Skip to main content
SpringerLink
Log in

Teammate-pattern-aware autonomy based on organizational self-design principles

  • Published:
Autonomous Agents and Multi-Agent Systems Aims and scope Submit manuscript

Abstract

We describe an approach for constraining robot autonomy based on the robot’s awareness of patterns of its human teammates’ behaviors, rather than either ignoring its teammates (which is fast but dangerous) or inferring their plans (which is safer but slow). We explore the promise, and limitations, of this approach in a series of simulated problems where an unmanned ground vehicle and its human teammates must rapidly respond to a sudden context shift. Our results help us discern conditions under which a pattern-aware approach can be more effective than the alternatives, and our current efforts investigate how the manned–unmanned team can adopt biases to more readily establish such conditions that are more favorable to the pattern-aware approach.

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.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

Notes

  1. Note that the prior distribution could represent complete uncertainty, modeling that a teammate might be equally likely to be anywhere when the context shift happens. Our methods do not require a more certain distribution, but as we empirically show the quality of the solution improves with more precise knowledge. And, in contrast to modeling an arbitrary multiagent situation, it is likely that teammates would have such knowledge, since they will typically know the roles each is playing on the team for the mission, including where each will generally be going and what each will generally be doing.

  2. When multiple robots are part of the team, then they might engage in MAPF among themselves. This possibility for future work is touched upon in Sect. 8.

  3. As mentioned a few paragraphs ago, such overwhelmingly strong organizational influences could equivalently be implemented by removing some action choices in selected states, and doing so can speed policy search by pruning some trajectories from consideration. We did not pursue this efficiency in this project, however, for two reasons: (1) as summarized in Sect. 4.1, capturing organizational influences in a costmap allows us to be compatible with how other types of influences are represented; and (2) as our empirical work points out (e.g., our experiments on the effects of teammate population size), our approach is designed support other mappings from occupancy to cost that allows trading off risk to teammates to gain other efficiencies. The alternative influence implementation through removing some action choices is “all or nothing” and is thus too rigid to support different tradeoffs.

  4. Had we used an approach that computed the optimal policy in some other manner such as value or policy iteration [28], then we would need to do an additional analysis (or round of simulations) to enumerate the states that have non-zero probability of being occupied by an agent following the policy.

  5. Note that, since we assume people will react independently to the context shift, we can model a single human teammate in each sample. If this were not the case, we’d sample initial configurations of multiple teammates, and the procedure CREATEPOLICY-LINEARPROGRAM would need to solve for their joint (interdependent) policy, as in the work of Sleight and Durfee [33].

  6. We purposely recomputed costmaps each time to average out cases, especially with fewer samples, where particularly lucky or unlucky sampling could skew the results.

References

  1. Agogino, A. K., & Tumer, K. (2005). Multi-agent reward analysis for learning in noisy domains. In 4th international joint conference on autonomous agents and multiagent systems (AAMAS) (pp. 81–88).

  2. Albus, J. S. (1993). A reference model architecture for intelligent systems design. In K. M. Passino & P. J. Antsaklis (Eds.), An introduction to intelligent and autonomous control (pp. 27–56). Berlin: Kluwer Academic Publishers.

    Google Scholar 

  3. Barbulescu, L., Rubinstein, Z. B., Smith, S. F., & Zimmerman, T. L. (2010). Distributed coordination of mobile agent teams: The advantage of planning ahead. In Proceedings of the 9th international conference on autonomous agents and multiagent systems, international foundation for autonomous agents and multiagent systems (pp. 1331–1338).

  4. Bibu, G. D. (2019). Modelling organisations as electronic institutions. International Journal of Scientific and Technology Research, 8(6), 37–43.

    Google Scholar 

  5. Clement, B. J., Durfee, E. H., & Barrett, A. C. (2007). Abstract reasoning for planning and coordination. Journal of Artificial Intelligence Research (JAIR), 28, 453–515.

    Article  Google Scholar 

  6. Corkill, D. D. (1983). A framework for organizational self-design in distributed problem-solving networks. Ph.D. thesis, University of Massachusetts.

