Skip to main content
SpringerLink
Log in

AutoMoDe: A novel approach to the automatic design of control software for robot swarms

  • Published:
Swarm Intelligence Aims and scope Submit manuscript

Abstract

We introduce AutoMoDe: a novel approach to the automatic design of control software for robot swarms. The core idea in AutoMoDe recalls the approach commonly adopted in machine learning for dealing with the bias–variance tradedoff: to obtain suitably general solutions with low variance, an appropriate design bias is injected. AutoMoDe produces robot control software by selecting, instantiating, and combining preexisting parametric modules—the injected bias. The resulting control software is a probabilistic finite state machine in which the topology, the transition rules and the values of the parameters are obtained automatically via an optimization process that maximizes a task-specific objective function. As a proof of concept, we define AutoMoDe-Vanilla, which is a specialization of AutoMoDe for the e-puck robot. We use AutoMoDe-Vanilla to design the robot control software for two different tasks: aggregation and foraging. The results show that the control software produced by AutoMoDe-Vanilla (i) yields good results, (ii) appears to be robust to the so called reality gap, and (iii) is naturally human-readable.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Notes

  1. The reference model assumes that, besides the ambient light, at most one light source is present in the environment.

  2. State \(i=1\) is the initial state of the probabilistic finite state machine.

  3. Because AutoMoDe-Vanilla is stochastic, reporting and discussing its expected performance appears to be the appropriate choice (Birattari and Dorigo 2007).

  4. The reader might wonder why, in order to estimate the expected performance of AutoMoDe-Vanilla on each design budget, we repeat the design process 20 times and we test the resulting design on the robots only once. Due to time constraints, we have decided to run 20 robot experiments per design budget. Having fixed to 20 the total number of robot experiments, one might be tempted to consider alternative protocols: repeat the design 20 times and evaluate each resulting design 1 time; repeat the design 10 times and evaluate each resulting design 2 times; repeat the design 5 times and evaluate each resulting design 4 times; or even performing the design once and evaluate the result 20 times. Although all these protocols would produce an unbiased estimate of the expected performance of AutoMoDe-Vanilla, the one implemented in this study is the one that minimizes the variance of the estimate. A similar issue has been formally studied in the context of the assessment of stochastic optimization algorithms (Birattari 2004, 2009).

References

  • Baldassarre, G., Trianni, V., Bonani, M., Mondada, F., Dorigo, M., & Nolfi, S. (2007). Self-organised coordinated motion in groups of physically connected robots. IEEE Transactions on Systems, Man and Cybernetics-Part B, 37(1), 224–239.

    Article  Google Scholar 

  • Berman, S., Kumar V., & Nagpal. R. (2011). Design of control policies for spatially inhomogeneous robot swarms with application to commercial pollination. In 2011 IEEE International Conference on Robotics and Automation (ICRA) (pp. 378–385). Piscataway, NJ: IEEE Press.

  • Birattari, M. (2004). On the estimation of the expected performance of a metaheuristic on a class of instances. How many instances, how many runs? Technical report TR/IRIDIA/2004-001, IRIDIA, Université Libre de Bruxelles, Brussels, Belgium.

  • Birattari, M. (2009). Tuning metaheuristics: A machine learning perspective. Berlin, Germany: Springer.

    Book  Google Scholar 

  • Birattari, M., & Dorigo, M. (2007). How to assess and report the performance of a stochastic algorithm on a benchmark problem: Mean or best result on a number of runs? Optimization Letters, 1(3), 309–311.

    Article  MATH  MathSciNet  Google Scholar 

  • Birattari, M., Stützle, T., Paquete, L., & Varrentrapp, K. (2002). A racing algorithm for configuring metaheuristics. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2002) (pp. 11–18). San Francisco: Morgan Kaufmann

  • Bishop, C. (1995). Training with noise is equivalent to Tikhonov regularization. Neural Computation, 7(1), 108–116.

    Article  Google Scholar 

  • Bongard, J., Zykov, V., & Lipson, H. (2006). Resilient machines through continuous self-modeling. Science, 314(5802), 1118–1121.

    Article  Google Scholar 

  • Bongard, J. C. (2013). Evolutionary robotics. Communications of the ACM, 56(8), 74–83.

