Browse Publications Technical Papers 2019-01-1051
2019-04-02

Vehicle Velocity Prediction and Energy Management Strategy Part 1: Deterministic and Stochastic Vehicle Velocity Prediction Using Machine Learning 2019-01-1051

There is a pressing need to develop accurate and robust approaches for predicting vehicle speed to enhance fuel economy/energy efficiency, drivability and safety of automotive vehicles. This paper details outcomes of research into various methods for the prediction of vehicle velocity. The focus is on a short-term predictions over 1-10 seconds time windows. Such short-term predictions can be integrated into a hybrid electric vehicle energy management strategy and have the potential to improve HEV energy efficiency. Deterministic and stochastic models are developed to predict the future vehicle velocity. Deterministic models include an Auto-Regressive Moving Average (ARMA) model, a Nonlinear Auto-Regressive with eXternal input (NARX) shallow neural network and a Long Short-Term Memory (LSTM) deep neural network. Stochastic models include a Markov Chain (MC) model and a Conditional Linear Gaussian (CLG) model. To derive the prediction models, numerous data streams are used, including internal vehicle data (CAN bus) and external vehicle data (radar information and V2I). Two data sets representative of real world driving in Ann Arbor, Michigan are used. One of these data sets reflects highway-focused single-car driving, and another one is representative of an urban/highway mixed three-cars driving. Time shift, a novel index which reflects the time lag of prediction, is introduced to assess the prediction accuracy of vehicle velocity. Also, a more standard Mean Absolute Error (MAE) metric is used to evaluate the prediction results. In order to improve the vehicle speed prediction accuracy, additional labels are introduced to cue machine learners on different features present in the driving trajectories. The results show that these manually introduced labels can significantly improve the prediction accuracy both in terms of MAE and time shift metrics. The results also indicate that deterministic models can give more accurate performance on average while stochastic models, while may be less accurate in terms of the average velocity prediction, provide information on the prediction error distribution. Overall, LSTM deep neural network has been able to achieve the best accuracy in predicting vehicle velocity. For 10 seconds velocity prediction, LSTM demonstrates prediction accuracy with MAE of about 1 m/s and time shift of about 2 seconds.

SAE MOBILUS

Subscribers can view annotate, and download all of SAE's content. Learn More »

Access SAE MOBILUS »

Attention: This item is not yet published. Pre-Order to be notified, via email, when it becomes available.
Members save up to 40% off list price.
Login to see discount.
Special Offer: With TechSelect, you decide what SAE Technical Papers you need, when you need them, and how much you want to pay.
X