Towards an Ethical Robot: Internal Models, Consequences and Ethical Action Selection

  • Alan F. T. Winfield
  • Christian Blum
  • Wenguo Liu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8717)


If robots are to be trusted, especially when interacting with humans, then they will need to be more than just safe. This paper explores the potential of robots capable of modelling and therefore predicting the consequences of both their own actions, and the actions of other dynamic actors in their environment. We show that with the addition of an ‘ethical’ action selection mechanism a robot can sometimes choose actions that compromise its own safety in order to prevent a second robot from coming to harm. An implementation with e-puck mobile robots provides a proof of principle by showing that a simple robot can, in real time, model and act upon the consequences of both its own and another robot’s actions. We argue that this work moves us towards robots that are ethical, as well as safe.


Human-Robot Interaction Safety Internal Model Machine Ethics 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Asimov, I.: I, ROBOT. Gnome Press (1950)Google Scholar
  2. 2.
    Bongard, J., Zykov, V., Lipson, H.: Resilient machines through continuous self-modeling. Science 314(5802), 1118–1121 (2006)CrossRefGoogle Scholar
  3. 3.
    Braitenberg, V.: Vehicles: Experiments in synthetic psychology. MIT Press (1984)Google Scholar
  4. 4.
    Holland, J.: Complex Adaptive Systems. Daedalus (1992)Google Scholar
  5. 5.
    Holland, O. (ed.): Machine Consciousness. Imprint Academic (2003)Google Scholar
  6. 6.
    Isidori, A., Marconi, L., Serrani, A.: Fundamentals of internal-model-based control theory. In: Robust Autonomous Guidance. Advances in Industrial Control, pp. 1–58. Springer, London (2003)CrossRefGoogle Scholar
  7. 7.
    Liu, W., Winfield, A.F.T.: Open-hardware e-puck Linux extension board for experimental swarm robotics research. Microprocessors and Microsystems 35(1) (2011)Google Scholar
  8. 8.
    Marques, H., Holland, O.: Architectures for functional imagination. Neurocomputing 72(4-6), 743–759 (2009)CrossRefGoogle Scholar
  9. 9.
    Michel, O.: Webots: Professional mobile robot simulation. International Journal of Advanced Robotic Systems 1(1), 39–42 (2004)Google Scholar
  10. 10.
    Mondada, F., Bonani, M., Raemy, X., Pugh, J., Cianci, C., Klaptocz, A., Magnenat, S., Zufferey, J.C., Floreano, D., Martinoli, A.: The e-puck, a robot designed for education in engineering. In: Proc. 9th Conference on Autonomous Robot Systems and Competitions, pp. 59–65 (2009)Google Scholar
  11. 11.
    O’Dowd, P.J., Winfield, A.F.T., Studley, M.: The distributed co-evolution of an embodied simulator and controller for swarm robot behaviours. In: Proc. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), pp. 4995–5000 (2011)Google Scholar
  12. 12.
    Stepney, S., Welch, P., Andrews, P. (eds.): CoSMoS 2011: Proc. 2011 Workshop on Complex Systems Modelling and Simulation. Luniver Press (2011)Google Scholar
  13. 13.
    Vaughan, R.: Massively multi-robot simulation in stage. Swarm Intelligence 2(2-4), 189–208 (2008)CrossRefGoogle Scholar
  14. 14.
    Vaughan, R.T., Gerkey, B.P.: Really reused robot code from the player/stage project. In: Brugali, D. (ed.) Software Engineering for Experimental Robotics, pp. 267–289. Springer (2007)Google Scholar
  15. 15.
    Vaughan, R.T., Zuluaga, M.: Use your illusion: Sensorimotor self-simulation allows complex agents to plan with incomplete self-knowledge. In: Proc. International Conference on Simulation of Adaptive Behaviour (SAB), pp. 298–309 (2006)Google Scholar
  16. 16.
    Wallach, W., Allen, C.: Moral Machines: Teaching Robots Right from Wrong. Oxford University Press, Oxford (2009)Google Scholar
  17. 17.
    Zagal, J.C., Delpiano, J., Ruiz-del Solar, J.: Self-modeling in humanoid soccer robots. Robot. Auton. Syst. 57(8), 819–827 (2009)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Alan F. T. Winfield
    • 1
  • Christian Blum
    • 2
  • Wenguo Liu
    • 1
  1. 1.Bristol Robotics LaboratoryUWE BristolUK
  2. 2.Cognitive Robotics, Department of Computer ScienceHumboldt-Universität zuBerlinGermany

Personalised recommendations