Abstract
We present the results of an experiment in the automatic design of control software for robot swarms. We conceived the experiment to corroborate a hypothesis that we proposed in a previous publication: the reality gap problem bears strong resemblance to the generalization problem faced in supervised learning. In particular, thanks to this experiment we observe for the first time a phenomenon that we shall call overdesign. Overdesign is the automatic design counterpart of the well known overfitting problem encountered in machine learning. Past an optimal level of the design effort, the longer the design process is protracted, the better the performance of the swarm becomes in simulation and the worst in reality. Our results show that some sort of early stopping mechanism could be beneficial.
This research was conceived by MB and GF and was directed by MB. The experiment was performed by YK using automatic design software developed by BD on the basis of a previous version by GF. The article was drafted by MB and GF. All authors read the manuscript and provided feedback. BD is currently with the Department of Advanced Robotics, Istituto Italiano di Tecnologia (IIT), Genova, Italy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
For a more advanced and general treatment of the issue, see also [57].
References
Baldassarre, G., Trianni, V., Bonani, M., Mondada, F., Dorigo, M., Nolfi, S.: Self-organised coordinated motion in groups of physically connected robots. IEEE Trans. Syst. Man Cybern. Part B 37(1), 224–239 (2007)
Bauer, F., Pereverzev, S., Rosasco, L.: On regularization algorithms in learning theory. J. Complex. 23, 52–72 (2007)
Berman, S., Kumar, V., Nagpal, R.: Design of control policies for spatially inhomogeneous robot swarms with application to commercial pollination. In: International Conference on Robotics and Automation, ICRA 2011, pp. 378–385. IEEE Press, Piscataway (2011)
Birattari, M.: Tuning Metaheuristics: A Machine Learning Perspective. Springer, Germany (2009)
Bongard, J., Zykov, V., Lipson, H.: Resilient machines through continuous self-modeling. Science 314(5802), 1118–1121 (2006)
Bongard, J.C.: Evolutionary robotics. Commun. ACM 56(8), 74–83 (2013)
Brambilla, M., Brutschy, A., Dorigo, M., Birattari, M.: Property-driven design for swarm robotics: a design method based on prescriptive modeling and model checking. ACM Trans. Auton. Adapt. Syst. 9(4), 17.1–17.28 (2015)
Brambilla, M., Ferrante, E., Birattari, M., Dorigo, M.: Swarm robotics: a review from the swarm engineering perspective. Swarm Intell. 7(1), 1–41 (2013)
Brooks, R.A.: Artificial life and real robots. In: Varela, F.J., Bourgine, P. (eds.) Toward a Practice of Autonomous Systems. Proceedings of the First European Conference on Artificial Life, pp. 3–10. MIT Press, Cambridge (1992)
Caruana, R., Lawrence, S., Giles, L.: Overfitting in neural nets: backpropagation, conjugate gradient, and early stopping. In: Leen, T., Dietterich, T., Tresp, V. (eds.) Advances in Neural Information Processing Systems 13, NIPS 2000, pp. 402–408. MIT Press (2001)
Christensen, A.L., Dorigo, M.: Evolving an integrated phototaxis and hole-avoidance behavior for a swarm-bot. In: Artificial Life, ALIFE 2006, pp. 248–254. MIT Press, Cambridge (2006)
Cybenko, G.: Approximations by superpositions of a sigmoidal function. Math. Control Signals Syst. 2(4), 303–314 (1989)
Dietterich, T., Kong, E.B.: Machine learning bias, statistical bias, and statistical variance of decision tree algorithms. Technical report, Department of Computer Science, Oregon State University (1995)
Doncieux, S., Mouret, J.B.: Beyond black-box optimization: a review of selective pressures for evolutionary robotics. Evol. Intell. 7(2), 71–93 (2014)
Duarte, M., Oliveira, S.M., Christensen, A.L.: Evolution of hierarchical controllers for multirobot systems. In: Artificial Life, ALIFE 2014, pp. 657–664. MIT Press, Cambridge (2014)
