Ben Jones
ABSTRACT
Body morphology is thought to have heavily influenced the evolution of neural architecture. However, the extent of this interaction and its underlying principles are largely unclear. To help us elucidate these principles, we examine the artificial evolution of a hypothetical nervous system embedded in a fish-inspired animat. The aim is to observe the evolution of neural structures in relation to both body morphology and required motor primitives. Our investigations reveal that increasing the pressure to evolve a wider range of movements also results in higher levels of neural symmetry. We further examine how different body shapes affect the evolution of neural structure; we find that, in order to achieve optimal movements, the neural structure integrates and compensates for asymmetrical body morphology. Our study clearly indicates that different parts of the animat - specifically, nervous system and body plan - evolve in concert with and become highly functional with respect to the other parts. The autonomous emergence of morphological and neural computation in this model contributes to unveiling the surprisingly strong coupling of such systems in nature.
- T. Bäck and H.-P. Schwefel. An overview of evolutionary algorithms for parameter optimization. Evolutionary Computation, 1(1):1--23, 1993. Google Scholar
Digital Library
- J. Blynel and D. Floreano. Levels of dynamics and adaptive behavior in evolutionary neural controllers. In From animals to animats: The seventh international conference on simulation of adaptive behavior, pages 272--281, Cambridge, MA, 2002. MIT Press. Google ScholarDigital Library
- J. Bongard. Morphological change in machines accelerates the evolution of robust behavior. Proceedings of the National Academy of Sciences, 108(4):1234--1239, 2011.Google ScholarCross Ref
- J. Bongard and R. Pfeifer. Evolving complete agents using artificial ontogeny. In Morpho-functional Machines: The New Species (Designing Embodied Intelligence), pages 237--258. Springer, Berlin, 2003.Google Scholar
- J.C. Bongard. Incremental Approaches to the Combined Evolution of a Robot's Body and Brain. PhD thesis, Mathematisch-naturwissenschaftlichen Fakultät der Universität Zürich, Zürich, 2003.Google Scholar
- J.C. Bongard and C. Paul. Investigating morphological symmetry and locomotive efficiency using virtual embodied evolution. In From Animals to Animats: The Sixth International Conference on Simulation of Adaptive Behavior, Cambridge, MA, 2000. MIT Press.Google Scholar
- V. Braitenberg. Vehicles: Experiments in synthetic psychology. MIT Press, Cambridge, Mass, 1984.Google Scholar
- M. Broun, S. Sokol, and H.R. Bode. Cngsc, a homologue of goosecoid, participates in the patterning of the head, and is expressed in the organizer region of Hydra. Development, 126:5245--5254, 1999.Google Scholar
- J.R. Finnerty. The origins of axial patterning in the metazoa: how old is bilateral symmetry? International Journal of Developmental Biology, 47(7--8):523--529, 2003.Google Scholar
- A. Ghysen. The origin and evolution of the nervous system. International Journal of Developmental Biology, 47(8):555--562, 2003.Google Scholar
- N.D. Holland. Early central nervous systems evolution: an era of skin brains? Nature reviews, 4(8):617--627, 2003.Google Scholar
- B. Jones. The Evolutionary Emergence of Neural Organisation in Computational Models of Primitive Organisms. PhD thesis, Computer Science, University of Bimringham, Birmingham, UK, 2010.Google Scholar
- B. Jones, Y. Jin, B. Sendhoff, and X. Yao. Evolving functional symmetry in a three dimensional model of an elongated organism. In Artificial Life XI: Proceedings of the Eleventh International Conference on the Simulation and Synthesis of Living Systems, pages 305--312, Cambridge, MA, 2008. MIT Press.Google Scholar
- B. Jones, Y. Jin, X. Yao, and B. Sendhoff. Evolution of neural organization in a hydra-like animat. In Proceedings of the 15th International Conference on Neural Information Processing of the Asia-Pacific Neural Network Assembly, volume 1, pages 216--223, Berlin, 2008. Springer. Google ScholarDigital Library
