How Useful is Lifelong Evolution for Robotics

Joanne Heather Walker; Myra Scott Wilson

How Useful is Lifelong Evolution for Robotics

Joanne Heather Walker, Myra Scott Wilson

Department of Computer Science

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

Abstract

This paper investigates a system that uses a genetic algorithm to train a robot for a generalised test environment, then an evolutionary strategy to investigate the effect of continuing the evolution as the robot progresses with its task. The paper concludes that continuing evolution after a training phase has an important role to play in producing truly adaptive robots.

Original language	English
Title of host publication	From animals to animats 7
Subtitle of host publication	Proceedings of the Seventh International Conference on Simulation of Adaptive Behavior
Editors	B. Hallam, D. Floreano, J. Meyer, G. Hayes
Publisher	MIT Press
Pages	347-348
Number of pages	2
Edition	1
ISBN (Print)	9780262291170
Publication status	Published - 2002

Access to Document

Permanent link

Persistent link

Cite this

@inproceedings{4f788ad0dc224480a96086d91ac10b5e,

title = "How Useful is Lifelong Evolution for Robotics",

abstract = "This paper investigates a system that uses a genetic algorithm to train a robot for a generalised test environment, then an evolutionary strategy to investigate the effect of continuing the evolution as the robot progresses with its task. The paper concludes that continuing evolution after a training phase has an important role to play in producing truly adaptive robots.",

author = "Walker, \{Joanne Heather\} and Wilson, \{Myra Scott\}",

note = "Walker,J. and Wilson,M.S., 'How Useful is Lifelong Evolution for Robotics', Proceedings of the 7th International Conference on Simulation of Adaptive Behaviour, ed Hallam,B. and Floreano,D. and Hallam,J. and Hayes,G. and Meyer,J.A., pp 347-348, 2002, MIT Press",

year = "2002",

language = "English",

isbn = "9780262291170",

pages = "347--348",

editor = "B. Hallam and D. Floreano and J. Meyer and G. Hayes",

booktitle = "From animals to animats 7",

publisher = "MIT Press",

address = "United States of America",

edition = "1",

}

How Useful is Lifelong Evolution for Robotics. / Walker, Joanne Heather; Wilson, Myra Scott.
From animals to animats 7: Proceedings of the Seventh International Conference on Simulation of Adaptive Behavior. ed. / B. Hallam; D. Floreano; J. Meyer; G. Hayes. 1. ed. MIT Press, 2002. p. 347-348.

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

TY - GEN

T1 - How Useful is Lifelong Evolution for Robotics

AU - Walker, Joanne Heather

AU - Wilson, Myra Scott

N1 - Walker,J. and Wilson,M.S., 'How Useful is Lifelong Evolution for Robotics', Proceedings of the 7th International Conference on Simulation of Adaptive Behaviour, ed Hallam,B. and Floreano,D. and Hallam,J. and Hayes,G. and Meyer,J.A., pp 347-348, 2002, MIT Press

PY - 2002

Y1 - 2002

N2 - This paper investigates a system that uses a genetic algorithm to train a robot for a generalised test environment, then an evolutionary strategy to investigate the effect of continuing the evolution as the robot progresses with its task. The paper concludes that continuing evolution after a training phase has an important role to play in producing truly adaptive robots.

AB - This paper investigates a system that uses a genetic algorithm to train a robot for a generalised test environment, then an evolutionary strategy to investigate the effect of continuing the evolution as the robot progresses with its task. The paper concludes that continuing evolution after a training phase has an important role to play in producing truly adaptive robots.

M3 - Conference Proceeding (ISBN)

SN - 9780262291170

SP - 347

EP - 348

BT - From animals to animats 7

A2 - Hallam, B.

A2 - Floreano, D.

A2 - Meyer, J.

A2 - Hayes, G.

PB - MIT Press

ER -

How Useful is Lifelong Evolution for Robotics

Abstract

Access to Document

Permanent link

Fingerprint

Cite this