Duarte, M., Oliveira, S.M., Christensen, A.L.: Hybrid control for large swarms of aquatic drones. In: Artificial Life, ALIFE 2014, pp. 785–792. MIT Press, Cambridge (2014)
Duarte, M., Costa, V., Gomes, J.C., Rodrigues, T., Silva, F., Oliveira, S.M., Christensen, A.L.: Evolution of collective behaviors for a real swarm of aquatic surface robots. arXiv-CoRR abs/1511.03154 (2015)
Floreano, D., Husbands, P., Nolfi, S.: Evolutionary robotics. In: Siciliano, B., Khatib, O. (eds.) Handbook of Robotics, pp. 1423–1451. Springer, Germany (2008)
Francesca, G., Birattari, M.: Automatic design of robot swarms: achievements and challenges. Front. Robot. AI 3(29), 1–9 (2016)
Francesca, G., Brambilla, M., Brutschy, A., Garattoni, L., Miletitch, R., Podevijn, G., Reina, A., Soleymani, T., Salvaro, M., Pinciroli, C., Mascia, F., Trianni, V., Birattari, M.: AutoMoDe-Chocolate: automatic design of control software for robot swarms. Swarm Intell. 9(2/3), 125–152 (2015)
Francesca, G., et al.: An experiment in automatic design of robot swarms. In: Dorigo, M., Birattari, M., Garnier, S., Hamann, H., Montes de Oca, M., Solnon, C., Stützle, T. (eds.) ANTS 2014. LNCS, vol. 8667, pp. 25–37. Springer, Heidelberg (2014)
Francesca, G., Brambilla, M., Brutschy, A., Trianni, V., Birattari, M.: AutoMoDe: a novel approach to the automatic design of control software for robot swarms. Swarm Intell. 8(2), 89–112 (2014)
Garattoni, L., Francesca, G., Brutschy, A., Pinciroli, C., Birattari, M.: Software infrastructure for e-puck (and TAM). Technical report 2015–004, IRIDIA, Université Libre de Bruxelles, Brussels, Belgium (2015)
Gauci, M., Chen, J., Li, W., Dodd, T.J., Groß, R.: Self-organized aggregation without computation. Int. J. Robot. Res. 33(8), 1145–1161 (2014)
Gauci, M., Chen, J., Li, W., Dodd, T.J., Groß, R.: Clustering objects with robots that do not compute. In: Lomuscio, A., et al. (eds.) Autonomous Agents and Multiagent Systems, AAMAS 2014, pp. 421–428. IFAAMAS, Richland (2014)
Geman, S., Bienenstock, E., Doursat, R.: Neural networks and the bias/variance dilemma. Neural Comput. 4(1), 1–58 (1992)
Gutiérrez, Á., Campo, A., Dorigo, M., Donate, J., Monasterio-Huelin, F., Magdalena, L.: Open e-puck range & bearing miniaturized board for local communication in swarm robotics. In: International Conference on Robotics and Automation, ICRA 2009, pp. 3111–3116. IEEE Press, Piscataway (2009)
Hamann, H., Wörn, H.: A framework of space-time continuous models for algorithm design in swarm robotics. Swarm Intell. 2(2), 209–239 (2008)
Hecker, J.P., Letendre, K., Stolleis, K., Washington, D., Moses, M.E.: Formica ex machina: ant swarm foraging from physical to virtual and back again. In: Dorigo, M., Birattari, M., Blum, C., Christensen, A.L., Engelbrecht, A.P., Groß, R., Stützle, T. (eds.) ANTS 2012. LNCS, vol. 7461, pp. 252–259. Springer, Heidelberg (2012)
Jacobi, N., Husbands, P., Harvey, I.: Noise and the reality gap: the use of simulation in evolutionary robotics. In: Morán, F., et al. (eds.) Advances in Artificial Life. LNCS (LNAI), vol. 929, pp. 704–720. Springer, London (1995)
Jakobi, N.: Evolutionary robotics and the radical envelope-of-noise hypothesis. Adapt. Behav. 6(2), 325–368 (1997)
Kazadi, S., Lee, J.R., Lee, J.: Model independence in swarm robotics. Int. J. Intell. Comput. Cybern. 2(4), 672–694 (2009)
Koos, S., Mouret, J., Doncieux, S.: The transferability approach: crossing the reality gap in evolutionary robotics. IEEE Trans. Evol. Comput. 17(1), 122–145 (2013)
Lopes, Y.K., Trenkwalder, S.M., Leal, A.B., Dodd, T.J., Groß, R.: Supervisory control theory applied to swarm robotics. Swarm Intell. 10(1), 65–97 (2016)
McCulloch, W., Pitts, W.: A logical calculus of ideas immanent in nervous activity. Bull. Math. Biophys. 5(4), 115–133 (1943)
Miglino, O., Lund, H.H., Nolfi, S.: Evolving mobile robots in simulated and real environments. Artif. Life 2(4), 417–434 (1995)
