Abstract
Automatic design of neurocontrollers (as in Evoluationary Robotics) utilizes incremental evolution to solve for more complex behaviors. Also manual design techniques such as task decomposition are employed. Manual design itself can benefit from focusing on using incremental evolution to add more automatic design. The imbalance network is a neural network that integrates incremental evolution with an incremental design process without the need for task decomposition. Instead, the imbalance network uses the mechanism of the equilibrium-action cycle to structure the network while emphasizing behavior emergence. An example 11-step design (including a 5-step evolutionary process) is briefly mentioned to help ground the imbalance network concepts.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Nelson, A.L., Barlow, G.J., Doitsidis, L.: Fitness functions in evolutionary robotics: A survey and analysis. Robotics and Autonomous Systems 57(4), 345–370 (2009)
Duarte, M., Oliveira, S., Christensen, A.L.: Hierarchical evolution of robotic controllers for complex tasks. In: 2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL), pp. 1–6. IEEE (November 2012)
Floreano, D., Dürr, P., Mattiussi, C.: Neuroevolution: from architectures to learning. Evolutionary Intelligence 1(1), 47–62 (2008)
Harvey, I., Husbands, P., Cliff, D., Thompson, A., Jakobi, N.: Evolutionary robotics: the Sussex approach. Robotics and Autonomous Systems 20(2), 205–224 (1997)
Gomez, F., Miikkulainen, R.: Incremental evolution of complex general behavior. Adaptive Behavior 5(3-4), 317–342 (1997)
Mouret, J.B., Doncieux, S.: Overcoming the bootstrap problem in evolutionary robotics using behavioral diversity. In: IEEE Congress on Evolutionary Computation, CEC 2009, pp. 1161–1168. IEEE (May 2009)
Seth, A.K.: Evolving action selection and selective attention without actions, attention, or selection. In: Proceedings of the Fifth International Conference on Simulation of Adaptive Behavior on From Animals to Animats, vol. 5, pp. 139–146 (September 1998)
Togelius, J.: Evolution of a subsumption architecture neurocontroller. Journal of Intelligent and Fuzzy Systems 15(1), 15–20 (2004)
Harvey, I.: Cognition is not computation; evolution is not optimisation. In: Gerstner, W., Hasler, M., Germond, A., Nicoud, J.-D. (eds.) ICANN 1997. LNCS, vol. 1327, pp. 685–690. Springer, Heidelberg (1997)
Olivier, P., Arostegui, J.M.M.: The Equilibrium-action cycle as a mechanism for design-evolution integration in autonomous behavior design. In: 2012 NASA/ESA Conference on Adaptive Hardware and Systems (AHS), pp. 190–197. IEEE (June 2012)
E-puck educational robot, http://www.e-puck.org/
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Olivier, P., Moreno Arostegui, J.M. (2013). The Imbalance Network and Incremental Evolution for Mobile Robot Nervous System Design. In: Mladenov, V., Koprinkova-Hristova, P., Palm, G., Villa, A.E.P., Appollini, B., Kasabov, N. (eds) Artificial Neural Networks and Machine Learning – ICANN 2013. ICANN 2013. Lecture Notes in Computer Science, vol 8131. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40728-4_65
Download citation
DOI: https://doi.org/10.1007/978-3-642-40728-4_65
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40727-7
Online ISBN: 978-3-642-40728-4
eBook Packages: Computer ScienceComputer Science (R0)