. p. 3909-3914 (Proceedings / IEEE International Conference on Robotics and Automation.).

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

Corradi, T, Hall, P & Iravani, P 2015, Bayesian tactile object recognition: learning and recognising objects using a new inexpensive tactile sensor. in 2015 IEEE International Conference on Robotics and Automation (ICRA). Proceedings / IEEE International Conference on Robotics and Automation., IEEE, pp. 3909-3914, IEEE Interational Conference on Robotics and Automation (ICRA) 2015, Seattle, USA United States, 26/05/15. https://doi.org/10.1109/ICRA.2015.7139744

@inproceedings{24ccfde93b2e42109c8c29509997043c,

title = "Bayesian tactile object recognition: learning and recognising objects using a new inexpensive tactile sensor",

abstract = "We present a Bayesian approach to tactile object recognition that improves on state-of-the-art in using single-touch events in two ways. First by improving recognition accuracy from about 90\textbackslash{}\% to about 95\textbackslash{}\%, using about half the number of touches. Second by reducing the number of touches needed for training from about 200 to about 60. In addition, we use a new tactile sensor that is less than one tenth of the cost of widely available sensors. The paper describes the sensor, the likelihood function used with the Naive Bayes classifier, and experiments on a set of ten real objects. We also provide preliminary results to test our approach for its ability to generalise to previously unencountered objects. ",

keywords = "tactile sensing, object recognition, Bayesian, Robotics",

author = "Tadeo Corradi and Peter Hall and Pejman Iravani",

year = "2015",

month = jul,

day = "2",

doi = "10.1109/ICRA.2015.7139744",

language = "English",

series = "Proceedings / IEEE International Conference on Robotics and Automation.",

publisher = "IEEE",

pages = "3909--3914",

booktitle = "2015 IEEE International Conference on Robotics and Automation (ICRA)",

address = "USA United States",

note = "IEEE Interational Conference on Robotics and Automation (ICRA) 2015 ; Conference date: 26-05-2015 Through 30-05-2015",

}

TY - GEN

T1 - Bayesian tactile object recognition

T2 - IEEE Interational Conference on Robotics and Automation (ICRA) 2015

AU - Corradi, Tadeo

AU - Hall, Peter

AU - Iravani, Pejman

PY - 2015/7/2

Y1 - 2015/7/2

N2 - We present a Bayesian approach to tactile object recognition that improves on state-of-the-art in using single-touch events in two ways. First by improving recognition accuracy from about 90\% to about 95\%, using about half the number of touches. Second by reducing the number of touches needed for training from about 200 to about 60. In addition, we use a new tactile sensor that is less than one tenth of the cost of widely available sensors. The paper describes the sensor, the likelihood function used with the Naive Bayes classifier, and experiments on a set of ten real objects. We also provide preliminary results to test our approach for its ability to generalise to previously unencountered objects.

AB - We present a Bayesian approach to tactile object recognition that improves on state-of-the-art in using single-touch events in two ways. First by improving recognition accuracy from about 90\% to about 95\%, using about half the number of touches. Second by reducing the number of touches needed for training from about 200 to about 60. In addition, we use a new tactile sensor that is less than one tenth of the cost of widely available sensors. The paper describes the sensor, the likelihood function used with the Naive Bayes classifier, and experiments on a set of ten real objects. We also provide preliminary results to test our approach for its ability to generalise to previously unencountered objects.

KW - tactile sensing

KW - object recognition

KW - Bayesian

KW - Robotics

UR - https://www.scopus.com/pages/publications/84938270160

U2 - 10.1109/ICRA.2015.7139744

DO - 10.1109/ICRA.2015.7139744

M3 - Chapter in a published conference proceeding

T3 - Proceedings / IEEE International Conference on Robotics and Automation.

SP - 3909

EP - 3914

BT - 2015 IEEE International Conference on Robotics and Automation (ICRA)

PB - IEEE

Y2 - 26 May 2015 through 30 May 2015

ER -

Bayesian tactile object recognition: learning and recognising objects using a new inexpensive tactile sensor

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Peter Hall

Cite this

Bayesian tactile object recognition: learning and recognising objects using a new inexpensive tactile sensor

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Profiles

Peter Hall

Cite this