Abstract
This paper focuses on the implementation and evaluation of a set of integrated models for the representation of emergent behavior control patterns in robotic environments. The models have been validated on a custom developed emergent behavior simulator and tested using the CORE-TX (COllaborative Robotic Environment - the Timisoara eXperiment) prototype platform. Four metrics (pheromone intensity, path affinity, reachability and liveness) are introduced and used to evaluate the performance of the proposed control patterns. Experimental results for an environment which employs ant colony behavior patterns in obstacle avoidance applications show that the emergent behavior of the robotic collective is triggered by a number ranging from 9 to 11 entities. The results are also consistent with the theoretical model-based predictions. When doubling the number of entities, the performance of the system can be further increased by 19.3%. On the other hand, a high concentration of entities has been noted to affect the emergent behavior of the system and, thus, its performance, mainly due to the interaction overhead. An upper bound to the number of individuals has been computed, based on a set of parameters which model each particular application. The experimental validation of the proposed behavior control patterns endorses them as a good framework for the analysis and development of complex applications which require collaborative and distributed intelligence, perception and operation.
This work is supported by the Romanian Ministry of Education and Research, through the grant PNCDI II ID-22/2007-2010 and, in parts through the grant PNCDI II PDP-2306/2007-2010.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Cioarga, R.D., Micea, M.V., Ciubotaru, B., Chiuciudean, D., Stanescu, D.: CORE-TX: Collective Robotic Environment - the Timisoara Experiment. In: Proc. 3-rd Romanian-Hungarian Joint Symp. on Applied Computational Intelig., SACI 2006, Timisoara, Romania, May 2006, pp. 495–506. IEEE, Los Alamitos (2006)
van der Zwaan, S., Marques, C.: Ant Colony Optimization for Job Shop Scheduling. In: Proc. Third Workshop on Genetic Algorithms and Artificial Life, Lisbon, Portugal (1999)
Merkle, D., Middendorf, M., Schmeck, H.: Ant Colony Optimization for Resource-Constrained Project Scheduling. In: Proceedings of the Genetic and Evolutionary Computation Conference, Las Vegas, Nevada, pp. 893–900 (2000)
Iredi, S., Merkle, D., Middendorf, M.: Bi-Criterion Optimization with Multi Colony Ant Algorithms. In: Zitzler, E., Deb, K., Thiele, L., Coello Coello, C.A., Corne, D.W. (eds.) EMO 2001. LNCS, vol. 1993, p. 359. Springer, Heidelberg (2001)
Dorigo, M., Di Caro, G.: The ant colony optimization meta-heuristic. In: Corne, D., Dorigo, M., Glover, F. (eds.) New Ideas in Optimization, pp. 11–32. McGraw-Hill, New York (1999)
Dorigo, M., Maniezzo, V., Colorni, A.: The Ant System: Optimization by a colony of cooperating agents. IEEE Trans. Syst, Man, Cybern. 26(2), 29–41 (1996)
Dorigo, M., Gambardella, L.M.: Ant colony System: A Cooperative Learning Approach to the Travelling Salesman Problem. IEEE Trans. on Evolutionary Computation 1(1) (April 1997)
Maniezzo, V., Gambardella, L.M., de Luigi, F.: Ant Colony Optimization: New Optimization Techniques in Engineering, by Onwubolu, G.C., Babu, B.V., pp. 101–117. Springer, Heidelberg (2004)
Van Dyke Parunak, H., Brueckner, S., Sauter, J., Matthews, R.: Global Convergence of Local Agent Behaviors. In: AAMAS 2005, Utrecht, Netherlands, July 2005, pp. 305–312 (2005)
Truszkowski, W., Hinchey, M., Rash, J., Rouff, C.: NASA’s swarm missions: The challenge of building autonomous software. IEEE IT Professional 6(5), 47–52 (2004)
Hinchey, M., Rouff, C., Rash, J.: Requirements of an Integrated Formal Method for Intelligent Swarms. In: Proc. FMICS 2005, Lisbon, Portugal, September 2005, pp. 125–133 (2005)
Cioarga, R., Micea, M., Ciubotaru, B., Chiciudean, D., Cretu, V., Groza, V.: eBML: A Formal Language for Behavior Modeling and Application Development in Robotic Collectives. In: Proc. International Workshop on Robotic and Sensors Environments ROSE 2007, pp. 1–6 (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Cioarga, RD., Micea, M.V., Cretu, V., Racoceanu, D. (2009). Emergent Behavior Control Patterns in Robotic Collectives. In: Xie, M., Xiong, Y., Xiong, C., Liu, H., Hu, Z. (eds) Intelligent Robotics and Applications. ICIRA 2009. Lecture Notes in Computer Science(), vol 5928. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-10817-4_16
Download citation
DOI: https://doi.org/10.1007/978-3-642-10817-4_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-10816-7
Online ISBN: 978-3-642-10817-4
eBook Packages: Computer ScienceComputer Science (R0)