Abstract
In this paper I describe EvoSphere, a tangible realization of the general Evolution of Things concept. EvoSphere can be used as a research platform to study the evolution of intelligent machines for practical as well as theoretical purposes. On the one hand, it can be used to develop robots that are hard to obtain with traditional design and optimization techniques and it can deliver original solutions that are unlikely to be conceived by a human designer. On the other hand, EvoSphere forms an evolving ecosystem that enables fundamental research into evolution and embodied intelligence. The use of real hardware is a pivotal feature as it avoids the reality gap and guarantees that the evolved solutions are physically feasible. On the long term, EvoSphere technology can pave the way for robot populations that evolve ‘in the wild’ and can adapt to unforeseen and changing circumstances.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
- 3.
There exist systems that mix the two in a certain way. The idea is that the principal method is a traditional digital EA with simulated fitness evaluations, but every now and then an individual in the population is physically constructed and evaluated in the real world.
- 4.
The paper [11] illustrated the components of this framework one by one using the modular robots of the Symbrion project. However, Symbrion was not aiming at physically evolving morphologies and the components of the ToL have not been integrated.
- 5.
- 6.
- 7.
A simple example is to use NN controllers with inheritable topology and learnable weights.
- 8.
These steps may need to be revised for radically different types of robots, for instance soft robots with novel forms of control and actuation, but there will always be a list of such steps.
References
Auerbach, J.E., Aydin, D., Maesani, A., Kornatowski, P., Cieslewski, T., Heitz, G., Fernando, P.R., Loshchilov, I., Daler, L., Floreano, D.: Robogen: robot generation through artificial evolution. In: Sayama, H., Rieffel, J., Risi, S., Doursat, R., Lipson, H. (eds.) Artificial Life 14: Proceedings of the Fourteenth International Conference on the Synthesis and Simulation of Living Systems, pp. 136–137. The MIT Press (2014)
Auerbach, J.E., Bongard, J.C.: Environmental influence on the evolution of morphological complexity in machines. PLOS Comput. Biol. 10(1), e1003399 (2014)
Bentley, P., Corne, D.: Creative Evolutionary Systems. Morgan Kaufmann, San Francisco (2002)
Bentley, P.J. (ed.): Evolutionary Design by Computers. Morgan Kaufmann, San Francisco (1999)
Bongard, J.C., Lipson, H.: Evolved machines shed light on robustness and resilience. Proc. IEEE 302(5), 899–914 (2014)
Bongard, J.C., Pfeifer, R.: Evolving complete agents using artificial ontogeny. In: Hara, F., Pfeifer, R. (eds.) Morpho-Functional Machines: The New Species, pp. 237–258. Springer, Tokyo (2003)
Brodbeck, L., Hauser, S., Iida, F.: Morphological evolution of physical robots through model-free phenotype development. PLoS One 10(6), e0128444 (2015)
Eiben, A.E.: In Vivo Veritas: towards the evolution of things. In: Bartz-Beielstein, T., Branke, J., Filipič, B., Smith, J. (eds.) PPSN 2014. LNCS, vol. 8672, pp. 24–39. Springer, Heidelberg (2014)
Eiben, A.E., Kernbach, S., Haasdijk, E.: Embodied artificial evolution - artificial evolutionary systems in the 21st century. Evol. Intell. 5(4), 261–272 (2012)
Eiben, A.E., Smith, J.E.: Introduction to Evolutionary Computing. Natural Computing Series, 2nd edn. Springer, Heidelberg (2015)
Eiben, A.E., Bredeche, N., Hoogendoorn, M., Stradner, J., Timmis, J., Tyrrell, A.M., Winfield, A.: The triangle of life: evolving robots in real-time and real-space. In: Liò, P., Miglino, O., Nicosia, G., Nolfi, S., Pavone, M. (eds.) Advances In Artificial Life, ECAL 2013, pp. 1056–1063. MIT Press, (2013)
