research-article

Evolution of vision capabilities in embodied virtual creatures

Authors:

Marcin L. Pilat,

Christian JacobAuthors Info & Claims

GECCO '10: Proceedings of the 12th annual conference on Genetic and evolutionary computation

Pages 95 - 102

https://doi.org/10.1145/1830483.1830502

Published: 07 July 2010 Publication History

Get Access

Abstract

We evolve light following behaviours in virtual creatures through neural network training using an incremental evolution approach. The neural controllers of creatures evolved for movement are augmented with simple visual neurons and neural connections. Using an evolutionary algorithm, the resulting creatures are trained to identify and follow a light source. Through this process, we are able to train the neural controllers to create various light following behaviours. Many of the evolved behaviours show stability and adaptiveness to environmental perturbations of body orientation.

References

[1]

J. Bongard. Behavior Chaining: Incremental Behavior Integration for Evolutionary Robotics. In Artificial Life XI, Cambridge, MA, 2008. MIT Press.

Google Scholar

[2]

R. A. Brooks. Intelligence without Representation. Artificial Intelligence, 47:139--159, January 1991.

Digital Library

Google Scholar

[3]

N. Chaumont, R. Egli, and C. Adami. Evolving Virtual Creatures and Catapults. Artificial Life, 13:139--157, 2007.

Digital Library

Google Scholar

[4]

A. L. Christensen and M. Dorigo. Incremental Evolution of Robot Controllers for a Highly Integrated Task. In Proceedings of The Ninth International Conference on the Simulation of Adaptive Behavior SAB'06, pages 473--484, Berlin, Germany, 2006. Springer-Verlag.

Digital Library

Google Scholar

[5]

M. Dorigo. SWARM-BOT: An experiment in swarm robotics. In P. Arabshahi and A. Martinoli, editors, Proceedings of SIS 2005 - 2005 IEEE Swarm Intelligence Symposium, pages 192--200, Piscataway, NJ, 2005. IEEE Press.

Crossref

Google Scholar

[6]

T. Miconi. Evosphere: Evolutionary Dynamics in a Population of Fighting Virtual Creatures. In CEC2008: Proceedings of the IEEE Congress on Evolutionary Computation, pages 3066--3073, 2008.

Crossref

Google Scholar

[7]

T. Miconi and A. Channon. An Improved System for Artificial Creatures Evolution. In e. a. L. M. Rocha, editor, ALIFE X: Proceedings of the 10th Conference on the Simulation and Synthesis of Living Systems. MIT Press, 2006.

Google Scholar

[8]

S. Nolfi and D. Parisi. Evolution of Artificial Neural Networks. In In Handbook of brain theory and neural networks, pages 418--421. MIT Press, 2002.

Google Scholar

[9]

M. L. Pilat. Morphid Academy: A Virtual Laboratory for Evolution of Form and Function. PhD thesis, University of Calgary, 2009.

Digital Library

Google Scholar

[10]

M. L. Pilat and C. Jacob. Creature Academy: A System for Virtual Creature Evolution. In CEC2008: Proceedings of the IEEE Congress on Evolutionary Computation, pages 3289--3297. IEEE Press, 2008.

Google Scholar

[11]

K. Sims. Evolving 3D Morphology and Behavior by Competition. Artificial Life IV: Proceedings of the Fourth International Workshop on the Synthesis and Simulation of Living Systems, 1(4):353--372, 1994.

Digital Library

Google Scholar

[12]

K. Sims. Evolving Virtual Creatures. In SIGGRAPH '94: Proceedings of the 21st annual conference on Computer graphics and interactive techniques, pages 15--22, New York, NY, USA, 1994. ACM Press.

Digital Library

Google Scholar

[13]

M. H. Wake. Bodies and Body Plans, and How They Came to Be. In W. J. Kress and G. W. Barrett, editors, A New Century of Biology, pages 29--52. Smithsonian Books, 2001.

Google Scholar

[14]

J. Walker, S. Garrett, and M. Wilson. Evolving controllers for real robots: A survey of the literature. Adaptive Behavior, 11(3):179--203, 2003.

