Genetic evolution of hierarchical behavior
structures
B. Woolley, and G. Peterson. GECCO '07: Proceedings of the 9th annual conference on
Genetic and evolutionary computation, 2, page 1731--1738. London, ACM Press, (7-11 July 2007)
Abstract
The development of coherent and dynamic behaviours for
mobile robots is an exceedingly complex endeavour ruled
by task objectives, environmental dynamics and the
interactions within the behavior structure. This paper
discusses the use of genetic programming techniques and
the unified behaviour framework to develop effective
control hierarchies using interchangeable behaviors and
arbitration components. Given the number of possible
variations provided by the framework, evolutionary
programming is used to evolve the overall behaviour
design. Competitive evolution of the behaviour
population incrementally develops feasible solutions
for the domain through competitive ranking. By
developing and implementing many simple behaviours
independently and then evolving a complex behaviour
structure suited to the domain, this approach allows
for the reuse of elemental behaviours and eases the
complexity of development for a given domain.
Additionally, this approach has the ability to locate a
behaviour structure which a developer may not have
previously considered, and whose ability exceeds
expectations. The evolution of the behaviour structure
is demonstrated using agents in the Robocode
environment, with the evolved structures performing up
to 122 percent better than one crafted by an expert.
GECCO '07: Proceedings of the 9th annual conference on
Genetic and evolutionary computation
year
2007
month
7-11 July
pages
1731--1738
publisher
ACM Press
volume
2
organisation
ACM SIGEVO (formerly ISGEC)
publisher_address
New York, NY, USA
isbn13
978-1-59593-697-4
notes
GECCO-2007 A joint meeting of the sixteenth
international conference on genetic algorithms
(ICGA-2007) and the twelfth annual genetic programming
conference (GP-2007).
ACM Order Number 910071
%0 Conference Paper
%1 1277296
%A Woolley, Brian G.
%A Peterson, Gilbert L.
%B GECCO '07: Proceedings of the 9th annual conference on
Genetic and evolutionary computation
%C London
%D 2007
%E Thierens, Dirk
%E Beyer, Hans-Georg
%E Bongard, Josh
%E Branke, Jurgen
%E Clark, John Andrew
%E Cliff, Dave
%E Congdon, Clare Bates
%E Deb, Kalyanmoy
%E Doerr, Benjamin
%E Kovacs, Tim
%E Kumar, Sanjeev
%E Miller, Julian F.
%E Moore, Jason
%E Neumann, Frank
%E Pelikan, Martin
%E Poli, Riccardo
%E Sastry, Kumara
%E Stanley, Kenneth Owen
%E Stutzle, Thomas
%E Watson, Richard A
%E Wegener, Ingo
%I ACM Press
%K algorithms, based behaviour evolutionary framework genetic programming, robotics, unified
%P 1731--1738
%T Genetic evolution of hierarchical behavior
structures
%U http://doi.acm.org/10.1145/1276958.1277296
%V 2
%X The development of coherent and dynamic behaviours for
mobile robots is an exceedingly complex endeavour ruled
by task objectives, environmental dynamics and the
interactions within the behavior structure. This paper
discusses the use of genetic programming techniques and
the unified behaviour framework to develop effective
control hierarchies using interchangeable behaviors and
arbitration components. Given the number of possible
variations provided by the framework, evolutionary
programming is used to evolve the overall behaviour
design. Competitive evolution of the behaviour
population incrementally develops feasible solutions
for the domain through competitive ranking. By
developing and implementing many simple behaviours
independently and then evolving a complex behaviour
structure suited to the domain, this approach allows
for the reuse of elemental behaviours and eases the
complexity of development for a given domain.
Additionally, this approach has the ability to locate a
behaviour structure which a developer may not have
previously considered, and whose ability exceeds
expectations. The evolution of the behaviour structure
is demonstrated using agents in the Robocode
environment, with the evolved structures performing up
to 122 percent better than one crafted by an expert.
@inproceedings{1277296,
abstract = {The development of coherent and dynamic behaviours for
mobile robots is an exceedingly complex endeavour ruled
by task objectives, environmental dynamics and the
interactions within the behavior structure. This paper
discusses the use of genetic programming techniques and
the unified behaviour framework to develop effective
control hierarchies using interchangeable behaviors and
arbitration components. Given the number of possible
variations provided by the framework, evolutionary
programming is used to evolve the overall behaviour
design. Competitive evolution of the behaviour
population incrementally develops feasible solutions
for the domain through competitive ranking. By
developing and implementing many simple behaviours
independently and then evolving a complex behaviour
structure suited to the domain, this approach allows
for the reuse of elemental behaviours and eases the
complexity of development for a given domain.
Additionally, this approach has the ability to locate a
behaviour structure which a developer may not have
previously considered, and whose ability exceeds
expectations. The evolution of the behaviour structure
is demonstrated using agents in the Robocode
environment, with the evolved structures performing up
to 122 percent better than one crafted by an expert.},
added-at = {2008-06-19T17:35:00.000+0200},
address = {London},
author = {Woolley, Brian G. and Peterson, Gilbert L.},
biburl = {https://www.bibsonomy.org/bibtex/248c961d876e54f3d5b3c187185d42c8c/brazovayeye},
booktitle = {GECCO '07: Proceedings of the 9th annual conference on
Genetic and evolutionary computation},
editor = {Thierens, Dirk and Beyer, Hans-Georg and Bongard, Josh and Branke, Jurgen and Clark, John Andrew and Cliff, Dave and Congdon, Clare Bates and Deb, Kalyanmoy and Doerr, Benjamin and Kovacs, Tim and Kumar, Sanjeev and Miller, Julian F. and Moore, Jason and Neumann, Frank and Pelikan, Martin and Poli, Riccardo and Sastry, Kumara and Stanley, Kenneth Owen and Stutzle, Thomas and Watson, Richard A and Wegener, Ingo},
interhash = {bd5b73522c3207ff7eba0017f1e4038b},
intrahash = {48c961d876e54f3d5b3c187185d42c8c},
isbn13 = {978-1-59593-697-4},
keywords = {algorithms, based behaviour evolutionary framework genetic programming, robotics, unified},
month = {7-11 July},
notes = {GECCO-2007 A joint meeting of the sixteenth
international conference on genetic algorithms
(ICGA-2007) and the twelfth annual genetic programming
conference (GP-2007).
ACM Order Number 910071},
organisation = {ACM SIGEVO (formerly ISGEC)},
pages = {1731--1738},
publisher = {ACM Press},
publisher_address = {New York, NY, USA},
timestamp = {2008-06-19T17:54:31.000+0200},
title = {Genetic evolution of hierarchical behavior
structures},
url = {http://doi.acm.org/10.1145/1276958.1277296},
volume = 2,
year = 2007
}