Battery aging prognosis is a key requirement for the successful market introduction of electric and hybrid vehicles. Currently, most methods rely on accelerated aging test data and physical or empirical aging models. However, considering the complexity of the aging mechanisms and the limited time and experimental resources, these methods fail on predicting battery aging in vehicles. Recent results of combining deliberate data generation with data-driven modeling to predict the behavior of complex dynamical systems using machine learning techniques, however, indicate how to tackle the battery aging problem. This project will explore these techniques to make use of combined field and lab data to estimate the states of aging. Based on such a model and by understanding the usage patterns affecting battery life the most, the project will derive design control strategies that can extend the RUL of the traction battery inside the vehicle.