  7. Corkill, D. D., Zhang, C., da Silva, B. C., Kim, Y., Garant, D., Lesser, V. R., & Zhang, X. (2013). Biasing the behavior of organizationally adept agents: Extended abstract. In International conference on autonomous agents and multi-agent systems, AAMAS (pp. 1309–1310).

  8. Cossentino, M., Lodato, C., Lopes, S., Ribino, P., Seidita, V., & Chella, A. (2011). Towards a design process for modeling MAS organizations. In 9th European workshop on multi-agent systems EUMAS (pp. 63–79).

  9. Cox, J. S., Clement, B. J., Pappachan, P. M., & Durfee, E. H. (2001). Integrating multiagent coordination with reactive plan execution. In Proceedings of the fifth international conference on autonomous agents (pp. 149–150). ACM

  10. Cranefield, S., Mahmoud, S., Padget, J. A., & Rocha, A. P. (Eds.) (2017). Coordination, organizations, institutions, and norms in agent systems XII—COIN 2016 revised selected papers, lecture notes in computer science (vol. 10315). Springer.

  11. Desaraju, V., & How, J. P. (2012). Decentralized path planning for multi-agent teams with complex constraints. Autonomous Robots, 32(4), 385–403.

    Article  Google Scholar 

  12. Ferrer, G., Garrell, A., & Sanfeliu, A. (2013). Social-aware robot navigation in urban environments. In European conference on mobile robots (ECMR) (pp. 331–336). IEEE.

  13. Gombolay, M. C., Wilcox, R. J., Diaz, A., Yu, F., & Shah, J. A. (2013). Towards successful coordination of human and robotic work using automated scheduling tools: An initial pilot study. In Proceedings of robotics: Science and systems (RSS) human–robot collaboration workshop (HRC).

  14. Groom, V., & Nass, C. (2007). Can robots be teammates? Benchmarks in human–robot teams. Interaction Studies, 8(3), 483–500.

    Article  Google Scholar 

  15. Hayes, B., & Scassellati, B. (2013). Challenges in share-environment human–robot collaboration. In Proceedings of the collaborative manipulation workshop at the 2013 human–robot interaction conference.

  16. Hoffman, G., & Breazeal, C. (2007). Cost-based anticipatory action selection for human–robot fluency. IEEE Transactions on Robotics, 23(5), 952–961.

    Article  Google Scholar 

  17. Hübner, J. F., Sichman, J. S., & Boissier, O. (2002). MOISE+: Towards a structural, functional, and deontic model for MAS organization. In 1st international conference on autonomous agents and multiagent systems AAMAS.

  18. Kallenberg, L. C. M. (1983). Linear programming and finite Markovian control problems. Amsterdam: Centrum Voor Wiskunde en Informatica, Technical report.

  19. King, J. E., & Likhachev, M. (2009). Efficient cost computation in cost map planning for non-circular robots. In 2009 IEEE/RSJ international conference on intelligent robots and systems (IROS) (pp. 3924–3930).

  20. Li, Y., Tee, K. P., Yan, R., Chan, W. L., & Wu, Y. (2016). A framework of human–robot coordination based on game theory and policy iteration. IEEE Transactions on Robotics, 32(6), 1408–1418.

    Article  Google Scholar 

  21. Lin, P., Liu, J., Jin, P. J., & Ran, B. (2017). Autonomous vehicle-intersection coordination method in a connected vehicle environment. IEEE Intelligent Transportation Systems Magazine, 9(4), 37–47.

    Article  Google Scholar 

  22. Murashov, V., Hearl, F., & Howard, J. (2016). Working safely with robot workers: Recommendations for the new workplace. Journal of Occupational and Environmental Hygiene, 13(3), 61–71.

    Article  Google Scholar 

  23. Nicolescu, M. N., & Matarić, M. J. (2002). A hierarchical architecture for behavior-based robots. In Proceedings of the first international joint conference on autonomous agents and multiagent systems (AAMAS) (pp 227–233). ACM.

  24. Onieva, E., Milanés, V., Villagra, J., Pérez, J., & Godoy, J. (2012). Genetic optimization of a vehicle fuzzy decision system for intersections. Expert Systems with Applications, 39(18), 13148–13157.

