Advertisement

Simulation-Based Air Mission Evaluation with Bayesian Threat Assessment for Opposing Forces

  • André N. CostaEmail author
  • Paulo C. G. Costa
Conference paper

Abstract

Several advancements have been made to the air mission planning process in recent years, spawning several software tools that allow for a quick analysis of the feasibility of the mission. However, the determination of the most likely outcomes of an air mission plan is still a challenge for modelers and planners. Mathematical models are capable of representing the complexity of sensors and weapons systems, but are not as effective in providing a thorough visualization of the mission, as well as in accounting for environmental factors and interactions between multiple systems within an operational setting.

Our research addresses the Systems Engineering problem of enhancing a system’s response by predicting the adversarial reactions to different inputs. We adopt a physics-grounded simulation approach that focuses on the handling of uncertainty in behavioral models as a means of properly assessing the responses. As part of this research, the work presented in this paper proposes the use of high-resolution simulation for evaluating the survivability and mission accomplishment rates of an attacking aircraft during an incursion. The work differs from purely scripted simulation, which employs rule-based entities, predefined routes and behaviors for blue and red forces. Instead, our prototype relies on a Bayesian threat assessment and response methodology. Our goal is to represent the enemy’s decision process, while being able to predict the mission outcomes and to correctly assess the regions of higher vulnerability.

Keywords

Military simulation Bayesian networks Threat assessment Survivability Air warfare Decision support 

Notes

Acknowledgments

The authors thank Danny Williams, from VT MÄK, who was instrumental in providing technical expertise in the VR-Forces suite and Shou Matsumoto for the support on its integration with UnBBayes.

References

  1. 1.
    Schulte A (2002) Cognitive automation for tactical mission management: concept and prototype evaluation in flight simulator trials. Cogn Technol Work 4(3):146–159Google Scholar
  2. 2.
    Theunissen E, Bolderheij F, Koeners GJM (2005) Integration of threat information into the route (re-) planning task. In: 24th Digital Avionics Systems Conference, Washington, DC, USA, vol 2, 14 ppGoogle Scholar
  3. 3.
    Richards MA, Scheer J, Holm WA (2010) Principles of modern radar. [electronic resource]. Scitech Pub., c2010, RaleighGoogle Scholar
  4. 4.
    Erlandsson T (2014) A combat survivability model for evaluating air mission routes in future decision support systemsGoogle Scholar
  5. 5.
    Quttineh N-H, Larsson T, Lundberg K, Holmberg K (2013) Military aircraft mission planning: a generalized vehicle routing model with synchronization and precedence. EURO J Transp Logist 2(1–2):109–127CrossRefGoogle Scholar
  6. 6.
    Erlandsson T (2014) Route planning for air missions in hostile environments. J Def Model Simul Appl Methodol Technol. doi: 10.1177/1548512914544529
  7. 7.
    VR-forces: computer generated forces – VT MÄK. [Online]. Available: http://www.mak.com/products/simulate/vr-forces. Accessed: 14 Aug 2016
  8. 8.
    Abdellaoui N, Taylor A, Parkinson G Comparative analysis of computer generated forces’ artificial intelligenceGoogle Scholar
  9. 9.
    Parkinson G (2009) AI in CGFs comparative analysis. Defence R&D, Ottawa, Canada, Summary Report, DecemberGoogle Scholar
  10. 10.
    Poropudas J, Virtanen K (2009) Influence diagrams in analysis of discrete event simulation data. In: Winter Simulation Conference, Austin, Texas, pp 696–708Google Scholar
  11. 11.
    Laskey KB (2008) MEBN: a language for first-order Bayesian knowledge bases. Artif Intell 172(2):140–178MathSciNetCrossRefzbMATHGoogle Scholar
  12. 12.
    Matsumoto S et al (2011) UnBBayes: a java framework for probabilistic models in AI. In: Ke Cai (ed) Java in Academia and Research - ISBN: 978-0980733082. Annerley, Australia, iConcept Press Ltd, p 34Google Scholar
  13. 13.
    Mahjoub MA, Kalti K (2011) Software comparison dealing with Bayesian networks. In: Liu D, Zhang H, Polycarpou M, Alippi C, He H (eds) Advances in neural networks – ISNN 2011. Berlin Heidelberg, Springer, pp 168–177CrossRefGoogle Scholar
  14. 14.
    Johansson F, Falkman G (2008) A Bayesian network approach to threat evaluation with application to an air defense scenario. In: 2008 11th International Conference on Information Fusion, Cologne, Germany, pp 1–7Google Scholar
  15. 15.
    Okello N, Thorns G (2003) Threat assessment using bayesian networks. In: Proceedings of the Sixth International Conference of Information Fusion, Cairns, Australia, vol 2, pp 1102–1109Google Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  1. 1.Institute for Advanced Studies, Brazilian Air ForceSão José dos CamposBrazil
  2. 2.Department of Systems Engineering and Operations ResearchGeorge Mason UniversityFairfaxUSA

Personalised recommendations