Skip to main content
Springer Nature Link
Log in

Revisiting the Use of Noise in Evolutionary Robotics

  • Conference paper
  • First Online:
Artificial Intelligence Research (SACAIR 2021)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 1551))

Included in the following conference series:

  • 990 Accesses

Abstract

The injection of noise into simulator predictions during controller evolution in Evolutionary Robotics (ER) has long been used as a method of counteracting the reality gap problem. This study endeavoured to design and conduct experiments to quantify the impact of different levels of such noise on two different factors that are believed to contribute to the reality gap: inconsistencies in real-world robotic behaviour and inaccuracies in the simulator used in ER. These experiments were conducted on a robot performing a maze-navigation task. The results obtained in this study showed that, as was anticipated, noise injection during controller evolution does have an appreciable positive impact on the transferability of evolved controllers to the real robot. Various additional trends were observed, however, such as the limited capability of noise to aid in transferability under certain conditions. Additionally, the results of this study illustrated that different contributors to the reality gap may be optimally counteracted using different levels of noise. The results thus emphasized the importance of noise injection and of selecting optimal noise levels during the ER process.

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

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Pratihar, D.K.: Evolutionary Robotics - A Review. Sadhana 28(6), 999–1009 (2003)

    Google Scholar 

  2. Engelbrecht, A.P.: Computational Intelligence: An Introduction, 2nd edn. Wiley, West Sussex (2007)

    Book  Google Scholar 

  3. Doncieux, S., Bredeche, N., Mouret, J., Eiben, A.E.G.: Evolutionary robotics: what, why, and where to. Front. Robot. AI 2, 4 (2015)

    Article  Google Scholar 

  4. Nelson, A.L., Barlow, G.J., Doitsidis, L.: Fitness functions in evolutionary robotics: a survey and analysis. Robot. Autonom. Syst. 57(4), 345–370 (2009)

    Article  Google Scholar 

  5. Koos, S., Mouret, J., Doncieux, S.: The transferability approach: crossing the reality gap in evolutionary robotics. IEEE Trans. Evol. Comput. 17(1), 122–145 (2012)

    Article  Google Scholar 

  6. Farooq, S.S., Kim, K.J.: Evolution of neural controllers for simulated and real quadruped robots. In: IEEE International Conference on Robot, Vision and Signal Processing, pp. 295–298 (2013)

    Google Scholar 

  7. Belter, D., Skrzypczyński, P.: A biologically inspired approach to feasible gait learning for a hexapod robot. Int. J. Appl. Math. Comput. Sci. 20(1), 69–84 (2010)

    Article  Google Scholar 

  8. Glette, K., Klaus, G., Zagal, J.C., Torresen, J.: Evolution of locomotion in a simulated quadruped robot and transferral to reality. In: International Symposium on Artificial Life and Robotics (2012)

    Google Scholar 

  9. Jakobi, N.: Running across the reality gap: octopod locomotion evolved in a minimal simulation. In: Evolutionary Robotics, pp. 39–58 (1998)

    Google Scholar 

  10. Jakobi, N., Husbands, P., Harvey, I.: Noise and the reality gap: the use of simulation in evolutionary robotics. In: Morán, F., Moreno, A., Merelo, J.J., Chacón, P. (eds.) ECAL 1995. LNCS, vol. 929, pp. 704–720. Springer, Heidelberg (1995). https://doi.org/10.1007/3-540-59496-5_337

    Chapter  Google Scholar 

  11. Mouret, J., Chatzilygeroudis, K.: 20 years of reality gap: a few thoughts about simulators in evolutionary robotics. In: Genetic and Evolutionary Computation Conference Companion, pp. 1121–1124 (2017)

    Google Scholar 

  12. Zagal, J.C., Ruiz-del Solar, J.: Combining simulation and reality in Evolutionary Robotics. J. Intell. Robot. Syst. 50, 19–39 (2007)

