Take a look at the new version of this page: [ beta version ]. Tell us what you think.

ABSTRACT

We compare the efficacy of the Enforced Sub-Populations (ESP) and Collective Neuro-Evolution (CONE) methods for designing behavioral specialization in a multi-rover collective behavior task. These methods are tested for Artificial Neural Network (ANN) controller design in an extension of the multi-rover task, where behavioral specialization is known to benefit task performance. The task is for multiple simulated autonomous vehicles (rovers) to maximize the detection of points of interest (red rocks) in a virtual environment. The task requires rovers to collectively sense such points of interest in order for them to be detected. Results indicate that the CONE method facilitates a level of specialization appropriate for achieving a significantly higher task performance, comparative to rover teams evolved by the ESP method.

REFERENCES

• 1: A. Agogino and K. Tumer. Efficient evaluation functions for multi-rover systems. In Proceedings of the Genetic and Evolutionary Computation Conference, pages 1--12, New York, USA, 2004. Springer-Verlag.
• 2: Gianluca Baldassarre , Stefano Nolfi , Domenico Parisi, Evolving mobile robots able to display collective behaviors, Artificial Life, v.9 n.3, p.255-267, Summer 2003 [doi>10.1162/106454603322392460]
• 3: A. Eiben. Multiparent recombination. In T. B. D. Fogel and Z. Michalewicz, editors, Evolutionary Computation 1: Basic Algorithms and Operators, pages 289--307. Institute of Physics Publishing, Ottawa, Canada, 2000.
• 4: Agoston E. Eiben , Thomas Bäck, Empirical investigation of multiparent recombination operators in evolution strategies, Evolutionary Computation, v.5 n.3, p.347-365, Fall 1997 [doi>10.1162/evco.1997.5.3.347]
• 5: Agoston E. Eiben , J. E. Smith, Introduction to Evolutionary Computing, SpringerVerlag, 2003
• 6: B. Flannery, S. Teukolsky, and W. Vetterling. Numerical Recipes. Cambridge University Press, Cambridge, 1986.
• 7: J. Gautrais, G. Theraulaz, J. Deneubourg, and C. Anderson. Emergent polyethism as a consequence of increased colony size in insect societies. Journal of Theoretical Biology, 215(1):363--373, 2002.
• 8: Faustino Gomez , Risto Mikkulainen, Incremental evolution of complex general behavior, Adaptive Behavior, v.5 n.3-4, p.317-342, Winter/Spring 1997 [doi>10.1177/105971239700500305]
• 9: David E. Moriarty , Risto Mikkulainen, Efficient reinforcement learning through symbiotic evolution, Machine Learning, v.22 n.1-3, p.11-32, Jan./Feb./March 1996 [doi>10.1007/BF00114722]
• 10: G. Nitschke, M. Schut, and A. Eiben. Collective specialization for evolutionary design of a multi-robot system. In Proceedings of the Second International Workshop on Swarm Robotics, pages 189--206, Rome, Italy, September 2006. Springer.
• 11: G. Nitschke, M. Schut, and A. Eiben. Emergent specialization in the extended multi-rover problem. In Proceedings of the IEEE Congress on Evolutionary Computation, pages 100--106, Singapore, 2007. IEEE.
• 12: Pekka Paalanen , Joni-Kristian Kamarainen , Jarmo Ilonen , Heikki Kälviäinen, Feature representation and discrimination based on Gaussian mixture model probability densities-Practices and algorithms, Pattern Recognition, v.39 n.7, p.1346-1358, July, 2006 [doi>10.1016/j.patcog.2006.01.005]
• 13: Kenneth O. Stanley , Risto Miikkulainen, Evolving neural networks through augmenting topologies, Evolutionary Computation, v.10 n.2, p.99-127, Summer 2002 [doi>10.1162/106365602320169811]
• 14: M. Wineberg and F. Oppacher. The underlying similarity of diversity measures used in evolutionary computation. In Proceedings of the Fifth Genetic and Evolutionary Computation Conference, pages 1493--1504, Berlin, 2003. Springer.
• 15: Chern H Yong , Risto Miikkulainen, COOPERATIVE COEVOLUTION OF MULTI-AGENT SYSTEMS, University of Texas at Austin, Austin, TX, 2001

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
        I.2.11 Distributed Artificial Intelligence
            Subjects: Intelligent agents

General Terms:
Algorithms

Keywords:
multi-rover, neuro-evolution, specialization