Estimation of position of a mobile robot using a neural net

C. S. Berger; L. Kleeman

doi:10.1109/TENCON.1992.271901

Estimation of position of a mobile robot using a neural net

C. S. Berger
, L. Kleeman

Electrical and Computer Systems Engineering

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

Abstract

An active beacon localization system is developed for estimating the position of a mobile robot. Six beacons transmit a pattern of ultrasonic pulses. A receiver on the robot logs the arrival times of the pulses. This information is used to train a new single stage neural network (the cerebellar model with interpolation, or CEINT) to track the robot position. This network converges rapidly and has modest storage requirements. Its performance over the test set shows that a more extensive training data set would yield improved performance. This underlines the main disadvantage of using neural nets, i.e., their performance depends on the properties of the training set.

Original language	English
Title of host publication	TENCON 1992 - Technology Enabling Tomorrow
Subtitle of host publication	Computers, Communications and Automation towards the 21st Century - 1992 IEEE Region 10 International Conference
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	468-472
Number of pages	5
ISBN (Electronic)	0780308492
DOIs	https://doi.org/10.1109/TENCON.1992.271901
Publication status	Published - 1 Jan 1992
Event	IEEE Tencon (IEEE Region 10 Conference) 1992 - Melbourne, Australia Duration: 11 Nov 1992 → 13 Nov 1992 https://ieeexplore.ieee.org/xpl/conhome/681/proceeding (Proceedings)

Publication series

Name	IEEE Region 10 Annual International Conference, Proceedings/TENCON
ISSN (Print)	2159-3442
ISSN (Electronic)	2159-3450

Conference

Conference	IEEE Tencon (IEEE Region 10 Conference) 1992
Abbreviated title	TENCON 1992
Country/Territory	Australia
City	Melbourne
Period	11/11/92 → 13/11/92
Internet address	https://ieeexplore.ieee.org/xpl/conhome/681/proceeding (Proceedings)

Access to Document

10.1109/TENCON.1992.271901

Cite this

Berger, C. S., & Kleeman, L. (1992). Estimation of position of a mobile robot using a neural net. In TENCON 1992 - Technology Enabling Tomorrow: Computers, Communications and Automation towards the 21st Century - 1992 IEEE Region 10 International Conference (pp. 468-472). Article 271901 (IEEE Region 10 Annual International Conference, Proceedings/TENCON). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/TENCON.1992.271901

Berger, C. S. ; Kleeman, L. / Estimation of position of a mobile robot using a neural net. TENCON 1992 - Technology Enabling Tomorrow: Computers, Communications and Automation towards the 21st Century - 1992 IEEE Region 10 International Conference. IEEE, Institute of Electrical and Electronics Engineers, 1992. pp. 468-472 (IEEE Region 10 Annual International Conference, Proceedings/TENCON).

@inproceedings{c4741ec9f25f4e4891e21c11afc89f5f,

title = "Estimation of position of a mobile robot using a neural net",

abstract = "An active beacon localization system is developed for estimating the position of a mobile robot. Six beacons transmit a pattern of ultrasonic pulses. A receiver on the robot logs the arrival times of the pulses. This information is used to train a new single stage neural network (the cerebellar model with interpolation, or CEINT) to track the robot position. This network converges rapidly and has modest storage requirements. Its performance over the test set shows that a more extensive training data set would yield improved performance. This underlines the main disadvantage of using neural nets, i.e., their performance depends on the properties of the training set.",

author = "Berger, \{C. S.\} and L. Kleeman",

year = "1992",

month = jan,

day = "1",

doi = "10.1109/TENCON.1992.271901",

language = "English",

series = "IEEE Region 10 Annual International Conference, Proceedings/TENCON",

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

pages = "468--472",

booktitle = "TENCON 1992 - Technology Enabling Tomorrow",

address = "United States of America",

note = "IEEE Tencon (IEEE Region 10 Conference) 1992, TENCON 1992 ; Conference date: 11-11-1992 Through 13-11-1992",

url = "https://ieeexplore.ieee.org/xpl/conhome/681/proceeding",

}

Berger, CS & Kleeman, L 1992, Estimation of position of a mobile robot using a neural net. in TENCON 1992 - Technology Enabling Tomorrow: Computers, Communications and Automation towards the 21st Century - 1992 IEEE Region 10 International Conference., 271901, IEEE Region 10 Annual International Conference, Proceedings/TENCON, IEEE, Institute of Electrical and Electronics Engineers, pp. 468-472, IEEE Tencon (IEEE Region 10 Conference) 1992, Melbourne, Victoria, Australia, 11/11/92. https://doi.org/10.1109/TENCON.1992.271901

Estimation of position of a mobile robot using a neural net. / Berger, C. S.; Kleeman, L.
TENCON 1992 - Technology Enabling Tomorrow: Computers, Communications and Automation towards the 21st Century - 1992 IEEE Region 10 International Conference. IEEE, Institute of Electrical and Electronics Engineers, 1992. p. 468-472 271901 (IEEE Region 10 Annual International Conference, Proceedings/TENCON).

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

TY - GEN

T1 - Estimation of position of a mobile robot using a neural net

AU - Berger, C. S.

AU - Kleeman, L.

PY - 1992/1/1

Y1 - 1992/1/1

N2 - An active beacon localization system is developed for estimating the position of a mobile robot. Six beacons transmit a pattern of ultrasonic pulses. A receiver on the robot logs the arrival times of the pulses. This information is used to train a new single stage neural network (the cerebellar model with interpolation, or CEINT) to track the robot position. This network converges rapidly and has modest storage requirements. Its performance over the test set shows that a more extensive training data set would yield improved performance. This underlines the main disadvantage of using neural nets, i.e., their performance depends on the properties of the training set.

AB - An active beacon localization system is developed for estimating the position of a mobile robot. Six beacons transmit a pattern of ultrasonic pulses. A receiver on the robot logs the arrival times of the pulses. This information is used to train a new single stage neural network (the cerebellar model with interpolation, or CEINT) to track the robot position. This network converges rapidly and has modest storage requirements. Its performance over the test set shows that a more extensive training data set would yield improved performance. This underlines the main disadvantage of using neural nets, i.e., their performance depends on the properties of the training set.

UR - https://www.scopus.com/pages/publications/85066907463

U2 - 10.1109/TENCON.1992.271901

DO - 10.1109/TENCON.1992.271901

M3 - Conference Paper

AN - SCOPUS:85066907463

T3 - IEEE Region 10 Annual International Conference, Proceedings/TENCON

SP - 468

EP - 472

BT - TENCON 1992 - Technology Enabling Tomorrow

PB - IEEE, Institute of Electrical and Electronics Engineers

T2 - IEEE Tencon (IEEE Region 10 Conference) 1992

Y2 - 11 November 1992 through 13 November 1992

ER -

Berger CS, Kleeman L. Estimation of position of a mobile robot using a neural net. In TENCON 1992 - Technology Enabling Tomorrow: Computers, Communications and Automation towards the 21st Century - 1992 IEEE Region 10 International Conference. IEEE, Institute of Electrical and Electronics Engineers. 1992. p. 468-472. 271901. (IEEE Region 10 Annual International Conference, Proceedings/TENCON). doi: 10.1109/TENCON.1992.271901

Estimation of position of a mobile robot using a neural net

Abstract

Publication series

Conference

Access to Document

Other files and links

Cite this