    Article  Google Scholar 

  • Brambilla, M., Pinciroli, C., Birattari, M., & Dorigo. M. (2012). Property-driven design for swarm robotics. In Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2012) (pp. 139–146). Richland, SC: IFAAMAS.

  • Brambilla, M., Ferrante, E., Birattari, M., & Dorigo, M. (2013). Swarm robotics: A review from the swarm engineering perspective. Swarm Intelligence, 7(1), 1–41.

    Article  Google Scholar 

  • Brooks, R. A. (1986). A robust layered control system for a mobile robot. IEEE Journal of Robotics and Automation, 2(1), 14–23.

    Article  Google Scholar 

  • Şahin, E. (2005). Swarm robotics: From sources of inspiration to domains of application. In Proceedings of the 2004 International Conference on Swarm Robotics, volume 3342 of LNCS, (pp. 10–20). Berlin, Germany: Springer.

  • Dietterich, T., & Kong, E. B. (1995). Machine learning bias, statistical bias, and statistical variance of decision tree algorithms. Technical report: Department of Computer Science, Oregon State University.

  • Dorigo, M., Birattari, M., & Brambilla, M. (2014). Swarm robotics. Scholarpedia, 9(1), 1463.

    Article  Google Scholar 

  • Duarte, M., Oliveira, S., & Christensen, A. L. (2012a). Automatic synthesis of controllers for real robots based on preprogrammed behaviors. In From animals to animats 12, volume 7426 of LNCS (pp. 249–258). Berlin, Germany: Springer.

  • Duarte, M., Oliveira, S., & Christensen, A. L. (2012b). Hierarchical evolution of robotic controllers for complex tasks. In 2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL) (pp. 1–6). Piscataway, NJ: IEEE Press.

  • Ferrante, E., Guzmán, E. D., Turgut, A. E., & Wenseleers, T. (2013). GESwarm: Grammatical evolution for the automatic synthesis of collective behaviors in swarm robotics. In Proceedings of the Fifteenth International Conference on Genetic and Evolutionary Computation Conference Companion (pp. 17–24). New York: ACM.

  • Floreano, D., & Keller, L. (2010). Evolution of adaptive behaviour in robots by means of Darwinian selection. Plos Biology, 8(1), e1000292.

    Article  Google Scholar 

  • Floreano, D., Husbands, P., & Nolfi, S. (2008). Evolutionary robotics. Springer handbook of robotics (pp. 1423–1451). Berlin, Germany: Springer.

    Chapter  Google Scholar 

  • Francesca, G., Brambilla, M., Trianni, V., Dorigo, M., & Birattari. M. (2012). Analysing an evolved robotic behaviour using a biological model of collegial decision making. In From animals to animats 12, volume 7426 of LNCS (pp. 381–390) Berlin, Germany: Springer.

  • Francesca, G., Brambilla, M., Brutschy, A., Trianni, V., & Birattari, M. (2013). AutoMoDe: A novel approach to the automatic design of control software for robot swarms. Supplementary information page at http://iridia.ulb.ac.be/supp/IridiaSupp2013-007/

  • Geman, S., Bienenstock, E., & Doursat, R. (1992). Neural networks and the bias/variance dilemma. Neural Computation, 4(1), 1–58.

    Article  Google Scholar 

  • Gutiérrez, Á., Campo, A., Dorigo, M., Donate, J., Monasterio-Huelin, F., & Magdalena, L. (2009). Open E-puck range & bearing miniaturized board for local communication in swarm robotics. In 2009 IEEE International Conference on Robotics and Automation (ICRA) (pp. 3111–3116). Piscataway, NJ: IEEE Press.

  • Hamann, H., & Wörn, H. (2008). A framework of space-time continuous models for algorithm design in swarm robotics. Swarm Intelligence, 2(2), 209–239.

    Article  Google Scholar 

  • Harvey, I., Husbands, P., Cliff, D., Thompson, A., & Jakobi, N. (1997). Evolutionary robotics: The Sussex approach. Robotics and Autonomous Systems, 20(2), 205–224.

    Article  Google Scholar 

  • Hauert, S., Zufferey, J.-C., & Floreano, D. (2008). Evolved swarming without positioning information: An application in aerial communication relay. Autonomous Robots, 26(1), 21–32.