    Article  Google Scholar 

  13. Bongard, J.C.: Evolutionary robotics. Commun. ACM 56(8), 74–83 (2013). https://doi.org/10.1145/2493883

    Article  Google Scholar 

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

    Article  Google Scholar 

  15. Seth, A.K.: Noise and the pursuit of complexity: a study in evolutionary robotics. In: Husbands, P., Meyer, J.-A. (eds.) EvoRobots 1998. LNCS, vol. 1468, pp. 123–136. Springer, Heidelberg (1998). https://doi.org/10.1007/3-540-64957-3_68

    Chapter  Google Scholar 

  16. Holland, J., Gallagher, C., Griffith, J., O’Riordan, C.: Identifying the reality gap between abstract and realistic models using evolved agents and simulated kilobots. In: 2018 IEEE International Conference on Robotics and Biomimetics (ROBIO), pp. 224–230. IEEE (2018)

    Google Scholar 

  17. Pretorius, C.J., du Plessis, M.C., Gonsalves, J.W.: A comparison of neural networks and physics models as motion simulators for simple robotic evolution. In: Evolutionary Computation (CEC), 2014 IEEE Congress on, pp. 2793–2800. IEEE (2014)

    Google Scholar 

  18. Woodford, G.W., Pretorius, C.J., du Plessis, M.C.: Concurrent controller and simulator neural network development for a differentially-steered robot in evolutionary robotics. Robot. Autonom. Syst. 76, 80–92 (2016)

    Article  Google Scholar 

  19. Jakobi, N.: Half-baked, ad-hoc and noisy: minimal simulations for evolutionary robotics. In: Fourth European Conference on Artificial Life, vol. 4, p. 348. MIT press (1997)

    Google Scholar 

  20. Phillips, A.P., du Plessis, M.C.: Towards the incorporation of proprioception in evolutionary robotics controllers. In: International Conference on Robotic Computing, IEEE (2019)

    Google Scholar 

  21. Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural comput. 9(8), 1735–1780 (1997)

    Article  Google Scholar 

  22. Gers, F.A., Schmidhuber, J.: Recurrent nets that time and count. In: Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium, vol. 3, pp. 189–194. IEEE (2000)

    Google Scholar 

  23. Phillips, A.P., du Plessis, M.C.: Evolutionary robotics controllers with proprioception facilitated by neural network based simulators. In: Unpublished (2020)

    Google Scholar 

  24. Leonard, B.A., du Plessis, M.C., Woodford, G.W.: Bootstrapped neuro-simulation as a method of concurrent neuro-evolution and damage recovery. Robot. Autonom. Syst. 124, 103398 (2020). https://doi.org/10.1016/j.robot.2019.103398

  25. Jakobi, N.: Evolutionary robotics and the radical envelope-of-noise hypothesis. Adapt. Behav. 6(2), 325–368 (1997)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Nelson Mandela University, Gqeberha, South Africa

    Mathys C. du Plessis, Antin P. Phillips & Christiaan J. Pretorius

Authors
  1. Mathys C. du Plessis
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Antin P. Phillips
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Christiaan J. Pretorius
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mathys C. du Plessis .

Editor information

Editors and Affiliations

  1. University of KwaZulu-Natal, Durban, South Africa

    Edgar Jembere

  2. University of Pretoria, Pretoria, South Africa

    Aurona J. Gerber

  3. University of KwaZulu-Natal, Durban, South Africa

    Serestina Viriri

  4. University of KwaZulu-Natal, Durban, South Africa

    Anban Pillay

Rights and permissions

Reprints and permissions

Copyright information

© 2022 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

du Plessis, M.C., Phillips, A.P., Pretorius, C.J. (2022). Revisiting the Use of Noise in Evolutionary Robotics. In: Jembere, E., Gerber, A.J., Viriri, S., Pillay, A. (eds) Artificial Intelligence Research. SACAIR 2021. Communications in Computer and Information Science, vol 1551. Springer, Cham. https://doi.org/10.1007/978-3-030-95070-5_14

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-95070-5_14

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-95069-9

  • Online ISBN: 978-3-030-95070-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics