Abstract
Recent works explored the possibility of designing physical robots using evolutionary algorithms. We propose a novel algorithm for the evolution of morphology and control of autonomous robots controlled by artificial neural networks. The proposed algorithm is inspired by NeuroEvolution of Augmenting Topologies (NEAT) which efficiently evolves artificial neural networks. All three main components of NEAT algorithm (protecting evolutionary innovation through speciation, effective crossover of neural networks with different topologies and incremental growth from minimal structure) are applied to the evolution of both morphology and control system of a robot. Large-scale experiments with simulated robots have shown that the proposed algorithm uses significantly less fitness evaluations than a standard genetic algorithm on all four tested fitness functions. Positive contribution of each component of the proposed algorithm has been confirmed with a series of supplementary ablation experiments.
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
Bongard, L.H., Zykov, J., Resilient, V.: machines through continuous self-modeling. Science 314(5802), 1118–1121 (2006)
Goldberg, D.E., Richardson, J.: Genetic algorithms with sharing for multimodal function optimization. In: Proceedings of the Second International Conference on Genetic Algorithms on Genetic algorithms and their application, pp. 41–49. Lawrence Erlbaum Associates, Inc, Mahwah (1987)
Hornby, G.S., Lipson, H., Pollack, J.B.: Evolution of generative design systems for modular physical robots. In: IEEE International Conference on Robotics and Automation (ICRA) (2001)
Hornby, G.S., Pollack, J.B.: Body-brain co-evolution using L-systems as a generative encoding. In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2001), pp. 868–875. Morgan Kaufmann, San Francisco (2001)
Krcah, P.: Evolutionary development of robotic organisms. Master’s thesis, Charles University in Prague (September 2007)
Krcah, P.: Towards efficient evolutionary design of autonomous robots. Technical Report 2008/4, Charles University in Prague (2008)
Lipson, H., Pollack, J.B.: Automatic design and manufacture of robotic lifeforms. Nature 406, 974–978 (2000)
Miconi, T., Channon, A.: An improved system for artificial creatures evolution. In: Proceedings of the 10th conference on the simulation and synthesis of living systems (ALIFE X). MIT Press, Bloomington (2006)
Sims, K.: Evolving virtual creatures. In: SIGGRAPH 1994: Proceedings of the 21st annual conference on Computer graphics and interactive techniques, pp. 15–22. ACM Press, New York (1994)
Smith, R.: ODE manual, http://www.ode.org
Stanley, K.O., Miikkulainen, R.: Efficient reinforcement learning through evolving neural network topologies. In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2002). Morgan Kaufmann, San Francisco (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Krčah, P. (2008). Towards Efficient Evolutionary Design of Autonomous Robots. In: Hornby, G.S., Sekanina, L., Haddow, P.C. (eds) Evolvable Systems: From Biology to Hardware. ICES 2008. Lecture Notes in Computer Science, vol 5216. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-85857-7_14
Download citation
DOI: https://doi.org/10.1007/978-3-540-85857-7_14
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-85856-0
Online ISBN: 978-3-540-85857-7
eBook Packages: Computer ScienceComputer Science (R0)