Predictive Modeling of Aircraft Dynamics Using Neural Networks

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.