Abstract
In Evolutionary Robotics, population-based evolutionary computation is used to design robot neurocontrollers that produce behaviors which allow the robot to fulfill a user-defined task. However, the standard approach is to use canonical evolutionary algorithms, where the search tends to make the evolving population converge towards a single behavioral solution, even if the high-level task could be accomplished by structurally different behaviors. In this work, we present an approach that preserves behavioral diversity within the population in order to produce a diverse set of structurally different behaviors that the robot can use. In order to achieve this, we employ the concept of speciation, where the population is dynamically subdivided into sub-groups, or species, each one characterized by a particular behavioral structure that all individuals within that species share. Speciation is achieved by describing each neurocontroller using a representations that we call a behavior signature, these are descriptors that characterize the traversed path of the robot within the environment. Behavior signatures are coded using character strings, this allows us to compare them using a string similarity measure, and three measures are tested. The proposed behavior-based speciation is compared with canonical evolution and a method that speciates based on network topology. Experimental tests were carried out using two robot tasks (navigation and homing behavior), several training environments, and two different robots (Khepera and Pioneer), both real and simulated. Results indicate that behavior-based speciation increases the diversity of the behaviors based on their structure, without sacrificing performance. Moreover, the evolved controllers exhibit good robustness when the robot is placed within environments that were not used during training. In conclusion, the speciation method presented in this work allows an evolutionary algorithm to produce several robot behaviors that are structurally different but all are able to solve the same robot task.
Similar content being viewed by others
References
Coello, C., Veldhuizen, D.V., Lamont, G.: Evolutionary Algorithms for Solving Multi-Objective Problems. Kluwer Academic Publishers, New York, New York (2002)
Darwen, P.J., Yao, X.: Speciation as automatic categorical modularization. IEEE Trans. Evol. Comput. 1(2), 101–108 (1997)
DeJong, K.A.: Evolutionary Computation: A Unified Approach. MIT Press, Cambridge, MA, USA (2002)
Dorigo, M., Stützle, T.: Ant Colony Optimization. Bradford Company, Scituate, MA, USA (2004)
Dunn, E., Olague, G., Lutton, E.: Parisian camera placement for vision metrology. Pattern Recogn. Lett. 27(11), 1209–1219 (2006)
Eberhart, R.C., Shi, Y., Kennedy, J.: Swarm Intelligence, 1st edn. The Morgan Kaufmann Series in Evolutionary Computation, Morgan Kaufmann (2001)
Floreano, D., Mattiussi, C.: Bio-inspired Artificial Intelligence: Theories, Methods and Technologies. MIT Press, Cambridge, MA (2008)
Floreano, D., Sanderson, F.M.A.C.: Evolution of homing navigation in a real mobile robot. IEEE Trans. Syst. Man Cybern. Part B 26(3), 396–407 (1996)
Goldberg, D.E., Richardson, J.: Genetic algorithms with sharing for multimodal function optimization. In: Proceedings of the Second International Conference on Genetic Algorithms on Genetic algorithms and their Application, pp. 41–49. Lawrence Erlbaum Associates, Inc., Mahwah, NJ, USA (1987)
Gomez, F.J., Miikkulainen, R.: Solving non-Markovian control tasks with neuro-evolution. In: Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence, IJCAI 99, pp. 1356–1361. Morgan Kaufmann, San Mateo, CA (1999)
Hocaoǧlu, C., Sanderson, A.C.: Planning multiple paths with evolutionary speciation. IEEE Trans. Evol. Comput. 5(3), 169–191 (2001)
Landrin-Schweitzer, Y., Collet, P., Lutton, E., Prost, T.: Introducing lateral thinking in search engines with interactive evolutionary algorithms. In: SAC ’03: Proceedings of the 2003 ACM Symposium on Applied Computing, pp. 214–219. ACM Press, New York, NY, USA (2003)
Mahfoud, S.W.: Niching methods for genetic algorithms. Ph.D. thesis, University of Illinois at Urbana-Champaign, Champaign, IL, USA (1995)
Martin, P., Bateson, P.: Measuring Behaviour: An Introductory Guide, 3rd edn. Cambridge University Press, Cambridge, UK (2007)
Mattiussi, C., Waibel, M., Floreano, D.: Measures of diversity for populations and distances between individuals with highly reorganizable genomes. Evol. Comput. 12(4), 495–515 (2004)
Michel, O.: Khepera Simulator v. 2 User Manual. University of Nice-Sophia, Antipolis (1996)
Miglino, O., Lund, H.H., Nolfi, S.: Evolving mobile robots in simulated and real environments. Artif. Life 2(4), 417–434 (1995)
Montana, D.J., Davis, L.: Training feedforward neural networks using genetic algorithms. In: Sridharan, S. (ed.) Proceedings of the Eleventh International Joint Conference on Artificial Intelligence, pp. 762–767. Morgan Kaufman, San Francisco, California (1989)
Moriarty, D.E., Mikkulainen, R.: Efficient reinforcement learning through symbiotic evolution. Mach. Learn. 22(1–3), 11–32 (1996)
Nguyen, Q.H., Ong, Y.S., Lim, M.H.: A probabilistic memetic framework. IEEE Trans. Evol. Comput. 13, 604–623 (2009)
Nitschke, G., Schut, M.: Designing multi-rover emergent specialization. In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2008). ACM Press (2008)
Nolfi, S., Floreano, D.: Evolutionary Robotics: the Biology, Intelligence, and Technology of Self-Organizing Machines. Bradford Book (2004)
Ong, Y.S., Lim, M.H., Chen, X.: Research frontier: memetic computation-past, present & future. IEEE Comput. Intell. Mag. 5, 24–31 (2010)
Pollack, J.B., Blair, A.D.: Co-evolution in the successful learning of backgammon strategy. Mach. Learn. 32(1), 225–240 (1998)
Potter, M.: The design and analysis of a computational model of cooperative coevolution. Ph.D. thesis, George Mason University, Fairfax, VA, USA (1997)
Price, K., Storn, R.M., Lampinen, J.A.: Differential Evolution: a Practical Approach to Global Optimization (Natural Computing Series). Springer-Verlag New York, Inc., Secaucus, NJ, USA (2005)
Rosca, J.: Hierarchical learning with procedural abstraction mechanisms. Ph.D. thesis, Rochester, NY, USA (1997)
Savage, T.: Measurement and the explanation of adaptive and novel behaviors in real and artificial creatures. Cogn. Syst. Res. 5(1), 3–39 (2004)
Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evol. Comput. 10(2), 99–127 (2002)
Trujillo, L., Olague, G., Lutton, E., de Vega, F.F.: Discovering several robot behaviors through speciation. In: Giacobini, M., et al. (eds.) EvoWorkshops: the 4th European Workshop on Bio-inspired Heuristics for Design Automation (EvoHOT’07). Lecture Notes in Computer Science, vol. 4974, pp. 164–174, 26–28 March, Napoli, Italy, Springer (best paper award) (2008)
Viola, P.A., Jones, M.J.: Rapid object detection using a boosted cascade of simple features. In: Proceeding from the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2001), pp. 511–518, 8–14 December, Kauai, HI, USA. IEEE Computer Society (2001)
Yujian, L., Bo, L.: A normalized levenshtein distance metric. IEEE Trans. Pattern Anal. Mach. Intell. 29(6), 1091–1095 (2007)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Trujillo, L., Olague, G., Lutton, E. et al. Speciation in Behavioral Space for Evolutionary Robotics. J Intell Robot Syst 64, 323–351 (2011). https://doi.org/10.1007/s10846-011-9542-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10846-011-9542-z