Evolving Controllers for Real Robots: A Survey of the Literature

Standard

Evolving Controllers for Real Robots: A Survey of the Literature. / Walker, Joanne Heather; Garrett, Simon Martin; Wilson, Myra Scott.

In: Adaptive Behavior, Vol. 11, No. 3, 2003, p. 179-203.

Research output: Contribution to journalArticlepeer-review

Author

Walker, Joanne Heather ; Garrett, Simon Martin ; Wilson, Myra Scott. / Evolving Controllers for Real Robots: A Survey of the Literature. In: Adaptive Behavior. 2003 ; Vol. 11, No. 3. pp. 179-203.

Bibtex - Download

@article{10bfff857c264e1bbe05c444fcabd584,
title = "Evolving Controllers for Real Robots: A Survey of the Literature",
abstract = "For many years, researchers in the field of mobile robotics have been investigating the use of genetic and evolutionary computation (GEC) to aid the development of mobile robot controllers. Alongside the fundamental choices of the GEC mechanism and its operators, which apply to both simulated and physical evolutionary robotics, other issues have emerged which are specific to the application of GEC to physical mobile robotics. This paper presents a survey of recent methods in GEC-developed mobile robot controllers, focusing on those methods that include a physical robot at some point in the learning loop. It simultaneously relates each of these methods to a framework of two orthogonal issues: the use of a simulated and/or a physical robot, and the use of finite, training phase evolution prior to a task and/or lifelong adaptation by evolution during a task. A list of evaluation criteria are presented and each of the surveyed methods are compared to them. Analyses of the framework and evaluation criteria suggest several possibilities; however, there appear to be particular advantages in combining simulated, training phase evolution (TPE) with lifelong adaptation by evolution (LAE) on a physical robot.",
keywords = "evolutionary robotics, physical robots, simulation, training, lifelong adaptation by evolution",
author = "Walker, {Joanne Heather} and Garrett, {Simon Martin} and Wilson, {Myra Scott}",
note = "Walker,J. and Garrett,S. and Wilson,M.S., 'Evolving Controllers for Real Robots: A Survey of the Literature', Adaptive Behavior, 2003, volume 11, number 3, pp 179--203, Sage",
year = "2003",
doi = "10.1177/1059712303113003",
language = "English",
volume = "11",
pages = "179--203",
journal = "Adaptive Behavior",
issn = "1059-7123",
publisher = "SAGE Publishing",
number = "3",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - Evolving Controllers for Real Robots: A Survey of the Literature

AU - Walker, Joanne Heather

AU - Garrett, Simon Martin

AU - Wilson, Myra Scott

N1 - Walker,J. and Garrett,S. and Wilson,M.S., 'Evolving Controllers for Real Robots: A Survey of the Literature', Adaptive Behavior, 2003, volume 11, number 3, pp 179--203, Sage

PY - 2003

Y1 - 2003

N2 - For many years, researchers in the field of mobile robotics have been investigating the use of genetic and evolutionary computation (GEC) to aid the development of mobile robot controllers. Alongside the fundamental choices of the GEC mechanism and its operators, which apply to both simulated and physical evolutionary robotics, other issues have emerged which are specific to the application of GEC to physical mobile robotics. This paper presents a survey of recent methods in GEC-developed mobile robot controllers, focusing on those methods that include a physical robot at some point in the learning loop. It simultaneously relates each of these methods to a framework of two orthogonal issues: the use of a simulated and/or a physical robot, and the use of finite, training phase evolution prior to a task and/or lifelong adaptation by evolution during a task. A list of evaluation criteria are presented and each of the surveyed methods are compared to them. Analyses of the framework and evaluation criteria suggest several possibilities; however, there appear to be particular advantages in combining simulated, training phase evolution (TPE) with lifelong adaptation by evolution (LAE) on a physical robot.

AB - For many years, researchers in the field of mobile robotics have been investigating the use of genetic and evolutionary computation (GEC) to aid the development of mobile robot controllers. Alongside the fundamental choices of the GEC mechanism and its operators, which apply to both simulated and physical evolutionary robotics, other issues have emerged which are specific to the application of GEC to physical mobile robotics. This paper presents a survey of recent methods in GEC-developed mobile robot controllers, focusing on those methods that include a physical robot at some point in the learning loop. It simultaneously relates each of these methods to a framework of two orthogonal issues: the use of a simulated and/or a physical robot, and the use of finite, training phase evolution prior to a task and/or lifelong adaptation by evolution during a task. A list of evaluation criteria are presented and each of the surveyed methods are compared to them. Analyses of the framework and evaluation criteria suggest several possibilities; however, there appear to be particular advantages in combining simulated, training phase evolution (TPE) with lifelong adaptation by evolution (LAE) on a physical robot.

KW - evolutionary robotics

KW - physical robots

KW - simulation

KW - training

KW - lifelong adaptation by evolution

U2 - 10.1177/1059712303113003

DO - 10.1177/1059712303113003

M3 - Article

VL - 11

SP - 179

EP - 203

JO - Adaptive Behavior

JF - Adaptive Behavior

SN - 1059-7123

IS - 3

ER -

View graph of relations
Citation formats