Skip to main content
SpringerLink
Log in

Simultaneous versus incremental learning of multiple skills by modular robots

  • Special Issue
  • Published:
Evolutionary Intelligence Aims and scope Submit manuscript

Abstract

This paper is concerned with the problem of learning multiple skills by modular robots. The main question we address is whether it is better to learn multiple skills simultaneously (all-at-once) or incrementally (one-by-one). We conduct an experimental study with modular robots of various morphologies that need to acquire three different but correlated skills, efficient locomotion, navigation towards a target point, and obstacle avoidance, using a real-time, on-board evolution as the learning method. The results indicate that the one-by-one strategy is more efficient and more stable than the all-at-once strategy.

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
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

Notes

  1. Webots system by Cyberbotics, www.cyberbotics.com.

  2. Early work on such learning strategy for the problem at hand has shown that an individual mutation rate for each gene does not provide an advantage, w.r.t having a common mutation rate for all genes, see [28].

  3. Recall that the Infancy stage is part of a cycle—the Triangle of Life—where individuals mate sto generate new offspring.

References

  1. Auerbach JE, Bongard JC (2009) How robot morphology and training order affect the learning of multiple behaviors. In: Proceedings of the IEEE congress on evolutionary computation (CEC’2009). IEEE Press, pp 39–46

  2. Auerbach JE, Bongard JC (2012) On the relationship between environmental and mechanical complexity in evolved robots. In: Adami C, Bryson D, Ofria C, Pennock R (eds) Proceedings of artificial life, vol 13. MIT Press, pp 309–316

  3. Bongard J (2011) Morphological and environmental scaffolding synergize when evolving robot controllers. In: Krasnogor N (ed) Proceedings of the 13th genetic and evolutionary computation conference (GECCO-2011). ACM, pp 179–186

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

    Article  Google Scholar 

  5. Bongard JC (2008) Behavior chaining: incremental behavior integration for evolutionary robotics. In: Bullock S, Noble J, Watson R, Bedau M (eds) Proceedings of artificial life XI. MIT Press, pp 64–71

  6. Chavas J, Corne C, Horvai P, Kodjabachian J, Meyer J.-A (1998) Incremental evolution of neural controllers for robust obstacle-avoidance in Khepera. In: Husbands P, Meyer J.-A (eds) Proceedings of the 1st European workshop on Evolutionary Robotics-EvoRobot98. Springer, Berlin, pp 227–247

  7. Christensen DJ, Larsen JC, Støy K (2013) Fault-tolerant gait learning and morphology optimization of a polymorphic walking robot. Evol Syst (to appear). doi:10.1007/s12530-013-9088-3

  8. Christensen DJ, Schultz UP, Støy K (2013) A distributed and morphology-independent strategy for adaptive locomotion in self-reconfigurable modular robots. Robotics Auton Syst 61(9):1021–1035

    Article  Google Scholar 

  9. Clune J, Beckmann BE, Ofria C, Pennock RT (2009) Evolving coordinated quadruped gaits with the HyperNEAT generative encoding. In: IEEE congress on evolutionary computation (CEC) 2009. IEEE Press, pp 2764–2771

  10. Colorado J, Barrientos A, Rossi C, Garzón M, Galán M, del Cerro J (2010) Efficient locomotion on non-wheeled snake-like robots. In: Filipe J, Andrade-Cetto J, Ferrier JL (eds) ICINCO (2). INSTICC Press, pp 246–251

  11. D’Angelo M, Weel B, Eiben A (2013) Online gait learning for modular robots with arbitrary shapes and sizes. In: Dediu AH, Martín-Vide C, Truthe B, Vega-Rodríguez MA (eds) Second international conference on the theory and practice of natural computing (TPNC 2013), no. 8273 in LNCS. Springer, Berlin, pp 45–56

  12. Dorigo M, Colombetti M (1994) Robot shaping: developing autonomous agents through learning. Artif Intell 2:321–370

    Article  Google Scholar 

  13. Eiben AE, Bredeche N, Hoogendoorn M, Stradner J, Timmis J, Tyrrell A, Winfield A (2013) The triangle of life: evolving robots in real-time and real-space. In: Lió P, Miglino O, Nicosia G, Nolfi S, Pavone M (eds) Advances in artificial life, (ECAL) 2013. MIT Press, pp 1056–1063

  14. Eiben AE, Kernbach S, Haasdijk E (2012) Embodied artificial evolution. Evol Intell 5(4):261–272

    Article  Google Scholar 

  15. Filliat D, Kodjabachian J, Meyer JA (1999) Evolution of neural controllers for locomotion and obstacle-avoidance in a 6-legged robot. Connect Sci 11(3–4):223–240

