Experiments in evolutionary synthesis of robotic neurocontrollers

Karthik Balakrishnan, Vasant Honavar

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Recurrent networks are proposed for designing neurocontrollers in robotic control systems. An evolutionary algorithm is used to develop a neurocontroller for a robot clearing an arena by pushing boxes to the enclosing walls. The number of boxes that the robot pushes to the walls, within an allocated time, is the measure of its fitness. The initially feedforward networks evolve and produce high fitness neurocontrollers with 30% (and sometimes even 70%) fewer recurrent links compared to networks fully recurrent from the start.

Original languageEnglish (US)
Title of host publicationProceedings of the National Conference on Artificial Intelligence
Editors Anon
PublisherAAAI
Pages1378
Number of pages1
Volume2
StatePublished - 1996
EventProceedings of the 1996 13th National Conference on Artificial Intelligence. Part 2 (of 2) - Portland, OR, USA
Duration: Aug 4 1996Aug 8 1996

Other

OtherProceedings of the 1996 13th National Conference on Artificial Intelligence. Part 2 (of 2)
CityPortland, OR, USA
Period8/4/968/8/96

Fingerprint

Robotics
Robots
Evolutionary algorithms
Experiments
Control systems

All Science Journal Classification (ASJC) codes

  • Software

Cite this

Balakrishnan, K., & Honavar, V. (1996). Experiments in evolutionary synthesis of robotic neurocontrollers. In Anon (Ed.), Proceedings of the National Conference on Artificial Intelligence (Vol. 2, pp. 1378). AAAI.
Balakrishnan, Karthik ; Honavar, Vasant. / Experiments in evolutionary synthesis of robotic neurocontrollers. Proceedings of the National Conference on Artificial Intelligence. editor / Anon. Vol. 2 AAAI, 1996. pp. 1378
@inproceedings{9ad84da929ee4967bb4581b6ea81b565,
title = "Experiments in evolutionary synthesis of robotic neurocontrollers",
abstract = "Recurrent networks are proposed for designing neurocontrollers in robotic control systems. An evolutionary algorithm is used to develop a neurocontroller for a robot clearing an arena by pushing boxes to the enclosing walls. The number of boxes that the robot pushes to the walls, within an allocated time, is the measure of its fitness. The initially feedforward networks evolve and produce high fitness neurocontrollers with 30{\%} (and sometimes even 70{\%}) fewer recurrent links compared to networks fully recurrent from the start.",
author = "Karthik Balakrishnan and Vasant Honavar",
year = "1996",
language = "English (US)",
volume = "2",
pages = "1378",
editor = "Anon",
booktitle = "Proceedings of the National Conference on Artificial Intelligence",
publisher = "AAAI",

}

Balakrishnan, K & Honavar, V 1996, Experiments in evolutionary synthesis of robotic neurocontrollers. in Anon (ed.), Proceedings of the National Conference on Artificial Intelligence. vol. 2, AAAI, pp. 1378, Proceedings of the 1996 13th National Conference on Artificial Intelligence. Part 2 (of 2), Portland, OR, USA, 8/4/96.

Experiments in evolutionary synthesis of robotic neurocontrollers. / Balakrishnan, Karthik; Honavar, Vasant.

Proceedings of the National Conference on Artificial Intelligence. ed. / Anon. Vol. 2 AAAI, 1996. p. 1378.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Experiments in evolutionary synthesis of robotic neurocontrollers

AU - Balakrishnan, Karthik

AU - Honavar, Vasant

PY - 1996

Y1 - 1996

N2 - Recurrent networks are proposed for designing neurocontrollers in robotic control systems. An evolutionary algorithm is used to develop a neurocontroller for a robot clearing an arena by pushing boxes to the enclosing walls. The number of boxes that the robot pushes to the walls, within an allocated time, is the measure of its fitness. The initially feedforward networks evolve and produce high fitness neurocontrollers with 30% (and sometimes even 70%) fewer recurrent links compared to networks fully recurrent from the start.

AB - Recurrent networks are proposed for designing neurocontrollers in robotic control systems. An evolutionary algorithm is used to develop a neurocontroller for a robot clearing an arena by pushing boxes to the enclosing walls. The number of boxes that the robot pushes to the walls, within an allocated time, is the measure of its fitness. The initially feedforward networks evolve and produce high fitness neurocontrollers with 30% (and sometimes even 70%) fewer recurrent links compared to networks fully recurrent from the start.

UR - http://www.scopus.com/inward/record.url?scp=0030374844&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030374844&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0030374844

VL - 2

SP - 1378

BT - Proceedings of the National Conference on Artificial Intelligence

A2 - Anon, null

PB - AAAI

ER -

Balakrishnan K, Honavar V. Experiments in evolutionary synthesis of robotic neurocontrollers. In Anon, editor, Proceedings of the National Conference on Artificial Intelligence. Vol. 2. AAAI. 1996. p. 1378