Auditory robotic tracking of sound sources using hybrid cross-correlation and recurrent networks

John Murray; Stefan Wermter; Harry Erwin

doi:10.1109/IROS.2005.1545093

Auditory robotic tracking of sound sources using hybrid cross-correlation and recurrent networks

John Murray, Stefan Wermter, Harry Erwin

University of Sunderland

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

17 Citations (Scopus)

Abstract

This paper describes an auditory robotic system capable of computing the angle of incidence of a sound source on the horizontal plane (azimuth). The system, with the use of an Elman type recurrent neural network (RNN), is able to dynamically track this sound source as it changes azimuthally within the environment. The RNN is used to enable fast tracking responses to the overall system over a set time, as opposed to waiting for the next sound position before moving. The system is first tested in a simulated environment and then these results are compared with testing on the robotic system. The results show that the development of a hybrid system incorporating cross-correlation and recurrent neural networks is an effective mechanism for the control of a robot that tracks sound sources azimuthally.

Original language	English
Title of host publication	2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2005
Publisher	IEEE Computer Society
Pages	3554-3559
Number of pages	6
ISBN (Print)	0780389123
DOIs	https://doi.org/10.1109/IROS.2005.1545093
Publication status	Published - 5 Dec 2005
Externally published	Yes
Event	2005 IEEE/RSJ International Conference on Intelligent Robots and Systems - Edmonton, Canada Duration: 2 Aug 2005 → 6 Aug 2005 https://ieeexplore.ieee.org/xpl/conhome/10375/proceeding

Publication series

Name	IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS
Publisher	IEEE
ISSN (Print)	2153-0858
ISSN (Electronic)	2153-0866

Conference

Conference	2005 IEEE/RSJ International Conference on Intelligent Robots and Systems
Abbreviated title	IROS 2005
Country/Territory	Canada
City	Edmonton
Period	2/08/05 → 6/08/05
Internet address	https://ieeexplore.ieee.org/xpl/conhome/10375/proceeding

Access to Document

10.1109/IROS.2005.1545093Licence: Unspecified

Cite this

Murray, J., Wermter, S., & Erwin, H. (2005). Auditory robotic tracking of sound sources using hybrid cross-correlation and recurrent networks. In 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2005 (pp. 3554-3559). Article 1545093 (IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS). IEEE Computer Society. https://doi.org/10.1109/IROS.2005.1545093

@inproceedings{af3afafe451749ad9b80f5dc3f47bdff,

title = "Auditory robotic tracking of sound sources using hybrid cross-correlation and recurrent networks",

abstract = "This paper describes an auditory robotic system capable of computing the angle of incidence of a sound source on the horizontal plane (azimuth). The system, with the use of an Elman type recurrent neural network (RNN), is able to dynamically track this sound source as it changes azimuthally within the environment. The RNN is used to enable fast tracking responses to the overall system over a set time, as opposed to waiting for the next sound position before moving. The system is first tested in a simulated environment and then these results are compared with testing on the robotic system. The results show that the development of a hybrid system incorporating cross-correlation and recurrent neural networks is an effective mechanism for the control of a robot that tracks sound sources azimuthally.",

keywords = "Cross-correlation, Prediction, Robotics, Sound source, Tracking",

author = "John Murray and Stefan Wermter and Harry Erwin",

year = "2005",

month = dec,

day = "5",

doi = "10.1109/IROS.2005.1545093",

language = "English",

isbn = "0780389123",

series = "IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS",

publisher = "IEEE Computer Society",

pages = "3554--3559",

booktitle = "2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2005",

address = "United States",

note = "2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2005 ; Conference date: 02-08-2005 Through 06-08-2005",

url = "https://ieeexplore.ieee.org/xpl/conhome/10375/proceeding",

}

Murray, J, Wermter, S & Erwin, H 2005, Auditory robotic tracking of sound sources using hybrid cross-correlation and recurrent networks. in 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2005., 1545093, IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS, IEEE Computer Society, pp. 3554-3559, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, Edmonton, Alberta, Canada, 2/08/05. https://doi.org/10.1109/IROS.2005.1545093

Auditory robotic tracking of sound sources using hybrid cross-correlation and recurrent networks. / Murray, John; Wermter, Stefan; Erwin, Harry.
2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2005. IEEE Computer Society, 2005. p. 3554-3559 1545093 (IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS).

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

TY - GEN

T1 - Auditory robotic tracking of sound sources using hybrid cross-correlation and recurrent networks

AU - Murray, John

AU - Wermter, Stefan

AU - Erwin, Harry

PY - 2005/12/5

Y1 - 2005/12/5

N2 - This paper describes an auditory robotic system capable of computing the angle of incidence of a sound source on the horizontal plane (azimuth). The system, with the use of an Elman type recurrent neural network (RNN), is able to dynamically track this sound source as it changes azimuthally within the environment. The RNN is used to enable fast tracking responses to the overall system over a set time, as opposed to waiting for the next sound position before moving. The system is first tested in a simulated environment and then these results are compared with testing on the robotic system. The results show that the development of a hybrid system incorporating cross-correlation and recurrent neural networks is an effective mechanism for the control of a robot that tracks sound sources azimuthally.

AB - This paper describes an auditory robotic system capable of computing the angle of incidence of a sound source on the horizontal plane (azimuth). The system, with the use of an Elman type recurrent neural network (RNN), is able to dynamically track this sound source as it changes azimuthally within the environment. The RNN is used to enable fast tracking responses to the overall system over a set time, as opposed to waiting for the next sound position before moving. The system is first tested in a simulated environment and then these results are compared with testing on the robotic system. The results show that the development of a hybrid system incorporating cross-correlation and recurrent neural networks is an effective mechanism for the control of a robot that tracks sound sources azimuthally.

KW - Cross-correlation

KW - Prediction

KW - Robotics

KW - Sound source

KW - Tracking

UR - https://www.scopus.com/pages/publications/34250665582

U2 - 10.1109/IROS.2005.1545093

DO - 10.1109/IROS.2005.1545093

M3 - Conference contribution

AN - SCOPUS:34250665582

SN - 0780389123

T3 - IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS

SP - 3554

EP - 3559

BT - 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2005

PB - IEEE Computer Society

T2 - 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems

Y2 - 2 August 2005 through 6 August 2005

ER -

Murray J, Wermter S, Erwin H. Auditory robotic tracking of sound sources using hybrid cross-correlation and recurrent networks. In 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2005. IEEE Computer Society. 2005. p. 3554-3559. 1545093. (IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS). doi: 10.1109/IROS.2005.1545093

Auditory robotic tracking of sound sources using hybrid cross-correlation and recurrent networks

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this