- M. Manuel. Early evolution of symmetry and polarity in metazoan body plans. Comptes Rendus Biologies, 332(2--3):184--209, 2009.Google Scholar
- M.Q. Martindale, J.R. Finnerty, and J.Q. Henry. The Radiata and the evolutionary origins of the bilaterian body plan. Molecular Phylogenetics and Evolution, 24(3):358--365, 2002.Google ScholarCross Ref
- H. Meinhardt. The radial-symmetric hydra and the evolution of the bilateral body plan: an old body become a young brain. BioEssays, 24:181--191, 2002.Google ScholarCross Ref
- H. Meinhardt. Different strategies for midline formation in bilaterians. Nature, 5:502--510, 2004.Google Scholar
- Y. Murakami, K. Uchida, F.M. Rijli, and S. Kuratani. Evolution of the brain developmental plan: insights from agnathans. Developmental Biology, 280(2):249--259, 2005.Google ScholarCross Ref
- R.W. Paine and J. Tani. How hierarchical control self-organizes in artificial adaptive systems. Adaptive Behavior, 13(3):211--225, 2005.Google ScholarCross Ref
- J. Sarma and K. De Jong. An analysis of the effects of neighborhood size and shape on local selection algorithms. In Parallel Problem Solving from Nature -- PPSN IV, volume 1141, pages 236--244, Berlin, 1996. Springer. Google ScholarDigital Library
- L. Schramm, Y. Jin, and B. Sendhoff. Emerged coupling of motor control and morphological development in evolution of multi-cellular animats. In Proceedings of the 10th European Conference on Artificial Life, pages 25--32, Berlin, 2009. Springer. Google ScholarDigital Library
- M. Sfakiotakis and D.P. Tsakiris. Simuun: A simulation environment for undulatory locomotion. International Journal of Modelling and Simulation, 26(4):350--358, 2006.Google ScholarCross Ref
- M.A. Shenk, H.R. Bode, and R.E. Steele. Expression of Cnox-2, a HOM/HOX homeobox gene in hydra, is correlated with axial pattern formation. Development, 117:657--667, 1993.Google Scholar
- K. Sims. Evolving 3D morphology and behavior by competition. Artificial Life, 1(4):353--372, 1994. Google ScholarDigital Library
- A. Soltoggio, J.A. Bullinaria, C. Mattiussi, P. Dürr, and D. Floreano. Evolutionary Advantages of Neuromodulated Plasticity in Dynamic, Reward-based Scenarios. In Artificial Life XI: Proceedings of the Eleventh International Conference on the Simulation and Synthesis of Living Systems, pages 569--576, Cambridge, MA, 2008. MIT Press.Google Scholar
- K.O. Stanley, D.B. D'Ambrosio, and J. Gauci. A hypercube-based encoding for evolving large-scale neural networks. Artificial Life, 15(2):185--212, 2009. Google ScholarDigital Library
- L. Steels and R. Brooks, editors. The Artificial Life Route to Artificial Intelligence: Building Embodied, Situated Agents. Lawrence Erlbaum Associates, Inc., New Jersey, 1995. Google ScholarDigital Library
Index Terms
- Evolution of neural symmetry and its coupled alignment to body plan morphology
Recommendations
Evolving neural networks
GECCO '11: Proceedings of the 13th annual conference companion on Genetic and evolutionary computationNeuroevolution, i.e. evolution of artificial neural networks, has recently emerged as a powerful technique for solving challenging reinforcement learning problems. Compared to traditional (e.g. value-function based) methods, neuroevolution is especially ...
A minimal developmental model can increase evolvability in soft robots
GECCO '17: Proceedings of the Genetic and Evolutionary Computation ConferenceDifferent subsystems of organisms adapt over many time scales, such as rapid changes in the nervous system (learning), slower morphological and neurological change over the lifetime of the organism (postnatal development), and change over many ...
Towards the evolution of multi-layered neural networks: a dynamic structured grammatical evolution approach
GECCO '17: Proceedings of the Genetic and Evolutionary Computation ConferenceCurrent grammar-based NeuroEvolution approaches have several shortcomings. On the one hand, they do not allow the generation of Artificial Neural Networks (ANNs) composed of more than one hidden-layer. On the other, there is no way to evolve networks ...
Comments