This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Predictive Modeling of Aircraft Dynamics Using Neural Networks
- Sean Soleyman - HRL Laboratories LLC, USA ,
- Yang Chen - HRL Laboratories LLC, USA ,
- Joshua Fadaie - HRL Laboratories LLC, USA ,
- Fan Hung - HRL Laboratories LLC, USA ,
- Deepak Khosla - HRL Laboratories LLC, USA ,
- Shawn Moffit - Boeing, USA ,
- Shane Roach - HRL Laboratories LLC, USA ,
- Charles Tullock - Boeing, USA
Journal Article
01-15-02-0010
ISSN: 1946-3855, e-ISSN: 1946-3901
Sector:
Citation:
Soleyman, S., Chen, Y., Fadaie, J., Hung, F. et al., "Predictive Modeling of Aircraft Dynamics Using Neural Networks," SAE Int. J. Aerosp. 15(2):159-170, 2022, https://doi.org/10.4271/01-15-02-0010.
Language:
English
Abstract:
Fighter pilots must study models of aircraft dynamics before learning complex
maneuvers and tactics. Similarly, autonomous fighter aircraft applications may
benefit from a model-based learning approach. Instead of using a preexisting
physics model of a given aircraft, a machine learning system can learn a
predictive model of the aircraft physics from training data. Furthermore, it can
model interactions between multiple friendly aircraft, enemy aircraft, and the
environment. Such a system can also learn to represent state variables that are
not directly observable, as well as dynamics that are not hard coded. Existing
model-based methods use a deep neural network that takes observable state
information and agent actions as input and provides predictions of future
observations as output. The proposed method builds upon this approach by adding
a residual feedforward skip connection from some of the inputs to all of the
outputs of the deep neural network. Further innovations address numerical
conditioning issues as well as periodic discontinuities of angular quantities
such as bearing or heading. The methods in this article also extend techniques
from model-based reinforcement learning control to the domain of adversarial
multi-agent environments. In previous literature, these model-based methods have
only been used for controlling individual agents. Instead of using a traditional
Recurrent Neural Network (RNN) to learn a representation of the world state, the
novel method also uses a compressive encoding scheme. This is based on an
augmented version of the same neural network that is used for predictive
modeling.