Advertisement

Influence of Local Selection and Robot Swarm Density on the Distributed Evolution of GRNs

  • Iñaki Fernández Pérez
  • Stéphane SanchezEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11454)

Abstract

Distributed Embodied Evolution (dEE) is a powerful approach to learn behaviors in robot swarms by exploiting their intrinsic parallelism: each robot runs an evolutionary algorithm, and locally shares its learning experience with other nearby robots. Given the distributed nature of this approach, dEE entails different evolutionary dynamics when compared to standard centralized Evolutionary Robotics. In this paper, we investigate the distributed evolution of Gene Regulatory Networks (GRNs) as controller representation to learn swarm robot behavior, which have been extensively used for the evolution of single-robot behavior with remarkable success. Concretely, we use dEE to evolve fixed-topology GRN swarm robot controllers for an item collection task; this constitutes the first work to evolve GRNs in distributed swarm robot settings. To improve our understanding of such distributed GRN evolution, we analyze the fitness and the behavioral diversity of the swarm over generations when using 5 levels of increasing local selection pressure and 4 different swarm sizes, from 25 to 200 robots. Our experiments reveal that there exist different regimes, depending on the swarm size, in the relationship between local selection pressure, and both behavioral diversity and overall swarm performance, providing several insights on distributed evolution. We further use a metric to quantify selection pressure in evolutionary systems, which is based on the correlation between number of offspring and fitness of the behaviors. This reveals a complex relationship on the overall selection pressure between the ability or ease to spread genomes (or environmental pressure), and the fitness of the behavior (or task-oriented (local) pressure), opening new research questions. We conclude the paper by discussing the need for developing specialized statistical tools to facilitate the analysis of the large and diverse amount of data relevant to distributed Embodied Evolution.

Keywords

Distributed Embodied Evolution Swarm robotics Gene Regulatory Networks Evolutionary Robotics Behavioral diversity 

