Abstract
In this report we introduce an artificial evolutionary system, Artificial Ontogeny (AO), that uses a developmental encoding scheme to translate a given genotype into a complete agent, which then acts in a physically-realistic virtual environment. Evolution is accomplished using a genetic algorithm, in which the genotypes are treated as genetic regulatory networks. The dynamics of the regulatory network direct the growth of the agent, and lead to the construction of both the morphology and neural control of the agent. We demonstrate that such a model can be used to evolve agents to perform non-trivial tasks, such as directed locomotion and block pushing in a noisy environment. It is shown that mutations expressed earlier in development tend to have a more variable morphological and behavioural effect than mutations expressed later in development, which tend to have a less pronounced effect. These results support the hypothesis that ontogeny provides artificial evolution with beneficial mutations that have varying degrees of phenotypic effect, depending on their onset of expression during development. In addition, we evolve agents using a fitness function which indirectly selects for increased size. In these agents we find evidence of functional specialization and repeated, differentiated structure. In the final section we argue that such a system would be a useful tool for the evolutionary design of morpo-functional machines.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Anderson KV, Nüsslein-Volhard C (1984) Information for the dorso-ventral pattern of the Drosophila embryo is stored in maternal mRNA. Nature 311:223–227
Bongard JC, Paul C (2000) Investigating morphological symmetry and locomotive efficiency using virtual embodied evolution. In: Procs Sixth Intl Conf on Simulation of Adaptive Behaviour, MIT Press, pp. 420–429.
Brooks RA (1990) Elephants don’t play chess. Robotics and Autonomous Systems 6:3–15.
Delleart F, Beer RD (1994) A developmental model for the evolution of complete autonomous agents. Artificial Life IV, MIT Press, pp. 246–257.
Eggenberger P (1997) Evolving morphologies of simulated 3D organisms based on differential gene expression. In: Procs Fourth European Conf Artificial Life, Springer-Verlag, pp. 205–213.
Gehring WJ (1998) Master control genes in development and evolution: the Homeobox story (Terry Lectures).Yale University Press, USA
Gruau F, Whitley D, Pyeatt L (1996) A comparison between cellular encoding and direct encoding for genetic neural networks. In: Procs First Genetic Programming Conf, MIT Press, pp. 81–89
Hara F, Pfeifer R (2000) On the relation among morphology, material and control in mor-phofunctional machines. In: Procs Sixth Intl Conf on Simulation of Adaptive Behaviour, MIT Press, pp. 33–40
Ijspeert AJ, Kodjabachian J (1999) Evolution and development of a central pattern generator for the swimming of a lamprey’. Artificial Life 5:3, pp. 247–269.
Kater SB, Guthrie PB (1990) Neuronal growth cone as an integrator of complex environmental information. In: Cold Spring Harbor Symposia on Quantitative Biology, Volume LV, pp. 359–370.
Kauffman SA (1993) The origins of order. Oxford University Press, London
Kawai N, Hara F (1998) Formation of morphology and morphofunction in a linear cluster robotic system. In: Procs Fifth Intl Conf on Simulation of Adaptive Behaviour, MIT Press, pp. 459–464
Kirschner M, Gerhart J (1998) Evolvability. Proc. Nat. Acad. Sei, 95:8420–8427
Komosinski M, Ulatowski S (1998) Framsticks: towards a simulation of a nature-like world, creatures and evolution. In: Procs Fifth Euro Conf Artificial Life, Springer-Verlag, pp. 261–265
Lichtensteiger L, Eggenberger P (1999) Evolving the morphology of a compound eye on a robot. In: Procs Third Euro Workshop on Advanced Mobile Robots, pp. 127–134
Lipson H, Pollack JB (2000) Automatic design and manufacture of artificial lifeforms. Nature 406:974–978
McGeer T (1990) Passive dynamic walking. Intl Journal of Robotics Research 9:62–82
Pfeifer R. (1999) Understanding Intelligence. MIT Press, USA
Raff RA (1996) The shape of life: genes, development, and the evolution of animal form. University of Chicago Press, pp. 321–361
Reil T (1999) Dynamics of gene expression in an artificial genome-Implications for biological and artificial ontogeny. In: Procs Fourth Euro Conf on Artificial Life, Springer-Verlag, pp. 457–466
Sims K (1994) Evolving 3D morphology and behaviour by competition. Artificial Life IV, MIT Press, pp. 28–39
Terzopoulos D, Rabie T, Grzeszczuk R (1996) Perception and learning in artificial animals. Artificial Life V, MIT Press, pp. 313–320
Ventrella J (1994) Explorations of morphology and locomotion behaviour in animated characters. Artificial Life IV, MIT Press, pp. 436–441
Wagner G, Altenberg L (1996) Perspective: Complex adaptations and the evolution of evolvability. Evolution, 50:(3), pp. 967–976
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer Japan
About this paper
Cite this paper
Bongard, J.C., Pfeifer, R. (2003). Evolving Complete Agents using Artificial Ontogeny. In: Hara, F., Pfeifer, R. (eds) Morpho-functional Machines: The New Species. Springer, Tokyo. https://doi.org/10.1007/978-4-431-67869-4_12
Download citation
DOI: https://doi.org/10.1007/978-4-431-67869-4_12
Publisher Name: Springer, Tokyo
Print ISBN: 978-4-431-68006-2
Online ISBN: 978-4-431-67869-4
eBook Packages: Springer Book Archive