Advertisement

Noise and the reality gap: The use of simulation in evolutionary robotics

  • Nick Jakobi
  • Phil Husbands
  • Inman Harvey
5. Robotics and Emulation of Animal Behavior
Part of the Lecture Notes in Computer Science book series (LNCS, volume 929)

Abstract

The pitfalls of naive robot simulations have been recognised for areas such as evolutionary robotics. It has been suggested that carefully validated simulations with a proper treatment of noise may overcome these problems. This paper reports the results of experiments intended to test some of these claims. A simulation was constructed of a two-wheeled Khepera robot with IR and ambient light sensors. This included detailed mathematical models of the robot-environment interaction dynamics with empirically determined parameters. Artificial evolution was used to develop recurrent dynamical network controllers for the simulated robot, for obstacle-avoidance and light-seeking tasks, using different levels of noise in the simulation. The evolved controllers were down-loaded onto the real robot and the correspondence between behaviour in simulation and in reality was tested. The level of correspondence varied according to how much noise was used in the simulation, with very good results achieved when realistic quantities were applied. It has been demonstrated that it is possible to develop successful robot controllers in simulation that generate almost identical behaviours in reality, at least for a particular class of robot-environment interaction dynamics.

Keywords

Evolutionary Robotics Noise High Fidelity Simulations Artificial Evolution 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    R.A. Brooks. Intelligence without reason. In Proceedings IJCAI-91, pages 569–595. Morgan Kaufmann, 1991.Google Scholar
  2. 2.
    R.A. Brooks. Intelligence without representation. Artificial Intelligence, 47:139–159, 1991.Google Scholar
  3. 3.
    Rodney A. Brooks. Artificial life and real robots. In F. J. Varela and P. Bourgine, editors, Proceedings of the First European Conference on Artificial Life, pages 3–10. MIT Press/Bradford Books, Cambridge, MA, 1992.Google Scholar
  4. 4.
    R. Collins and D. Jefferson. Selection in massively parallel genetic algorithms. In R. K. Belew and L. B. Booker, editors, Proceedings of the Fourth Intl. Conf. on Genetic Algorithms, ICGA-91, pages 249–256. Morgan Kaufmann, 1991.Google Scholar
  5. 5.
    D. Floreano and F. Mondada. Automatic creation of an autonomous agent: Genetic evolution of a neural-network driven robot. In D. Cliff, P. Husbands, J.-A. Meyer, and S. Wilson, editors, From Animals to Animats 3, Proc. of 3rd Intl. Conf. on Simulation of Adaptive Behavior, SAB'94. MIT Press/Bradford Books, 1994.Google Scholar
  6. 6.
    A.S. Glasner, editor. An Introduction To Ray Tracing. Academic Press, London, 1989.Google Scholar
  7. 7.
    I. Harvey, P. Husbands, and D. Cliff. Seeing the light: Artificial evolution, real vision. In D. Cliff, P. Husbands, J.-A. Meyer, and S. Wilson, editors, From Animals to Animats 3, Proc. of 3rd Intl. Conf. on Simulation of Adaptive Behavior, SAB'94, pages 392–401. MIT Press/Bradford Books, 1994.Google Scholar
  8. 8.
    P. Husbands and I. Harvey. Evolution versus design: Controlling autonomous robots. In Integrating Perception, Planning and Action, Proceedings of 3rd Annual Conference on Artificial Intelligence, Simulation and Planning, pages 139–146. IEEE Press, 1992.Google Scholar
  9. 9.
    P. Husbands, I. Harvey, and D. Cliff. An evolutionary approach to situated AI. In A. Sloman et al., editor, Proc. 9th bi-annual conference of the Society for the Study of Artificial Intelligence and the Simulation of Behaviour (AISB 93), pages 61–70. IOS Press, 1993.Google Scholar
  10. 10.
    N. Jakobi. Evolving sensorimotor control architectures in simulation for a real robot. Master's thesis, School of Cognitive and Computing Sciences, University of Sussex, 1994.Google Scholar
  11. 11.
    K-Team. Khepera users manual. EPFL, Lausanne, June 1993.Google Scholar
  12. 12.
    J. Kunt. An Introduction to Control Theory. Huddersfield and Wallstone, 1964.Google Scholar
  13. 13.
    O. Miglino, C. Nafasi, and C. Taylor. Selection for wandering behavior in a small robot. Technical Report UCLA-CRSP-94-01, Dept. Cognitive Science, UCLA, 1994.Google Scholar
  14. 14.
    F. Mondada and P. Verschure. Modeling system-environment interaction: The complementary roles of simulations and real world artifacts. In Proceedings of Second European Conference on Artificial Life, ECAL93, pages 808–817. Brussels, May 1993, 1993.Google Scholar
  15. 15.
    S. Nolfi, D. Floreano, O. Miglino, and F. Mondada. How to evolve autonomous robots: Different approaches in evolutionary robotics. In R. Brooks and P. Maes, editors, Artificial Life IV, pages 190–197. MIT Press/Bradford Books, 1994.Google Scholar
  16. 16.
    Tim Smithers. On why better robots make it harder. In D. Cliff, P. Husbands, J.-A. Meyer, and S. Wilson, editors, From Animals to Animats 3, Proc. of 3rd Intl. Conf. on Simulation of Adaptive Behavior, SAB'94, pages 54–72. MIT Press/Bradford Books, 1994.Google Scholar
  17. 17.
    A. Thompson. Evolving electronic robot controllers that exploit hardware resources. In Submitted to ECAL'95, 1995.Google Scholar
  18. 18.
    B. Yamauchi and R. Beer. Integrating reactive, sequential, and learning behavior using dynamical neural networks. In D. Cliff, P. Husbands, J.-A. Meyer, and S. Wilson, editors, From Animals to Animats 3, Proc. of 3rd Intl. Conf, on Simulation of Adaptive Behavior, SAB'94, pages 382–391. MIT Press/Bradford Books, 1994.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • Nick Jakobi
    • 1
  • Phil Husbands
    • 1
  • Inman Harvey
    • 1
  1. 1.School of Cognitive and Computing SciencesUniversity of SussexBrightonEngland

Personalised recommendations