Minsky, M., Papert, S.: Perceptrons: An Introduction to Computational Geometry. MIT Press, Cambridge (1969)
Mondada, F., et al.: The e-puck, a robot designed for education in engineering. In: 9th Conference on Autonomous Robot Systems and Competitions, pp. 59–65. Instituto Politécnico de Castelo Branco, Portugal (2009)
Morgan, N., Bourlard, H.: Generalization and parameter estimation in feedforward nets: some experiments. In: Touretzky, D. (ed.) Advances in Neural Information Processing Systems 2, NIPS 1990, pp. 630–637. Morgan Kaufman, San Mateo (1990)
Nolfi, S., Floreano, D.: Evolutionary Robotics. MIT Press, Cambridge (2000)
Pinciroli, C., Trianni, V., O’Grady, R., Pini, G., Brutschy, A., Brambilla, M., Mathews, N., Ferrante, E., Di Caro, G., Ducatelle, F., Birattari, M., Gambardella, L.M., Dorigo, M.: ARGoS: a modular, parallel, multi-engine simulator for multi-robot systems. Swarm Intell. 6(4), 271–295 (2012)
Prechelt, L.: Early stopping-but when? In: Orr, G.B., Müller, K.-R. (eds.) NIPS-WS 1996. LNCS, vol. 1524, pp. 55–59. Springer, Heidelberg (1998)
Quinn, M., Smith, L., Mayley, G., Husbands, P.: Evolving controllers for a homogeneous system of physical robots: structured cooperation with minimal sensors. Philos. Trans. Royal Soc. London A Math. Phys. Eng. Sci. 361(1811), 2321–2343 (2003)
Raskutti, G., Wainwright, M.J., Yu, B.: Early stopping and non-parametric regression: an optimal data-dependent stopping rule. J. Mach. Learn. Res. 15, 335–366 (2014)
Reina, A., Valentini, G., Fernández-Oto, C., Dorigo, M., Trianni, V.: a design pattern for decentralised decision making. PLoS ONE 10(10), e0140950 (2015)
Rosenblatt, F.: The perceptron: a probabilistic model for information storage and organization in the brain. Psychol. Rev. 65(6), 386–408 (1958)
Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015)
Silva, F., Duarte, M., Correia, L., Oliveira, S.M., Christensen, A.L.: Open issues in evolutionary robotics. Evol. Comput. (2016, in press)
Stone, M.: Cross-validatory choice and assessment of statistical predictions. J. Royal Stat. Soc. Ser. B (Methodol.) 36(2), 111–147 (1974)
Stranieri, A., Turgut, A., Salvaro, M., Garattoni, L., Francesca, G., Reina, A., Dorigo, M., Birattari, M.: IRIDIA’s arena tracking system. Technical report 2013–013, IRIDIA, Université Libre de Bruxelles, Brussels, Belgium (2013)
Trianni, V., Nolfi, S.: Self-organising sync in a robotic swarm. A dynamical system view. IEEE Trans. Evol. Comput. 13(4), 722–741 (2009)
Trianni, V.: Evolutionary Swarm Robotics. Springer, Germany (2008)
Trianni, V.: Evolutionary robotics: model or design? Front. Robot. AI 1(13), 1–6 (2014)
Waibel, M., Keller, L., Floreano, D.: Genetic team composition and level of selection in the evolution of cooperation. IEEE Trans. Evol. Comput. 13(3), 648–660 (2009)
Werbos, P.: Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences. Ph.D. thesis, Harvard University, Cambridge (1974)
Werfel, J., Petersen, K., Nagpal, R.: Designing collective behavior in a termite-inspired robot construction team. Science 343(6172), 754–758 (2014)
Wolpert, D.: On bias plus variance. Neural Comput. 9(6), 1211–1243 (1997)
Acknowledgments
Mauro Birattari acknowledges support from the Belgian F.R.S.–FNRS, of which he is a Senior Research Associate.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Birattari, M., Delhaisse, B., Francesca, G., Kerdoncuff, Y. (2016). Observing the Effects of Overdesign in the Automatic Design of Control Software for Robot Swarms. In: Dorigo, M., et al. Swarm Intelligence. ANTS 2016. Lecture Notes in Computer Science(), vol 9882. Springer, Cham. https://doi.org/10.1007/978-3-319-44427-7_13
Download citation
DOI: https://doi.org/10.1007/978-3-319-44427-7_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-44426-0
Online ISBN: 978-3-319-44427-7
eBook Packages: Computer ScienceComputer Science (R0)