Andrew Simpson

Shuyang Du, Haoli Guo, Andrew Simpson

Self-driving vehicles have expanded dramatically over the last few years. Udacity has release a dataset containing, among other data, a set of images with the steering angle captured during driving. The Udacity challenge aimed to predict steering angle based on only the provided images. We explore two different models to perform high quality prediction of steering angles based on images using different deep learning techniques including Transfer Learning, 3D CNN, LSTM and ResNet. If the Udacity challenge was still ongoing, both of our models would have placed in the top ten of all entries.

Eduardo dos Santos, Andrew Simpson, Dominik Schoop

Ensuring a car's internal systems are free from security vulnerabilities is of utmost importance, especially due to the relationship between security and other properties, such as safety and reliability. We provide the starting point for a model-based framework designed to support the security testing of modern cars. We use Communicating Sequential Processes (CSP) to create architectural models of the vehicle bus systems, as well as an initial set of attacks against these systems. While this contribution represents initial steps, we are mindful of the ultimate objective of generating test code to exercise the security of vehicle bus systems. We present the way forward from the models created and consider their potential integration with commercial engineering tools