Crossref

Google Scholar

Cited By

View all

Ito TPilat MSuzuki RArita T(2016)Population and evolutionary dynamics based on predator-prey relationships in a 3d physical simulationArtificial Life10.1162/ARTL_a_0020122:2(226-240)Online publication date: 1-May-2016
https://dl.acm.org/doi/10.1162/ARTL_a_00201
Chaumont NAdami C(2016)Evolution of sustained foraging in three-dimensional environments with physicsGenetic Programming and Evolvable Machines10.1007/s10710-016-9270-z17:4(359-390)Online publication date: 1-Dec-2016
https://dl.acm.org/doi/10.1007/s10710-016-9270-z
Lessin DFussell DMiikkulainen RAlba E(2013)Open-ended behavioral complexity for evolved virtual creaturesProceedings of the 15th annual conference on Genetic and evolutionary computation10.1145/2463372.2463411(335-342)Online publication date: 6-Jul-2013
https://dl.acm.org/doi/10.1145/2463372.2463411
Show More Cited By

Index Terms

Evolution of vision capabilities in embodied virtual creatures
1. Computing methodologies
  1. Artificial intelligence
  2. Machine learning
    1. Machine learning approaches
      1. Neural networks
2. Theory of computation
  1. Design and analysis of algorithms
    1. Algorithm design techniques
      1. Dynamic programming

Recommendations

Towards designing artificial neural networks by evolution
Special issue on articficial life and robotics

Designing artificial neural networks (ANNs) for different applications has been a key issue in the ANN field. At present, ANN design still relies heavily on human experts who have sufficient knowledge about ANNs and the problem to be solved. As ANN ...
Evolving a diversity of virtual creatures through novelty search and local competition
GECCO '11: Proceedings of the 13th annual conference on Genetic and evolutionary computation

An ambitious challenge in artificial life is to craft an evolutionary process that discovers a wide diversity of well-adapted virtual creatures within a single run. Unlike in nature, evolving creatures in virtual worlds tend to converge to a single ...
Learning and evolution in neural networks

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

GECCO '10: Proceedings of the 12th annual conference on Genetic and evolutionary computation

July 2010

1520 pages

ISBN:9781450300728

DOI:10.1145/1830483

General Chair:
Martin Pelikan
University of Missouri, USA
,
Program Chair:
Jürgen Branke
University of Warwick, Coventry, UK

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 07 July 2010

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Conference

GECCO '10

Sponsor:

SIGEVO

GECCO '10: Genetic and Evolutionary Computation Conference

July 7 - 11, 2010

Oregon, Portland, USA

Acceptance Rates

Overall Acceptance Rate 1,669 of 4,410 submissions, 38%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

7
Total Citations
View Citations
217
Total Downloads

Downloads (Last 12 months)9
Downloads (Last 6 weeks)0

Reflects downloads up to 18 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

View all

Ito TPilat MSuzuki RArita T(2016)Population and evolutionary dynamics based on predator-prey relationships in a 3d physical simulationArtificial Life10.1162/ARTL_a_0020122:2(226-240)Online publication date: 1-May-2016
https://dl.acm.org/doi/10.1162/ARTL_a_00201
Chaumont NAdami C(2016)Evolution of sustained foraging in three-dimensional environments with physicsGenetic Programming and Evolvable Machines10.1007/s10710-016-9270-z17:4(359-390)Online publication date: 1-Dec-2016
https://dl.acm.org/doi/10.1007/s10710-016-9270-z
Lessin DFussell DMiikkulainen RAlba E(2013)Open-ended behavioral complexity for evolved virtual creaturesProceedings of the 15th annual conference on Genetic and evolutionary computation10.1145/2463372.2463411(335-342)Online publication date: 6-Jul-2013
https://dl.acm.org/doi/10.1145/2463372.2463411
Ouannes NDjedi NDuthen YLuga H(2012)Toward the construction of a virtual ecosystem by evolving virtual creature's behaviours2012 International Conference on Multimedia Computing and Systems10.1109/ICMCS.2012.6320173(350-355)Online publication date: May-2012
https://doi.org/10.1109/ICMCS.2012.6320173
Pilat MSuzuki RArita T(2012)Dealing with rounding error problems in evolutionary physical simulationArtificial Life and Robotics10.1007/s10015-012-0038-017:1(158-162)Online publication date: 1-Oct-2012
https://dl.acm.org/doi/10.1007/s10015-012-0038-0
Bongard JLanzi P(2011)Morphological and environmental scaffolding synergize when evolving robot controllersProceedings of the 13th annual conference on Genetic and evolutionary computation10.1145/2001576.2001602(179-186)Online publication date: 12-Jul-2011
https://dl.acm.org/doi/10.1145/2001576.2001602
Krcah P(2010)Solving deceptive tasks in robot body-brain co-evolution by searching for behavioral novelty2010 10th International Conference on Intelligent Systems Design and Applications10.1109/ISDA.2010.5687250(284-289)Online publication date: Nov-2010
https://doi.org/10.1109/ISDA.2010.5687250

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Index Terms

Recommendations

Towards designing artificial neural networks by evolution

Evolving a diversity of virtual creatures through novelty search and local competition

Learning and evolution in neural networks