By observing driver in real road situations, we learn a computer assistant that can make driving easier, safer and more enjoyable.
Self-driving cars have obtained a lot of attention in recent years from both research and industry. On the way to fully autonomous vehicles we aim to support a human driver by providing a computer assistant. We want to advance existing systems to another level by providing natural and targeted interaction based on the events both in and outside the car. We use a dataset from recording of real driving in combination with machine learning techniques in order to predict driver's intentions. This will help the artificial co-pilot in the car to determine the most efficient solution for given road situation.