References

  1. 1.
    Watson, R.A., Ficici, S.G., Pollack, J.B.: Embodied evolution: distributing an evolutionary algorithm in a population of robots. Robot. Auton. Syst. 39(1), 1–18 (2002)CrossRefGoogle Scholar
  2. 2.
    Fernández Pérez, I., Boumaza, A., Charpillet, F.: Comparison of selection methods in on-line distributed evolutionary robotics. In: Proceedings of the International Conference on the Synthesis and Simulation of Living Systems (Alife 2014), pp. 282–289. MIT Press, New York, July 2014. http://mitpress.mit.edu/books/artificial-life-14
  3. 3.
    Fernández Pérez, I., Boumaza, A., Charpillet, F.: Maintaining diversity in robot swarms with distributed embodied evolution. In: ANTS Conference, the Eleventh International Conference on Swarm Intelligence, October 2018Google Scholar
  4. 4.
    Bredèche, N., Montanier, J.M., Liu, W., Winfield, A.: Environment-driven distributed evolutionary adaptation in a population of autonomous robotic agents. Math. Comput. Model. Dyn. Syst. 18(1), 101–129 (2012). http://hal.inria.fr/inria-00531450
  5. 5.
    Fernández Pérez, I., Boumaza, A., Charpillet, F.: Learning collaborative foraging in a swarm of robots using embodied evolution. In: ECAL 2017–14th European Conference on Artificial Life. Inria, Lyon, France, September 2017. https://hal.archives-ouvertes.fr/hal-01534242. nominated to the best paper award at ECAL2017 (4 nominees over 100+ papers)
  6. 6.
    Weiss, G.: Multiagent Systems: A Modern Approach to Distributed Artificial Intelligence. MIT press, Cambridge (1999)Google Scholar
  7. 7.
    Joachimczak, M., Wrobel, B.: Evolving gene regulatory networks for real time control of foraging behaviours. artificial life XII. In: Proceedings of the 12th International Conference on the Synthesis and Simulation of Living Systems, pp. 348–355 (2010)Google Scholar
  8. 8.
    Nicolau, M., Schoenauer, M., Banzhaf, W.: Evolving genes to balance a pole. In: Esparcia-Alcázar, A.I., Ekárt, A., Silva, S., Dignum, S., Uyar, A.Ş. (eds.) EuroGP 2010. LNCS, vol. 6021, pp. 196–207. Springer, Heidelberg (2010).  https://doi.org/10.1007/978-3-642-12148-7_17CrossRefGoogle Scholar
  9. 9.
    Quick, T., Nehaniv, C.L., Dautenhahn, K., Roberts, G.: Evolving embodied genetic regulatory network-driven control systems. In: Banzhaf, W., Ziegler, J., Christaller, T., Dittrich, P., Kim, J.T. (eds.) ECAL 2003. LNCS (LNAI), vol. 2801, pp. 266–277. Springer, Heidelberg (2003).  https://doi.org/10.1007/978-3-540-39432-7_29CrossRefGoogle Scholar
  10. 10.
    Roli, A., Manfroni, M., Pinciroli, C., Birattari, M.: On the design of boolean network robots. EvoApplications 2011. LNCS, vol. 6624, pp. 43–52. Springer, Heidelberg (2011).  https://doi.org/10.1007/978-3-642-20525-5_5CrossRefGoogle Scholar
  11. 11.
    Cussat-Blanc, S., Harrington, K.: Genetically-regulated neuromodulation facilitates multi-task reinforcement learning. In: Proceedings of the 2015 on Genetic and Evolutionary Computation Conference - GECCO 2015, No. 1, pp. 551–558. ACM Press, New York (2015)Google Scholar
  12. 12.
    Sanchez, S., Cussat-Blanc, S.: Gene regulated car driving: using a gene regulatory network to drive a virtual car. Genet. Program. Evolvable Mach. 15(4), 477–511 (2014).  https://doi.org/10.1007/s10710-014-9228-y
  13. 13.
    Cussat-Blanc, S., Luga, H., Duthen, Y.: From single cell to simple creature morphology and metabolism. In: Artificial Life XI, pp. 134–141 (2008)Google Scholar
  14. 14.
    Taylor, T.: A genetic regulatory network-inspired real-time controller for a group of underwater robots. In: Proceedings of the Eighth Conference on Intelligent Autonomous Systems (IAS-8), pp. 403–412. IOS Press (2004)Google Scholar
  15. 15.
    Delecluse, M., Sanchez, S., Cussat-Blanc, S., Schneider, N., Welcomme, J.B.: High-level behavior regulation for multi-robot systems. In: Proceedings of the Companion Publication of the 2014 Annual Conference on Genetic and Evolutionary Computation GECCO Comp 2014, pp. 29–30. ACM, New York (2014). http://doi.acm.org/10.1145/2598394.2598454
  16. 16.
    Fernández Pérez, I., Sanchez, S.: Influence of mating mechanisms in distributed evolution for collective robotics. In: EVOSLACE Workshop at ALIFE2018: Workshop on the Emergence and Evolution of Social Learning, Communication, Language and Culture in Natural and Artificial Agent, Tokyo, Japan (2018)Google Scholar
  17. 17.
    Bredeche, N., Montanier, J.-M.: Environment-driven embodied evolution in a population of autonomous agents. In: Schaefer, R., Cotta, C., Kołodziej, J., Rudolph, G. (eds.) PPSN 2010. LNCS, vol. 6239, pp. 290–299. Springer, Heidelberg (2010).  https://doi.org/10.1007/978-3-642-15871-1_30. http://hal.inria.fr/inria-00506771CrossRefGoogle Scholar
  18. 18.
    Banzhaf, W.: Artificial regulatory networks and genetic programming. In: Riolo, R., Worzel, B. (eds.) Genetic Programming Theory and Practice, vol. 6, pp. 43–61. Springer, Boston (2003).  https://doi.org/10.1007/978-1-4419-8983-3_4
  19. 19.
    Disset, J., Wilson, D.G., Cussat-Blanc, S., Sanchez, S., Luga, H., Duthen, Y.: A comparison of genetic regulatory network dynamics and encoding. In: Proceedings of the Genetic and Evolutionary Computation Conference GECCO 2017, pp. 91–98. ACM, New York (2017). http://doi.acm.org/10.1145/3071178.3071322
  20. 20.
    Knabe, J., Nehaniv, C., Schilstra, M., Quick, T.: Evolving biological clocks using genetic regulatory networks. In: Artificial Life X : Proceedings of the Tenth International Conference on the Simulation and Synthesis of Living Systems (Alife 10), pp. 15–21 (2006)Google Scholar
  21. 21.
    Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evol. Comput. 10(2), 99–127 (2002)CrossRefGoogle Scholar
  22. 22.
    Cussat-Blanc, S., Harrington, K., Pollack, J.: Gene regulatory network evolution through augmenting topologies. IEEE Trans. Evol. Comput. 19(6), 823–837 (2015)CrossRefGoogle Scholar
  23. 23.
    Haasdijk, E., Heinerman, J.: Quantifying selection pressure. Evol. Comput., 1–23 (2017)Google Scholar
  24. 24.
    Bredèche, N., Montanier, J.M., Weel, B., Haasdijk, E.: Roborobo! a fast robot simulator for swarm and collective robotics. CoRR abs/1304.2888 (2013)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.University of Toulouse - IRIT - CNRS - UMR5505ToulouseFrance

Personalised recommendations