Skip to main content

Wolves in Sheep’s Clothing: Using Shill Agents to Misdirect Multi-robot Teams

  • Conference paper
  • First Online:
Deceptive AI (DeceptECAI 2020, DeceptAI 2021)

Abstract

When robots undertake tasks in adversarial environments in which they must cooperate with one another (e.g., military applications or the RoboCup Competition), they are at risk for being deceived by competitors. Competitors can misdirect the team to gain a positional advantage. Our lab is exploring ways in which teams of robots can be misdirected, in part, so counter-deception strategies can be devised. This paper explores how robot shills can be used to misdirect a multi-robot team. It defines behaviors for the agents to be deceived (the mark agents) using the multi-agent coordination literature as well as behaviors for the deceiving team (the shills and lead agent). These behaviors were implemented and simulations were run for a variety of conditions. The results show how shills can facilitate misdirection in certain circumstances. They provide insights into enhancing multi-robot team deception.

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

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 54.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 69.99
Price excludes VAT (USA)
  • Compact, lightweight 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

References

  1. Couzin, I.D., Krause, J., Franks, N.R., Levin, S.A.: Effective leadership and decision-making in animal groups on the move. Nature 433(7025), 513 (2005)

    Article  Google Scholar 

  2. Duncan, B.A., Ulam, P.D., Arkin, R.C.: Lek behavior as a model for multi-robot systems. In: Proceedings of the 2009 IEEE International Conference on Robotics and Biomimetics (ROBIO), pp. 25–32. IEEE (2009)

    Google Scholar 

  3. Epstein, J.M.: Modeling civil violence: an agent-based computational approach. Proc. Natl. Acad. Sci. 99(Suppl. 3), 7243–7250 (2002)

    Article  Google Scholar 

  4. Gade, S., Paranjape, A.A., Chung, S.: Herding a flock of birds approaching an airport using an unmanned aerial vehicle. In: AIAA Guidance, Navigation, and Control Conference (2015)

    Google Scholar 

  5. Granovetter, M.: Threshold models of collective behavior. Am. J. Sociol. 83(6), 1420–1443 (1978)

    Article  Google Scholar 

  6. Paranjape, A.A., Chung, S., Kim, K., Shim, D.H.: Robotic herding of a flock of birds using an unmanned aerial vehicle. IEEE Trans. Rob. 34(4), 901–915 (2018)

    Article  Google Scholar 

  7. Pettinati, M.J., Arkin, R.C.: Push and pull: shepherding multi-agent robot teams in adversarial situations. In: 15th IEEE International Conference on Advanced Robotics and Its Social Impacts (ARSO 2019), Beijing, China (2019)

    Google Scholar 

  8. Sanghvi, N., Nagavalli, S., Sycara, K.: Exploiting robotic swarm characteristics for adversarial subversion in coverage task. In: Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems (2017)

    Google Scholar 

  9. Shim, J., Arkin, R.C.: Biologically-inspired deceptive behavior for a robot. In: Ziemke, T., Balkenius, C., Hallam, J. (eds.) SAB 2012. LNCS (LNAI), vol. 7426, pp. 401–411. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33093-3_40

    Chapter  Google Scholar 

  10. Shim, J., Arkin, R.C.: A taxonomy of robot deception and its benefits in HRI. In: 2013 IEEE International Conference on Systems, Man, and Cybernetics. IEEE (2013)

    Google Scholar 

  11. Vaughan, R., Sumpter, N., Frost, R., Cameron, S.: Robot sheepdog project achieves automatic flock control. In: Proceedings of the Fifth International Conference on the Simulation of Adaptive Behaviour, vol. 489 (1998)

    Google Scholar 

  12. Vaughan, R., Sumpter, N., Henderson, J., Frost, A., Cameron, S.: Experiments in automatic flock control. Robot. Auton. Syst. 31(1–2), 109–117 (2000)

    Article  Google Scholar 

Download references

Acknowledgments

This research is supported by the National Science Foundation under CNS EAGER grant #1848653.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Ronald C. Arkin .

Editor information

Editors and Affiliations

Appendices

Appendix I

The definitions of the robotic behaviors discussed in the text appear below.

figure a

Appendix II

The parameters used for the behavior assemblages appear below. The parameters for the set of simulations in which the Lek Behavior was changed appear in parentheses.

figure b

Rights and permissions

Reprints and permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Pettinati, M.J., Arkin, R.C., Krishnan, A. (2021). Wolves in Sheep’s Clothing: Using Shill Agents to Misdirect Multi-robot Teams. In: Sarkadi, S., Wright, B., Masters, P., McBurney, P. (eds) Deceptive AI. DeceptECAI DeceptAI 2020 2021. Communications in Computer and Information Science, vol 1296. Springer, Cham. https://doi.org/10.1007/978-3-030-91779-1_4

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-91779-1_4

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-91778-4

  • Online ISBN: 978-3-030-91779-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics