Skip to main content
SpringerLink
Log in

Evolving Monolithic Robot Controllers through Incremental Shaping

  • Conference paper
New Horizons in Evolutionary Robotics

Part of the book series: Studies in Computational Intelligence ((SCI,volume 341))

Abstract

Evolutionary robotics has been shown to be an effective technique for generating robot behaviors that are difficult to derive analytically from the robot’s mechanics and task environment. Moreover, augmenting evolutionary algorithms with environmental scaffolding via an incremental shaping method makes it possible to evolve controllers for complex tasks that would otherwise be infeasible. In this paper we present a summary of two recent publications in the evolutionary robotics literature demonstrating how these methods can be used to evolve robot controllers for non-trivial tasks, what the obstacles are in evolving controllers in this way, and present a novel research question that can be investigated under this framework.

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 129.00
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 169.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 169.99
Price excludes VAT (USA)
  • Durable hardcover 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. Anderson, M.: Embodied Cognition: A field guide. Artificial Intelligence 149(1), 91–130 (2003)

    Article  Google Scholar 

  2. Auerbach, J., Bongard, J.C.: Evolution of functional specialization in a morphologically homogeneous robot. In: Proceedings of the Genetic and Evolutionary Computation Conference, GECCO (2009)

    Google Scholar 

  3. Auerbach, J., Bongard, J.C.: How robot morphology and training order affect the learning of multiple behaviors. In: Proceedings of the IEEE Congress on Evolutionary Computation, CEC (2009)

    Google Scholar 

  4. Beer, R.: The Dynamics of Active Categorical Perception in an Evolved Model Agent. Adaptive Behavior 11(4), 209 (2003)

    Article  Google Scholar 

  5. Beer, R.D.: Parameter space structure of continuous-time recurrent neural networks. Neural Comp. 18(12), 3009–3051 (2006)

    Article  MATH  MathSciNet  Google Scholar 

  6. Beer, R.D.: The dynamics of brain-body-environment systems: A status report. In: Calvo, P., Gomila, A. (eds.) Handbook of Cognitive Science: An Embodied Approach, pp. 99–120. Elsevier, Amsterdam (2008)

    Chapter  Google Scholar 

  7. Bongard, J.: Behavior chaining: incremental behavioral integration for evolutionary robotics. In: Bullock, S., Noble, J., Watson, R., Bedau, M.A. (eds.) Artificial Life XI: Proceedings of the Eleventh International Conference on the Simulation and Synthesis of Living Systems, pp. 64–71. MIT Press, Cambridge (2008)

    Google Scholar 

  8. Brooks, R.: A robust layered control system for a mobile robot. IEEE Journal of Robotics and Automation, [legacy, pre - 1988] 2(1), 14–23 (1986), http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1087032

    Article  Google Scholar 

  9. Brooks, R.: Cambrian intelligence. MIT Press, Cambridge (1999)

    MATH  Google Scholar 

  10. Calabretta, R., Nolfi, S., Parisi, D., Wagner, G.P.: Duplication of modules facilitates the evolution of functional specialization. Artificial Life 6(1), 69–84 (2000)

    Article  Google Scholar 

  11. Dorigo, M., Colombetti, M.: Robot shaping: Developing situated agents through learning. Artificial Intelligence 70(2), 321–370 (1994)

    Article  Google Scholar 

  12. Harvey, I., Husbands, P., Cliff, D., Thompson, A., Jakobi, N.: Evolutionary robotics: the sussex approach. Robotics and Autonomous Systems 20, 205–224 (1997)

    Article  Google Scholar 

  13. Hornby, G., Takamura, S., Yamamoto, T., Fujita, M.: Autonomous evolution of dynamic gaits with two quadruped robots. IEEE Transactions on Robotics 21(3), 402–410 (2005), doi:10.1109/TRO.2004.839222

    Article  Google Scholar 

  14. Izquierdo, E., Buhrmann, T.: Analysis of a dynamical recurrent neural network evolved for two qualitatively different tasks: walking and chemotaxis. In: Bullock, S., Noble, J., Watson, R., Bedau, M.A. (eds.) Artificial Life XI: Proceedings of the Eleventh International Conference on the Simulation and Synthesis of Living Systems, pp. 257–264. MIT Press, Cambridge (2008)

    Google Scholar 

  15. Noë, A.: Action in Perception. MIT Press, Cambridge (2004)

    Google Scholar 

  16. Nolfi, S., Floreano, D.: Evolutionary Robotics: The Biology,Intelligence,and Technology. MIT Press, Cambridge (2000)

    Google Scholar 

  17. Pfeifer, R., Bongard, J.: How the Body Shapes the Way We Think: A New View of Intelligence. MIT Press, Cambridge (2006)

    Google Scholar 

  18. Reil, T., Husbands, P.: Evolution of central pattern generators for bipedal walking in a real-time physics environment. IEEE Transactions on Evolutionary Computation 6(2), 159–168 (2002), doi:10.1109/4235.996015

    Article  Google Scholar 

  19. Saksida, L., Raymond, S., Touretzky, D.S.: Shaping robot behavior using principles from instrumental conditioning. Robotics and Autonomous Systems 22, 231–249 (1997)

    Article  Google Scholar 

  20. Singh, S.P.: Transfer of learning across sequential tasks. Machine Learning 8, 323–339 (1992)

    MATH  Google Scholar 

  21. Wood, D., Bruner, J., Ross, G.: The role of tutoring in problem solving. J. Child Psychol. Psychiatry 17(2), 89–100 (1976)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Morphology, Evolution and Cognition Laboratory, Department of Computer Science, University of Vermont, Burlington, VT, 05405, USA

    Joshua E. Auerbach & Josh C. Bongard

Authors
  1. Joshua E. Auerbach
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Josh C. Bongard
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. CNRS UMR 7222, ISIR - Pierre and Marie Curie University, 4, place Jussieu cedex 05, Boite courrier 173, 75252, Paris, France

    Stéphane Doncieux

  2. Université Paris-Sud, TAO - Univ. Paris-Sud, INRIASaclay, CNRS, LRI, Bat. 490, F-91405, Orsay, France

    Nicolas Bredèche

  3. CNRS UMR 7222, ISIR - Pierre andMarie Curie University, 4, place Jussieu cedex 05, Boite courrier 173, 75252, Paris, France

    Jean-Baptiste Mouret

Rights and permissions

Reprints and permissions

Copyright information

© 2011 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Auerbach, J.E., Bongard, J.C. (2011). Evolving Monolithic Robot Controllers through Incremental Shaping. In: Doncieux, S., Bredèche, N., Mouret, JB. (eds) New Horizons in Evolutionary Robotics. Studies in Computational Intelligence, vol 341. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-18272-3_5

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-18272-3_5

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-18271-6

  • Online ISBN: 978-3-642-18272-3

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics

Search

Navigation