Transfer learning for adaptable autonomy

We explore the use of transfer learning to reduce the data and computing resources required for training convolutional neural networks used by autonomous vehicles for predicting target behavior and improving target tracking as the scenario/environment changes. We demonstrate the ability to adapt to four different changes to the baseline scenario: a new target behavior, mission, adversary, and environment. The results from all four scenarios demonstrate positive transfer learning with reduced training datasets and show that transfer learning is a robust approach to dealing with changing environments even when the input or output dimensions of the neural network are changed.