Many animals are able to modify their morphology during their lifetime in response to changes in the environment. Such modifications are often adaptive—they can improve individual’s chances of survival and reproduction. In this paper we explore the effects of such morphological plasticity on body–brain coevolution of virtual creatures. We propose a method where morphological plasticity is achieved through learning during individual’s lifetime allowing each individual to quickly adapt its morphology to the current environment. We show that the resulting plasticity allows evolution of creatures better adapted to different simulated environments. We also show that evolution combined with the new learning rule reduces the total computational cost required to evolve an individual with a given target fitness compared to evolution without learning.
AgrawalA. A. (2001). Phenotypic plasticity in the interactions and evolution of species. Science, 294, 321–326.
2.
BaldwinJ. M. (1896). A new factor in evolution. The American Naturalist, 30, 441–451.
3.
BongardJ. (2008). Behavior chaining: incremental behavioral integration for evolutionary robotics. In BullockS.NobleJ.WatsonR.BedauM. A. (Eds.), Artificial Life XI: Proceedings of the eleventh international conference on the simulation and synthesis of living systems (pp. 64–71). Cambridge, MA: MIT Press.
4.
BongardJ. (2011). Morphological change in machines accelerates the evolution of robust behavior. Proceedings of the National Academy of Sciences, 108 (4), 1234–1239.
5.
DennettD. C. (1991). Consciousness explained. Boston, MA: Little, Brown.
6.
DennettD. C. (2003). The Baldwin effect: A crane, not a skyhook. In WeberB. H.DepewD. J. (Eds.), Evolution and learning: The Baldwin effect reconsidered (pp. 60–79). Cambridge, MA: MIT Press, Bradford Books.
7.
FloreanoD.MondadaF. (1996). Evolution of plastic neurocontrollers for situated agents. In From animals to animats 4: Proceedings of the 4th international conference on simulation of adaptive behavior (SAB 1996) (pp. 402–410).
8.
FuscoG.MinelliA. (2010). Phenotypic plasticity in development and evolution: Facts and concepts. Philosophical Transactions of the Royal Society B: Biological Sciences, 365, 547.
9.
HintonG. E.NowlanS. J. (1987). How learning can guide evolution. Complex Systems, 1, 495–502.
10.
HornbyG. S.PollackJ. B. (2001). Body–brain co-evolution using L-systems as a generative encoding. In L. S.. (Ed.), Proceedings of the genetic and evolutionary computation conference (GECCO-2001) (pp. 868–875). San Francisco, CA: Morgan Kaufmann Publishers.
11.
KrčahP. (2008). Towards efficient evolutionary design of autonomous robots. In HornbyG. S.SekaninaL.HaddowP. C. (Eds.), ICES ’08: Proceedings of the 8th international conference on evolvable systems: From biology to hardware (Vol. 5216, pp. 153–164). Berlin, Heidelberg, Germany: Springer-Verlag.
12.
LessinD.FussellD.MiikkulainenR. (2014). Adapting morphology to multiple tasks in evolved virtual creatures. In SayamaH.RieffelJ.RisiS. (Eds.), Proceedings of the fourteenth international conference on the synthesis and simulation of living systems (ALIFE 14) 2014 (pp. 247–254). Cambridge, MA: MIT Press.
13.
LipsonH.PollackJ. B. (2000, August). Automatic design and manufacture of robotic lifeforms. Nature, 406, 974–978.
14.
MoczekA. P.SultanS.FosterS.. (2011). The role of developmental plasticity in evolutionary innovation. Proceedings of the Royal Society of London B: Biological Sciences, 278, 2705–2713.
15.
NolfiS.FloreanoD. (1999). Learning and evolution. Autonomous Robots, 7, 89–113.
16.
NolfiS.ParisiD.ElmanJ. L. (1994). Learning and evolution in neural networks. Adaptive Behavior, 3, 5–28.
17.
NolfiS.TaniJ. (1999). Extracting regularities in space and time through a cascade of prediction networks: The case of a mobile robot navigating in a structured environment. Connection Science, 11, 125–148.
18.
OsterG. F.WilsonE. O. (1978). Caste and ecology in the social insects. New Jersey, USA: Princeton University Press.
19.
RoperM.KatsarosN.FernandoC. (2014). Voxel robot: A pneumatic robot with deformable morphology. In PobilA. P. D.ChinellatoE.Martínez-MartínE. (Eds.), From animals to animats 13: 13th international conference on simulation of adaptive behavior (SAB 2014) (Vol. 8575, pp. 230–239). Springer.
20.
SimsK. (1994). Evolving virtual creatures. In SIGGRAPH ’94: Proceedings of the 21st annual conference on computer graphics and interactive techniques (pp. 15–22). New York: ACM Press.
21.
SmithJ. M. (1987). Natural selection: When learning guides evolution. Nature, 329, 761–762. (reprint in: Adaptive Individuals in Evolving Populations: Models and Algorithms, BelewR. K.MitchellM. (eds.), 1996, pp. 455–457, Reading, MA: Addison Wesley.)
22.
SmithR. (2005). ODE: Open Dynamics Engine. Retrieved from http://www.ode.org
WaddingtonC. H. (1942). Canalization of development and the inheritance of acquired characters. Nature, 150, 563–565.
25.
WaddingtonC. H. (1953). Genetic assimilation of an acquired character. Evolution, 7, 118–126.
26.
West-EberhardM. J. (2003). Developmental plasticity and evolution. New York: Oxford University Press.
27.
WhitmanD. W.AgrawalA. A. (2009). What is phenotypic plasticity and why is it important? In WhitmanD. W.AnanthakrishnanT. N. (Eds.), Phenotypic plasticity of insects: Mechanisms and consequences (Vol. 10, pp. 1–63). Enfield, NH: Science Publishers.
