Abstract
In this paper, we investigate the dynamics of different neuronal models on online neuroevolution of robotic controllers in multirobot systems. We compare the performance and robustness of neural network-based controllers using summing neurons, multiplicative neurons, and a combination of the two. We perform a series of simulation-based experiments in which a group of e-puck-like robots must perform an integrated navigation and obstacle avoidance task in environments of different complexity. We show that: (i) multiplicative controllers and hybrid controllers maintain stable performance levels across tasks of different complexity, (ii) summing controllers evolve diverse behaviours that vary qualitatively during task execution, and (iii) multiplicative controllers lead to less diverse and more static behaviours that are maintained despite environmental changes. Complementary, hybrid controllers exhibit both behavioural characteristics, and display superior generalisation capabilities in simple and complex tasks.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Floreano, D., Keller, L.: Evolution of adaptive behaviour by means of Darwinian selection. PLoS Biology 8(1), e1000292 (2010)
Floreano, D., Dürr, P., Mattiussi, C.: Neuroevolution: from architectures to learning. Evolutionary Intelligence 1(1), 47–62 (2008)
Watson, R., Ficici, S., Pollack, J.: Embodied evolution: Distributing an evolutionary algorithm in a population of robots. Robotics and Autonomous Systems 39(1), 1–18 (2002)
Silva, F., Urbano, P., Oliveira, S., Christensen, A.L.: odNEAT: An algorithm for distributed online, onboard evolution of robot behaviours. In: 13th International Conference on Simulation & Synthesis of Living Systems, pp. 251–258. MIT Press, Cambridge (2012)
McCulloch, W., Pitts, W.: A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biology 5(4), 115–133 (1943)
Koch, C.: Biophysics of computation: information processing in single neurons. Oxford Univ. Press, Oxford (2004)
Cazenille, L., Bredeche, N., Hamann, H., Stradner, J.: Impact of neuron models and network structure on evolving modular robot neural network controllers. In: 14th Genetic and Evolutionary Computation Conference, pp. 89–96. ACM Press, New York (2012)
Durbin, R., Rumelhart, D.E.: Product units: A computationally powerful and biologically plausible extension to backpropagation networks. Neural Computation 1(1), 133–142 (1989)
Schmitt, M.: On the complexity of computing and learning with multiplicative neural networks. Neural Computation 14(2), 241–301 (2002)
Mondada, F., Bonani, M., Raemy, X., Pugh, J., Cianci, C., Klaptocz, A., Magnenat, S., Zufferey, J., Floreano, D., Martinoli, A.: The e-puck, a robot designed for education in engineering. In: 9th Conference on Autonomous Robot Systems and Competitions, IPCB, Castelo Branco, Portugal, pp. 59–65 (2009)
Floreano, D., Schoeni, N., Caprari, G., Blynel, J.: Evolutionary bits ’n’ spikes. In: 8th International Conference on Simulation & Synthesis of Living Systems, pp. 335–344. MIT Press, Cambridge (2003)
Mouret, J., Doncieux, S.: Encouraging behavioral diversity in evolutionary robotics: An empirical study. Evolutionary Computation 20(1), 91–133 (2012)
Fisher, R.: Statistical Methods for Research Workers. Oliver & Boyd, Edinburgh (1925)
Sammon Jr., J.: A nonlinear mapping for data structure analysis. IEEE Transactions on Computers C-18(5), 401–409 (1969)
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
Silva, F., Correia, L., Christensen, A.L. (2013). Dynamics of Neuronal Models in Online Neuroevolution of Robotic Controllers. In: Correia, L., Reis, L.P., Cascalho, J. (eds) Progress in Artificial Intelligence. EPIA 2013. Lecture Notes in Computer Science(), vol 8154. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40669-0_9
Download citation
DOI: https://doi.org/10.1007/978-3-642-40669-0_9
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40668-3
Online ISBN: 978-3-642-40669-0
eBook Packages: Computer ScienceComputer Science (R0)