    Article  Google Scholar 

  • Jakobi, N. (1997). Evolutionary robotics and the radical envelope-of-noise hypothesis. Adaptive Behavior, 6(2), 325–368.

    Article  Google Scholar 

  • Jakobi, N., Husbands, P., & Harvey, I. (1995). Noise and the reality gap: The use of simulation in evolutionary robotics. In Advances in Artificial Life (ECAL’95), volume 929 of LNCS (pp. 704–720) Berlin, Germany: Springer.

  • Kazadi, S., Lee, J. R., & Lee, J. (2009). Model independence in swarm robotics. International Journal of Intelligent Computing and Cybernetics, 2(4), 672–694.

    Article  MATH  MathSciNet  Google Scholar 

  • Koos, S., Mouret, J., & Doncieux, S. (2013). The transferability approach: Crossing the reality gap in evolutionary robotics. IEEE Transactions on Evolutionary Computation, 17(1), 122–145.

    Article  Google Scholar 

  • Liu, W., Winfield, A., Sa, J., Chen, J., & Dou, L. (2007). Strategies for energy optimisation in a swarm of foraging robots. Swarm Robotics, volume 4433 of LNCS (pp. 14–26). Berlin, Germany: Springer.

  • López-Ibáñez, M., Dubois-Lacoste, J., Stützle, T., & Birattari, M. (2011). The irace package, iterated race for automatic algorithm configuration. Technical report TR/IRIDIA/2011-004, IRIDIA, Université Libre de Bruxelles, Brussels, Belgium.

  • Maes, P. (1991). The agent network architecture (ANA). ACM SIGART Bulletin, 2(4), 115–120.

    Article  Google Scholar 

  • Marocco, D., & Nolfi, S. (2007). Emergence of communication in embodied agents evolved for the ability to solve a collective navigation problem. Connection Science, 19(1), 53–74.

    Article  Google Scholar 

  • Matarić, M. (1997a). Learning social behavior. Robotics and Autonomous Systems, 20(2–4), 191–204.

    Article  Google Scholar 

  • Matarić, M. (1997b). Reinforcement learning in the multi-robot domain. Autonomous Robots, 4(1), 73–83.

    Google Scholar 

  • Miglino, O., Lund, H. H., & Nolfi, S. (1995). Evolving mobile robots in simulated and real environments. Artificial Life, 2(4), 417–434.

    Google Scholar 

  • Mitri, S., Floreano, D., & Keller, L. (2011). Relatedness influences signal reliability in evolving robots. Proceedings of the Royal Society of London. Series B: Biological Sciences, 278(1704), 378–383.

    Article  Google Scholar 

  • Mondada, F., Bonani, M., Raemy, X., Pugh, J., Cianci, C., Klaptocz, A., Magnenat, S., Zufferey, J.-C., Floreano, D., & Martinoli, A. (2009a). The e-puck, a robot designed for education in engineering. In Proceedings of the 9th Conference on Autonomous Robot Systems and Competitions (pp. 59–65). Castelo Branco, Portugal: IPCB: Instituto Politécnico de Castelo Branco.

  • Mondada, F., Bonani, M., Raemy, X., Pugh, J., Cianci, C., Klaptocz, A., Magnenat, S., Zufferey, J.-C., Floreano, D., & Martinoli, A. (2009b). E-puck website. URL http://www.e-puck.org/. Accessed Nov 2013.

  • Nolfi, S. (2002). Power and the limits of reactive agents. Neurocomputing, 42(1), 119–145.

    Article  MATH  Google Scholar 

  • Nolfi, S., & Floreano, D. (2000). Evolutionary robotics: The biology, intelligence, and technology of self-organizing machines. Cambridge, MA: MIT Press.

  • Panait, L., & Luke, S. (2005). Cooperative multi-agent learning: The state of the art. Autonomous Agents and Multi-Agent Systems, 11(3), 387–434.

    Article  Google Scholar 

  • Parker, L. E. (1996). L-ALLIANCE: Task-oriented multi-robot learning in behavior-based systems. Advanced Robotics, 11(4), 305–322.

    Article  Google Scholar 

  • Pinciroli, C., Trianni, V., O’Grady, R., Pini, G., Brutschy, A., Brambilla, M., et al. (2012). ARGoS: A modular, parallel, multi-engine simulator for multi-robot systems. Swarm Intelligence, 6(4), 271–295.

