Abstract
Computational models of fighter pilot decision-making provide insight into a pilot’s behavior, facilitating pilot performance assessment. This paper describes our application of Long Short-Term Memory (LSTM) neural networks to a dataset of pilot actions during simulated missile avoidance to generate metrics of pilot behavior under pressure. Lockheed Martin collected and curated the data from multiple human pilots, with varying experience, executing simulated missile avoidance scenarios. By evaluating model performance across sweeps of data characteristics, then fitting exponential functions to the performance trends, we identify unique pilot behavior metrics that correlate with pilot performance. We discuss how these metrics could provide insight into the complexity of pilot behavior, as well as provide a mechanism to evaluate pilot performance and enhance human-machine symbiosis.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Gray, W.D.: Integrated models of cognitive systems. In: AFOSR Cognitive Modeling Workshop. Saratoga Springs, NY, USA (2005)
Busemeyer, J.R., et al.: Cognitive and neural bases of multi-attribute, multi-alternative, value-based decisions. Trends Cogn. Sci. 23(3) (2019). https://doi.org/10.1016/j.tics.2018.12.003
Sherstinsky, A.: Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network (2018). arXiv:1808.03314
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: 3rd International Conference for Learning Representations, San Diego (2015)
Grigsby, S.S.: Artificial intelligence for advanced human-machine symbiosis. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-91470-1_22
Acknowledgments
We would like to thank Danielle Clement and Sarah Mottino at Lockheed Martin Aero for providing us with the dataset used for this analysis. We would also like to thank Raquel Galvan-Garza and Joshua Pletz at Lockheed Martin Advanced Technology Laboratories for their contributions to this effort. Funding for this effort was provided by Lockheed Martin.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Barone, B., Coar, D., Shafer, A., Guo, J.K., Galego, B., Allen, J. (2021). Interpreting Pilot Behavior Using Long Short-Term Memory (LSTM) Models. In: Ahram, T.Z., Karwowski, W., Kalra, J. (eds) Advances in Artificial Intelligence, Software and Systems Engineering. AHFE 2021. Lecture Notes in Networks and Systems, vol 271. Springer, Cham. https://doi.org/10.1007/978-3-030-80624-8_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-80624-8_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-80623-1
Online ISBN: 978-3-030-80624-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)