    Google Scholar 

  16. Haasdijk E, Rusu AA, Eiben AE (2010) HyperNEAT for locomotion control in modular robots. In: Hornby GS, Sekanina L, Haddow PC (eds) Evolvable systems: from biology to hardware, lecture notes in computer science, vol 5216. Springer, Berlin, pp 169–180

  17. Hamann H, Stradner J, Schmickl T, Crailsheim K (2010) A hormone-based controller for evolutionary multi-modular robotics: from single modules to gait learning. In: IEEE congress on evolutionary computation (CEC) 2010. IEEE Press, pp 1–8

  18. Ijspeert AJ (2008) Central pattern generators for locomotion control in animals and robots: a review. Neural Netw 21(4):642–653

    Article  Google Scholar 

  19. Kamimura A, Kurokawa H, Yoshida E, Murata S, Tomita K, Kokaji S (2005) Automatic locomotion design and experiments for a modular robotic system. IEEE/ASME Trans Mechatron 10(3):314–325

    Article  Google Scholar 

  20. Kamimura A, Kurokawa H, Yoshida E, Tomita K, Kokaji S, Murata S (2004) Distributed adaptive locomotion by a modular robotic system, M-TRAN II. In: Proceedings of 2004 IEEE/RSJ international conference on intelligent robots and systems (IROS) 2004, vol 3. IEEE Press, pp 2370–2377

  21. Lessin D, Fussel D, Miikkulainen R (2013) Open-ended behavioral complexity for evolved virtual creatures. In: Proceedings of the fifteenth annual conference on genetic and evolutionary computation conference (GECCO-2013). ACM, pp 335–342

  22. Pfeifer R, Bongard JC (2007) How the body shapes the way we think. A new view of intelligence. MIT Press, Cambridge

    Google Scholar 

  23. Shen H, Yosinski J, Kormushev P, Caldwell DG, Lipson H (2012) Learning fast quadruped robot gaits with the RL PoWER spline parameterization. Cybern Inf Technol 12(3):66–75

    Google Scholar 

  24. Shen WM, Salemi B, Will P (2000) Hormones for self-reconfigurable robots. In: Pagello E, Groen F, Arai T, Dillman R, Stentz A (eds) Proceedings of the 6th international conference on intelligent autonomous systems (IAS-6). IOS Press, pp 918–925

  25. Spröwitz A, Moeckel R, Maye J, Ijspeert AJ (2008) Learning to move in modular robots using central pattern generators and online optimization. Int J Robot Res 27(3–4):423–443

    Article  Google Scholar 

  26. Stone P (2000) Layered learning in multiagent systems: a winning approach to robotic soccer. MIT Press, Cambridge

    Google Scholar 

  27. Suarez DM, Rossi C (2014) Evolutionary learning of basic functionalities for snake-like robots. In: Armada MA, Sanfeliu A, Ferre M (eds) ROBOT2013: first iberian robotics conference, advances in intelligent systems and computing, vol 252. Springer, Berlin, pp 391–406

  28. Suarez DPM, Rossi C (2013) A comparison between different encoding strategies for snake-like robot controllers. In: Proceedings of the EvoStar 2013, lecture notes in computer science 7835, pp 560–568

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

    Article  Google Scholar 

  30. Yim M (1993) A reconfigurable modular robot with many modes of locomotion. In: Proceedings of international conference on advanced mechatronics. Japan Society of Mechanical Engineers, Tokio, Japan, pp 283–288

  31. Yosinski J, Clune J, Hidalgo D, Nguyen S, Zagal J, Lipson H (2011) Evolving robot gaits in hardware: the HyperNEAT generative encoding vs. parameter optimization. In: Lenaerts T, Giacobini M, Bersini H, Bourgine P, Dorigo M, Doursat R (eds) Advances in artificial life (ECAL) 2011. MIT Press, pp 890–897

Download references

Author information

Authors and Affiliations

  1. Centre for Automation and Robotics UPM-CSIC, Madrid, Spain

    C. Rossi

  2. VU University Amsterdam, Amsterdam, The Netherlands

    A. E. Eiben

Authors
  1. C. Rossi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. A. E. Eiben
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to C. Rossi.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (m4v 4672 KB)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Rossi, C., Eiben, A.E. Simultaneous versus incremental learning of multiple skills by modular robots. Evol. Intel. 7, 119–131 (2014). https://doi.org/10.1007/s12065-014-0109-3

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12065-014-0109-3

Keywords

Search

Navigation