    Article  Google Scholar 

  25. Pynadath, D. V., & Tambe, M. (2003). An automated teamwork infrastructure for heterogeneous software agents and humans. Journal of Autonomous Agents and Multi-Agent Systems, 7(1–2), 71–100.

    Article  Google Scholar 

  26. Ren, W., & Sorensen, N. (2008). Distributed coordination architecture for multi-robot formation control. Robotics and Autonomous Systems, 56(4), 324–333.

    Article  Google Scholar 

  27. Richardson, A., & Olson, E. (2011). Iterative path optimization for practical robot planning. In IEEE/RSJ international conference on intelligent robots and systems (IROS) (pp. 3881–3886). IEEE.

  28. Russell, S. J., & Norvig, P. (2010). Artificial intelligence: A modern approach. Third international edition. London: Pearson Education.

    MATH  Google Scholar 

  29. Shah, J., & Breazeal, C. (2010). An empirical analysis of team coordination behaviors and action planning with application to human–robot teaming. Human Factors, 52(2), 234–245.

    Article  Google Scholar 

  30. Shoham, Y., & Tennenholtz, M. (1995). On social laws for artificial agent societies: Off-line design. Artificial Intelligence, 73(1–2), 231–252.

    Article  Google Scholar 

  31. Sims, M., Corkill, D. D., & Lesser, V. R. (2008). Automated organization design for multi-agent systems. Autonomous Agents and Multi-Agent Systems, 16(2), 151–185.

    Article  Google Scholar 

  32. Sleight, J., & Durfee, E. H. (2013). Organizational design principles and techniques for decision-theoretic agents. In International conference on autonomous agents and multiagent systems, (AAMAS) (pp. 463–470).

  33. Sleight, J., & Durfee, E. H. (2014). Multiagent metareasoning through organizational design. In Proceedings of the twenty-eighth AAAI conference on artificial intelligence (pp. 1478–1484).

  34. Sleight, J., & Durfee, E. H. (2015). Effective influence abstractions for organizational design. In International conference on autonomous agents and multiagent systems (AAMAS) (pp. 1267–1274).

  35. Stern, R., Sturtevant, N. R., Felner, A., Koenig, S., Ma, H., Walker, T. T., Li, J., Atzmon, D., Cohen, L., Kumar, T. K. S., Barták, R., & Boyarski, E. (2019). Multi-agent pathfinding: Definitions, variants, and benchmarks. In Proceedings of the twelfth international symposium on combinatorial search, SOCS (pp. 151–159).

  36. Wei, C., Hindriks, K. V., & Jonker, C. M. (2016). Altruistic coordination for multi-robot cooperative pathfinding. Applied Intelligence, 44(2), 269–281.

    Article  Google Scholar 

Download references

Acknowledgements

We appreciate the assistance of Dr. Jonathon Smereka in formulating the problem addressed in this article. We also thank the reviewers for many helpful and insightful suggestions for improving the paper. Our implementation built off of some code originally written by Dr. Jason Sleight. Finally, we wish to acknowledge the technical and financial support of the Automotive Research Center (ARC) in accordance with Cooperative Agreement W56HZV-14-2-0001 U.S. Army Tank Automotive Research, Development and Engineering Center (TARDEC) Warren, MI, and Cooperative Agreement W56HZV-19-2-0001 U.S. Army Ground Vehicle System Center (GVSC) in Warren, MI.

Author information

Authors and Affiliations

  1. Computer Science and Engineering, University of Michigan, Ann Arbor, USA

    Edmund H. Durfee, Abhishek Thakur & Eli Goldweber

Authors
  1. Edmund H. Durfee
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Abhishek Thakur
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Eli Goldweber
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Edmund H. Durfee.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Distribution A: Approved for public release; distribution unlimited. OPSEC # 2970.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Durfee, E.H., Thakur, A. & Goldweber, E. Teammate-pattern-aware autonomy based on organizational self-design principles. Auton Agent Multi-Agent Syst 34, 39 (2020). https://doi.org/10.1007/s10458-020-09462-x

Download citation

  • Published:

  • DOI: https://doi.org/10.1007/s10458-020-09462-x

Keywords

Search

Navigation