Eiben, A.E., Smith, J.: From evolutionary computation to the evolution of things. Nature 521(7553), 476–482 (2015)
Floreano, D., Keller, L.: Evolution of adaptive behaviour in robots by means of darwinian selection. PLOS Biol. 8(1), e1000292 (2010)
Jakobi, N., Husbands, P., Harvey, I.: Noise and the reality gap: the use of simulation in evolutionary robotics. In: Morán, F., Moreno, A., Merelo, J.J., Chacón, P. (eds.) Advances in Artificial Life. Lecture Notes in Computer Science, pp. 704–720. Springer, Heidelberg (1995)
Komosinski, M.: The framsticks system: versatile simulator of 3d agents and their evolution. Kybernetes 32(1/2), 156–173 (2003)
Lipson, H., Pollack, J.B.: Automatic design and manufacture of robotic lifeforms. Nature 406, 974–978 (2000)
Long, J.: Darwin’s Devices: What Evolving Robots Can Teach Us About the History of Life and the Future of Technology. Basic Books, New York (2012)
Lund, H.: Co-evolving control and morphology with LEGO robots. In: Hara, F., Pfeifer, R. (eds.) Morpho-functional Machines: The New Species, pp. 59–79. Springer, Tokyo (2003)
Nehmzow, U.: Physically embedded genetic algorithm learning in multi-robot scenarios: the pega algorithm. In: Prince, C.G., Demiris, Y., Marom, Y., Kozima, H., Balkenius, C. (eds.) Proceedings of The Second International Workshop on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems, Number 94 in Lund University Cognitive Studies, LUCS, Edinburgh, UK, August 2002
Pfeifer, R., Bongard, J.: How the Body Shapes the Way We Think. MIT Press, Cambridge (2006)
Simoes, E.D.V., Dimond, K.R.: An evolutionary controller for autonomous multi-robot systems. In: IEEE International Conference on Systems, Man, and Cybernetics, 1999. IEEE SMC 1999 Conference Proceedings, vol. 6, pp. 596–601. IEEE (1999)
Sims, K.: Evolving 3D morphology and behavior by competition. In: Artificial Life IV, pp. 28–39 (1994)
Sproewitz, A., Billard, A., Dillenbourg, P., Ijspeert, A.J.: Roombots - mechanical design of self-reconfiguring modular robots for adaptive furniture. In: IEEE International Conference on Robotics and Automation (ICRA 2009), pp. 4259–4264. IEEE (2009)
Usui, Y., Arita, T.: Situated and embodied evolution in collective evolutionary robotics. In: Proceedings of the 8th International Symposium on Artificial Life and Robotics, pp. 212–215 (2003)
Waibel, M., Floreano, D., Keller, L.: A quantitative test of Hamilton’s rule for the evolution of altruism. PLOS Biol. 9(5), e1000615 (2011)
Watson, R., Ficici, S., Pollack, J.B.: Embodied evolution: distributing an evolutionary algorithm in a population of robots. Robot. Auton. Syst. 39(1), 1–18 (2002)
Weel, B., Crosato, E., Heinerman, J., Haasdijk, E., Eiben, A.E.: A robotic ecosystem with evolvable minds and bodies. In: 2014 IEEE International Conference on Evolvable Systems (ICES), pp. 165–172. IEEE (2014)
Zykov, V., Mytilinaios, E., Adams, B., Lipson, H.: Self-reproducing machines. Nature 435(7039), 163–164 (2005)
Zykov, V., Mytilinaios, E., Desnoyer, M., Lipson, H.: Evolved and designed self-reproducing modular robotics. IEEE Trans. Robot. 23(2), 308–319 (2007)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Eiben, A.E. (2015). EvoSphere: The World of Robot Evolution. In: Dediu, AH., Magdalena, L., Martín-Vide, C. (eds) Theory and Practice of Natural Computing. TPNC 2015. Lecture Notes in Computer Science(), vol 9477. Springer, Cham. https://doi.org/10.1007/978-3-319-26841-5_1
Download citation
DOI: https://doi.org/10.1007/978-3-319-26841-5_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-26840-8
Online ISBN: 978-3-319-26841-5
eBook Packages: Computer ScienceComputer Science (R0)