Application of Dempster–Shafer Networks to a Real-Time Unmanned Systems Risk Analysis Framework

Abstract
Unmanned aerial systems (UASs) are continuing to proliferate. Quantitative risk assessment for UAS operations, both a priori and during the operation, are necessary for governing authorities and insurance companies to understand the risks and properly approve operations and assign insurance premiums, respectively. In this paper, the problem of UAS risk analysis and decision making is treated through a novel application of Dempster–Shafer (DS) networks using auto-updating transition matrices. This method was motivated by the results of the 2018 UAS Safety Symposium held at the Georgia Institute of Technology, which was conducted as part of the research detailed in this paper. The paper describes training a DS network based on simulated operation data, testing the capabilities of the trained network to make real-time decisions on a small UAS against a baseline system in a representative mission, and exploring how this system would extend to a more inclusive UAS ecosystem. Conclusions are drawn with respect to the research performed, and additional research directions are proposed.

Citation
Dunham, J., Johnson, E., Feron, E., & German, B. (2021). Application of Dempster–Shafer Networks to a Real-Time Unmanned Systems Risk Analysis Framework. Journal of Aerospace Information Systems, 1–16. doi:10.2514/1.i010924

Acknowledgements
The authors would like to thank the following people for participating in the 2018 UAS Safety Symposium at Georgia Tech since that effort provided much of the driver for this research: Roy Burke, Julianna Burke, Anthony Mormino, Eric Richey, Chris Proudlove, Naira Hovakimyan, Jeong Jur, Greg Ourada, and Michael Miller. The authors are also thankful to Olivia Jagiella-Lodise and Philippe Monmousseau for their contributions in editing and formatting this paper.

Publisher
American Institute of Aeronautics and Astronautics (AIAA)

Journal
Journal of Aerospace Information Systems

DOI
10.2514/1.i010924
10.2514/1.i010924.c1

Additional Links
https://arc.aiaa.org/doi/10.2514/1.I010924

Permanent link to this record