Skip to main content
SpringerLink
Log in

A Case Study on the Scalability of Online Evolution of Robotic Controllers

  • Conference paper
  • First Online:
Progress in Artificial Intelligence (EPIA 2015)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 9273))

Included in the following conference series:

Abstract

Online evolution of controllers on real robots typically requires a prohibitively long evolution time. One potential solution is to distribute the evolutionary algorithm across a group of robots and evolve controllers in parallel. No systematic study on the scalability properties and dynamics of such algorithms with respect to the group size has, however, been conducted to date. In this paper, we present a case study on the scalability of online evolution. The algorithm used is odNEAT, which evolves artificial neural network controllers. We assess the scalability properties of odNEAT in four tasks with varying numbers of simulated e-puck-like robots. We show how online evolution algorithms can enable groups of different size to leverage their multiplicity, and how larger groups can: (i) achieve superior task performance, and (ii) enable a significant reduction in the evolution time and in the number of evaluations required to evolve controllers that solve the task.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Floreano, D., Mondada, F.: Automatic creation of an autonomous agent: Genetic evolution of a neural-network driven robot. In: 3rd International Conference on Simulation of Adaptive Behavior, pp. 421–430. MIT Press, Cambridge (1994)

    Google Scholar 

  2. Matarić, M., Cliff, D.: Challenges in evolving controllers for physical robots. Robotics and Autonomous Systems 19(1), 67–83 (1996)

    Article  Google Scholar 

  3. Watson, R.A., Ficici, S.G., Pollack, J.B.: Embodied evolution: Distributing an evolutionary algorithm in a population of robots. Robotics and Autonomous Systems 39(1), 1–18 (2002)

    Article  Google Scholar 

  4. Bianco, R., Nolfi, S.: Toward open-ended evolutionary robotics: evolving elementary robotic units able to self-assemble and self-reproduce. Connection Science 16(4), 227–248 (2004)

    Article  Google Scholar 

  5. Bredeche, N., Montanier, J., Liu, W., Winfield, A.: Environment-driven distributed evolutionary adaptation in a population of autonomous robotic agents. Mathematical and Computer Modelling of Dynamical Systems 18(1), 101–129 (2012)

    Article  MATH  Google Scholar 

  6. 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 the Simulation and Synthesis of Living Systems, pp. 251–258. MIT Press, Cambridge (2012)

    Google Scholar 

  7. De Jong, K.A.: Evolutionary computation: a unified approach. MIT Press, Cambridge (2006)

    Google Scholar 

  8. Silva, F., Duarte, M., Oliveira, S.M., Correia, L., Christensen, A.L.: The case for engineering the evolution of robot controllers. In: 14th International Conference on the Synthesis and Simulation of Living Systems, pp. 703–710. MIT Press, Cambridge (2014)

    Google Scholar 

  9. Silva, F., Urbano, P., Correia, L., Christensen, A.L.: odNEAT: An algorithm for decentralised online evolution of robotic controllers. Evolutionary Computation (2015) (in press). http://www.mitpressjournals.org/doi/pdf/10.1162/EVCO_a_00141

  10. Silva, F., Correia, L., Christensen, A.L.: Speeding Up online evolution of roboticcontrollers with macro-neurons. In: Esparcia-Alcázar, A.I., Mora, A.M. (eds.) EvoApplications 2014. LNCS, vol. 8602, pp. 765–776. Springer, Heidelberg (2014)

    Google Scholar 

  11. Silva, F., Urbano, P., Christensen, A.L.: Online evolution of adaptive robot behaviour. International Journal of Natural Computing Research 4(2), 59–77 (2014)

    Article  Google Scholar 

  12. 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, pp. 59–65, IPCB, Castelo Branco (2009)

    Google Scholar 

  13. Duarte, M., Silva, F., Rodrigues, T., Oliveira, S.M., Christensen, A.L.: JBotEvolver: A versatile simulation platform for evolutionary robotics. In: 14th International Conference on the Synthesis and Simulation of Living Systems, pp. 210–211. MIT Press, Cambridge (2014)

    Google Scholar 

  14. Groß, R., Dorigo, M.: Towards group transport by swarms of robots. International Journal of Bio-Inspired Computation 1(1–2), 1–13 (2009)

    Article  Google Scholar 

  15. Cao, Y., Fukunaga, A., Kahng, A.: Cooperative mobile robotics: Antecedents and directions. Autonomous Robots 4(1), 1–23 (1997)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. BioMachines Lab, Lisboa, Portugal

    Fernando Silva & Anders Lyhne Christensen

  2. Instituto de Telecomunicações, Lisboa, Portugal

    Fernando Silva & Anders Lyhne Christensen

  3. Instituto Universitário de Lisboa (ISCTE-IUL), Lisboa, Portugal

    Anders Lyhne Christensen

  4. BioISI, Faculdade de Ciências, Universidade de Lisboa, Lisboa, Portugal

    Fernando Silva & Luís Correia

Authors
  1. Fernando Silva
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Luís Correia
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Anders Lyhne Christensen
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Fernando Silva .

Editor information

Editors and Affiliations

  1. ISEC - Coimbra Institute of Engineering, Polytechnic Institute of Coimbra, Coimbra, Portugal

    Francisco Pereira

  2. CIUSC, Department of Informatics Engineering, University of Coimbra, Coimbra, Portugal

    Penousal Machado

  3. CIUSC, Department of Informatics Engineering, University of Coimbra, Coimbra, Portugal

    Ernesto Costa

  4. CIUSC, Department of Informatics Engineering, University of Coimbra, Coimbra, Portugal

    Amílcar Cardoso

Rights and permissions

Reprints and permissions

Copyright information

© 2015 Springer International Publishing Switzerland

About this paper

Cite this paper

Silva, F., Correia, L., Christensen, A.L. (2015). A Case Study on the Scalability of Online Evolution of Robotic Controllers. In: Pereira, F., Machado, P., Costa, E., Cardoso, A. (eds) Progress in Artificial Intelligence. EPIA 2015. Lecture Notes in Computer Science(), vol 9273. Springer, Cham. https://doi.org/10.1007/978-3-319-23485-4_20

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-23485-4_20

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-23484-7

  • Online ISBN: 978-3-319-23485-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation