Advertisement

Learning to Estimate: A Case-Based Approach to Task Execution Prediction

  • Bryan AuslanderEmail author
  • Michael W. Floyd
  • Thomas Apker
  • Benjamin Johnson
  • Mark Roberts
  • David W. Aha
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9343)

Abstract

A system that controls a team of autonomous vehicles should be able to accurately predict the expected outcomes of various subtasks. For example, this may involve estimating how well a vehicle will perform when searching a designated area. We present CBE, a case-based estimation algorithm, and apply it to the task of predicting the performance of autonomous vehicles using simulators of varying fidelity and past performance. Since there are costs to evaluating the performance in simulators (i.e., higher fidelity simulators are more computationally expensive) and in deployment (i.e., potential human injury and deployment expenses), CBE uses a variant of local linear regression to estimate values that cannot be directly evaluated, and incrementally revises its case base. We empirically evaluate CBE on Humanitarian Assistance/Disaster Relief (HA/DR) scenarios and show it to be more accurate than several baselines and more efficient than using a low fidelity simulator.

Keywords

Autonomous Vehicle Problem Feature High Fidelity Simulator Mission Manager Goal Reasoning 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Notes

Acknowledgements

Thanks to OSD ASD (R&E) for sponsoring this research.

References

  1. Abi-Zeid, I., Yang, Q., Lamontagne, L.: Is CBR applicable to the coordination of search and rescue operations? A feasibility study. In: Althoff, K.-D., Bergmann, R., Branting, L. (eds.) ICCBR 1999. LNCS (LNAI), vol. 1650, pp. 358–371. Springer, Heidelberg (1999)CrossRefGoogle Scholar
  2. Aha, D.W., Salzberg, S.L.: Learning to catch: applying nearest neighbor algorithms to dynamic control tasks. In: Proceedings of the Fourth International Workshop on Artificial Intelligence and Statistics, Ft. Lauderdale, FL, pp. 363–368 (1993, Unpublished)Google Scholar
  3. Atkeson, C., Moore, A., Schaal, S.: Locally weighted learning. Artif. Intell. Rev. 11(1–5), 11–73 (1997a)CrossRefGoogle Scholar
  4. Atkeson, C., Moore, A., Schaal, S.: Locally weighted learning for control. Artif. Intell. Rev. 11(1–5), 75–113 (1997b)CrossRefGoogle Scholar
  5. Auslander, B., Apker, T., Aha, D.W.: Case-based parameter selection for plans: coordinating autonomous vehicle teams. In: Lamontagne, L., Plaza, E. (eds.) ICCBR 2014. LNCS, vol. 8765, pp. 32–47. Springer, Heidelberg (2014)Google Scholar
  6. Borck, H., Karneeb, J., Alford, R., Aha, D.W.: Case-based behavior recognition in beyond visual range air combat. In: Proceedings of the Twenty-Eighth Florida Artificial Intelligence Research Society Conference, pp. 379–384. AAAI Press, Hollywood, FL (2015)Google Scholar
  7. Cleveland, W.S., Devlin, S.J.: Locally weighted regression: an approach to regression analysis by local fitting. J. Am. Stat. Assoc. 83(403), 596–610 (1988)CrossRefzbMATHGoogle Scholar
  8. Duquette, M.: Effects-level models for UAV simulation. In: Proceedings of the AIAA Modeling and Simulation Technologies Conference. AIAA, Chicago, IL (2009)Google Scholar
  9. Forbus, K.D., Gentner, D., Law, K.: MAC/FAC: A model of similarity-based retrieval. Cogn. Sci. 19, 141–205 (1995)CrossRefGoogle Scholar
  10. Gabel, T., Riedmiller, M.: An analysis of case-based value function approximation by approximating state transition graphs. In: Weber, R.O., Richter, M.M. (eds.) ICCBR 2007. LNCS (LNAI), vol. 4626, pp. 344–358. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  11. Geofabrik: OpenStreetMap data extracts (2014). http://download.geofabrik.de/index.html
