Abstract
We investigate an evolutionary robot system where (simulated) modular robots can reproduce and create robot children that inherit the parents’ morphologies by crossover and mutation. Within this system we compare two approaches to creating good controllers, i.e., evolution only and evolution plus learning. In the first one the controller of a robot child is inherited, so that it is produced by applying crossover and mutation to the controllers of its parents. In the second one the controller of the child is also inherited, but additionally, it is enhanced by a learning method. The experiments show that the learning approach does not only lead to different fitness levels, but also to different (bigger) robots. This constitutes a quantitative demonstration that changes in brains, i.e., controllers, can induce changes in the bodies, i.e., morphologies.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
This means that around 80% of the offspring will be result of crossovers, and also that around 80% of the offspring will suffer the above explained mutation.
- 2.
The types of modules would not have to be necessarily the same, as long as the morphology had the same amount of modules.
References
Alexander, R.M.: Principles of Animal Locomotion. Princeton University Press, Princeton (2003)
Auerbach, J., et al.: RoboGen: robot generation through artificial evolution. In: Artificial Life 14: Proceedings of the Fourteenth International Conference on the Synthesis and Simulation of Living Systems, pp. 136–137. The MIT Press (2014)
Buresch, T., Eiben, A.E., Nitschke, G., Schut, M.: Effects of evolutionary and lifetime learning on minds and bodies in an artificial society. In: Proceedings of the IEEE Conference on Evolutionary Computation (CEC 2005), pp. 1448–1454. IEEE Press (2005). http://www.cs.vu.nl/~schut/pubs/Buresch/2005.pdf
Doncieux, S., Bredeche, N., Mouret, J.B., Eiben, A.: Evolutionary robotics: what, why, and where to. Frontiers Robot. AI 2, 4 (2015)
Floreano, D., Husbands, P., Nolfi, S.: Evolutionary robotics. In: Siciliano, B., Khatib, O. (eds.) Springer Handbook of Robotics, Part G. 61, pp. 1423–1451. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-30301-5_62
Hamann, H., Stradner, J., Schmickl, T., Crailsheim, K.: A hormone-based controller for evolutionary multi-modular robotics: from single modules to gait learning. In: 2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 IEEE Congress on Evolutionary Computation, CEC 2010 (2010)
Hansen, N., Akimoto, Y., Brockhoff, D., Chan, M.: CMA-ES/pycma: r2.7.0, April 2019. https://doi.org/10.5281/zenodo.2651072
Hornby, G.S., Pollack, J.B.: Body-brain co-evolution using L-systems as a generative encoding. In: Proceedings of the 3rd Annual Conference on Genetic and Evolutionary Computation, pp. 868–875. Morgan Kaufmann Publishers (2001)
Ijspeert, A.J.: Central pattern generators for locomotion control in animals and robots: a review. Neural Netw. 21(4), 642–653 (2008)
Jelisavcic, M., Kiesel, R., Glette, K., Haasdijk, E., Eiben, A.: Analysis of Lamarckian evolution in morphologically evolving robots. In: Artificial Life Conference Proceedings, vol. 14. pp. 214–221. MIT Press (2017)
Marbach, D., Ijspeert, A.J.: Co-evolution of configuration and control for homogenous modular robots. In: Proceedings of the Eighth Conference on Intelligent Autonomous Systems (IAS8), pp. 712–719 (2004)
Miras, K., Haasdijk, E., Glette, K., Eiben, A.E.: Effects of selection preferences on evolved robot morphologies and behaviors. In: Proceedings of the Artificial Life Conference, Tokyo (ALIFE 2018). MIT Press (2018)
Miras, K., Haasdijk, E., Glette, K., Eiben, A.E.: Search space analysis of evolvable robot morphologies. In: Sim, K., Kaufmann, P. (eds.) EvoApplications 2018. LNCS, vol. 10784, pp. 703–718. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-77538-8_47
Pfeifer, R., Bongard, J.: How the Body Shapes the Way We Think: A New View of Intelligence. MIT Press, Cambridge (2006)
Sims, K.: Evolving 3D morphology and behavior by competition. Artif. Life 1(4), 353–372 (1994)
Sproewitz, A., Moeckel, R., Maye, J., Ijspeert, A.J.: Learning to move in modular robots using central pattern generators and online optimization. Int. J. Robot. Res. 27(3–4), 423–443 (2008)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Miras, K., De Carlo, M., Akhatou, S., Eiben, A.E. (2020). Evolving-Controllers Versus Learning-Controllers for Morphologically Evolvable Robots. In: Castillo, P.A., Jiménez Laredo, J.L., Fernández de Vega, F. (eds) Applications of Evolutionary Computation. EvoApplications 2020. Lecture Notes in Computer Science(), vol 12104. Springer, Cham. https://doi.org/10.1007/978-3-030-43722-0_6
Download citation
DOI: https://doi.org/10.1007/978-3-030-43722-0_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-43721-3
Online ISBN: 978-3-030-43722-0
eBook Packages: Computer ScienceComputer Science (R0)