    Article  Google Scholar 

  • Pinville, T., Koos, S., Mouret, J.-B., & Doncieux, S. (2011). How to promote generalisation in evolutionary robotics: The ProGAb approach. In Proceedings of the 13th Annual Conference on Genetic and Evolutionary Computation (pp. 259–266). New York: ACM.

  • R Development Core Team. (2008). R: A language and environment for statistical computing. Vienna, Austria: R Foundation for Statistical Computing. URL http://www.R-project.org.

  • Riano, L., & McGinnity, T. M. (2012). Automatically composing and parameterizing skills by evolving finite state automata. Robotics and Autonomous Systems, 60(4), 639–650.

    Article  Google Scholar 

  • Stranieri, A., Turgut, A., Francesca, G., Reina, A., Dorigo, M., & Birattari, M. (2013). IRIDIA’s arena tracking system. Technical report TR/IRIDIA/2013-013, IRIDIA, Université Libre de Bruxelles, Brussels, Belgium.

  • Trianni, V., & Dorigo, M. (2006). Self-organisation and communication in groups of simulated and physical robots. Biological Cybernetics, 95(3), 213–231.

    Article  MATH  Google Scholar 

  • Trianni, V., & Nolfi, S. (2009). Self-organising sync in a robotic swarm. A dynamical system view. IEEE Transactions on Evolutionary Computation, 13(4), 722–741.

    Article  Google Scholar 

  • Trianni, V., & Nolfi, S. (2011). Engineering the evolution of self-organizing behaviors in swarm robotics: A case study. Artificial Life, 17(3), 183–202.

    Article  Google Scholar 

  • Tuci, E. (2009). An investigation of the evolutionary origin of reciprocal communication using simulated autonomous agents. Biological Cybernetics, 101(3), 183–199.

    Article  Google Scholar 

  • Urzelai, J., Floreano, D., Dorigo, M., & Colombetti, M. (1998). Incremental robot shaping. Connection Science, 10(3–4), 341–360.

    Article  Google Scholar 

  • Waibel, M., Keller, L., & Floreano, D. (2009). Genetic team composition and level of selection in the evolution of cooperation. IEEE Transactions on Evolutionary Computation, 13(3), 648–660.

    Article  Google Scholar 

  • Winfield, A. F. T., & Erbas, M. D. (2011). On embodied memetic evolution and the emergence of behavioural traditions in robots. Memetic Computing, 3(4), 261–270.

    Article  Google Scholar 

  • Wischmann, S., Floreano, D., & Keller, L. (2012). Historical contingency affects signaling strategies and competitive abilities in evolving populations of simulated robots. Proceedings of the National Academy of Sciences, 109(3), 864–868.

    Article  Google Scholar 

Download references

Acknowledgments

The research leading to the results presented in this paper has received funding from the European Research Council under the European Union’s Seventh Framework Programme (FP7/2007-2013) / ERC grant agreement no. 246939. G. Francesca acknowledges support by the META-X project, an Action de Recherche Concertée funded by the Scientific Research Directorate of the French Community of Belgium. M. Brambilla, A. Brutschy, and M. Birattari acknowledge support from the Belgian F.R.S.-FNRS. Vito Trianni acknowledges support by the Italian National Research Council (CNR) within the EUROCORES Programme EuroBioSAS of the European Science Foundation. The authors thank the anonymous reviewers for their useful comments.

Author information

Authors and Affiliations

  1. IRIDIA, Université Libre de Bruxelles, Brussels, Belgium

    Gianpiero Francesca, Manuele Brambilla, Arne Brutschy & Mauro Birattari

  2. ISTC-CNR, Rome, Italy

    Vito Trianni

Authors
  1. Gianpiero Francesca
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Manuele Brambilla
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Arne Brutschy
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Vito Trianni
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Mauro Birattari
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Gianpiero Francesca or Mauro Birattari.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Francesca, G., Brambilla, M., Brutschy, A. et al. AutoMoDe: A novel approach to the automatic design of control software for robot swarms. Swarm Intell 8, 89–112 (2014). https://doi.org/10.1007/s11721-014-0092-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11721-014-0092-4

Keywords

Search

Navigation