  12. Gillespie, K., Molineaux, M., Floyd, M.W., Vattam, S.S., Aha, D.W.: Goal reasoning for an autonomous squad member. In: Aha, D.W. (ed.) Goal Reasoning: Papers from the ACS Workshop, Atlanta, GA (2015). www.cc.gatech.edu/~svattam/goal-reasoning
  13. Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The WEKA data mining software: an update. SIGKDD Explor. 11(1), 10–18 (2009)CrossRefGoogle Scholar
  14. Jaidee, U., Muñoz-Avila, H., Aha, D.W.: Case-based goal-driven coordination of multiple learning agents. In: Delany, S.J., Ontañón, S. (eds.) ICCBR 2013. LNCS, vol. 7969, pp. 164–178. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  15. Likhachev, M., Kaess, M., Arkin, R.: Learning behavioral parameterization using spatio-temporal case-based reasoning. In: Proceedings of the International Conference on Robotics and Automation, pp. 1282–1289. IEEE Press, Washington, DC (2002)Google Scholar
  16. Luke, S., Cioffi-Revilla, C., Panait, L., Sullivan, K., Balan, G.: MASON: a multiagent simulation environment. Simulation 81(7), 517–527 (2005)CrossRefGoogle Scholar
  17. Martinson, E., Apker, T., Bugajska, M.: Optimizing a reconfigurable robotic microphone array. In: Proceedings of the International Conference on Intelligent Robots and Systems, pp. 125–130. IEEE Press, San Francisco, CA (2011)Google Scholar
  18. Molineaux, M., Aha, D.W., Moore, P.: Learning continuous action models in a real-time strategy environment. In: Proceedings of the Twenty-First Florida Artificial Intelligence Research Conference, pp. 257–262. AAAI Press, Coconut Grove, FL (2008)Google Scholar
  19. Muñoz-Avila, H., Aha, D., Breslow, L., Nau, D.: HICAP: an interactive case-based planning architecture and its application to noncombatant evacuation operations. In: Proceedings of the Ninth National Conference on Innovative Applications of Artificial Intelligence, pp. 879–885. AAAI Press, Orlando, FL (1999)Google Scholar
  20. Muñoz-Avila, H., Aha, D., Nau, D., Weber, R., Breslow, L., Yaman, F.: SiN: integrating case-based reasoning with task decomposition. In: Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence, pp. 999–1004. Morgan Kaufmann, Seattle, WA (2001)Google Scholar
  21. O’Connor, C.: Foreign humanitarian assistance and disaster-relief operations: lessons learned and best practices. Nav. War Coll. Rev. 65(1), 152–160 (2012)Google Scholar
  22. Roberts, M., Apker, T., Johnson, B., Auslander, B., Wellman, B., Aha, D.W.: Coordinating robot teams for disaster relief. In: Proceedings of the Twenty-Eighth Florida Artificial Intelligence Research Society Conference, pp. 366–371. AAAI Press, Hollywood, FL (2015)Google Scholar
  23. Ros, R., Arcos, J., Lopez de Mantaras, R., Veloso, M.: A case-based approach for coordinated action selection in robot soccer. Artif. Intell. 173, 1014–1039 (2009)Google Scholar
  24. Wilson, M., Molineaux, M., Aha, D.W.: Domain-independent heuristics for goal formulation. In: Proceedings of the Twenty-Sixth Florida Artificial Intelligence Research Society Conference, pp. 160–165. AAAI Press, St. Pete Beach, FL (2013)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Bryan Auslander
    • 1
    Email author
  • Michael W. Floyd
    • 1
  • Thomas Apker
    • 2
  • Benjamin Johnson
    • 3
  • Mark Roberts
    • 3
  • David W. Aha
    • 2
  1. 1.Knexus Research CorporationSpringfieldUSA
  2. 2.Navy Center for Applied Research in Artificial Intelligence, Naval Research Laboratory (Code 5514)Washington, DCUSA
  3. 3.NRC Postdoctoral Fellow, Naval Research Laboratory (Code 5514)Washington, DCUSA

Personalised recommendations