Toward Safe and Smart Mobility: Energy-Aware Deep Learning for Driving Behavior Analysis and Prediction of Connected Vehicles

Connected automated driving technologies have shown tremendous improvement in recent years. However, it is still not clear how driving behaviors and energy consumption correlate with each other and to what extent these factors related to connected vehicles can influence the motion prediction performance. The precise recognition of driving behaviors and prediction of the vehicle motion is critical to the driving safety for connected automated vehicles (CAVs). Hence, in this study, an energy-aware driving pattern analysis and motion prediction system are proposed for CAVs using a deep learning-based time-series modeling approach. First, energy-aware longitudinal acceleration and deceleration behaviors and lateral lane-change behaviors are statistically analyzed. Then, a sliding standard deviation (SSD) test is applied to evaluate the smoothness of the trajectory and velocity signals considering different energy consumption levels. An energy-aware personalized joint time-series modeling (PJTSM) approach based on a deep recurrent neural network (RNN) and long short-term memory (LSTM) cell are proposed for accurate motion (trajectory and velocity) prediction of the leading vehicle. Finally, the differences in the prediction performance regarding different energy consumption levels are compared and discussed. It is shown that due to the higher randomness of the driving behaviors, the prediction accuracy for heavy energy users is the lowest among the three categories, which means it is harder to anticipate the driving behaviors of cars exhibiting heavy energy consumption. The personalized estimation of driving behaviors of CAVs will contribute to safer automated driving and transportation systems.

I. Introduction

Connected automated driving vehicles (CAVs) are gaining increasing attention from both areas of academia and industry. Vehicular technologies and automation are believed to be two of the cornerstones of next-generation automated driving vehicles [1], [2]. Vehicular technologies and connected vehicles enable the understanding and prediction of driving intents as well as the driving styles of surrounding vehicles [3], [4]. Moreover, vehicle energy consumption can be significantly reduced by connected and cooperative autonomous vehicles through moderate driving and platooning techniques [5], [6]. Energy consumption, driving behaviors, and motion prediction are three key aspects that can dynamically interact with each other to form the motion behavior of connected vehicles [7], [8]. It is known that different driving behaviors and driving styles can cause different levels of energy consumption [9], [10]. For instance, in [11], it was stated that the energy consumption of the vehicle could be determined by three key factors, which are driver, vehicle, and traffic context. Among these, driving behaviors and styles can influence energy consumption most significantly. Existing studies mainly focus on the study of how driving behaviors can influence vehicle energy consumption. While, how energy-aware driving behaviors influence the accuracy of the predicted vehicle motion, and how energy consumption can be connected with other driving behavior related techniques, such as the trajectory prediction still need to be exploited before CAVs can fully realize their potential in the optimization of future transportation systems.