Cooperative adaptive cruise control with vehicle trajectory prediction using machine learning techniques

点击翻译按钮获取中文摘要

The number of vehicles on roads and highways has soared in recent years and we are witnessing more traffic congestion and vehicle accidents on streets. To address these issues, car manufacturers have been developing advanced driver assistance systems (ADAS). This research proposal aims to improve adaptive cruise control (ACC) system performance by using vehicular communication and machine learning techniques. ACC relies on onboard sensors to adjust a vehicle's speed with the speed of the preceding vehicle. Since ACC performance is restricted by its sensing range, cooperative adaptive cruise control (CACC) has emerged to supplant on-board sensors with vehicular communication to exchange information between the vehicles. The main objective of this research proposal is to leverage machine learning techniques to predict vehicles trajectories in CACC. We will use the long short term memory (LSTM) deep model to predict the position of target vehicles at future time steps. This research proposal will have several benefits. Firstly, it contributes to traffic safety because the proposed system will be able to predict a collision situation and warn the driver in advance. Furthermore, our system has the potential to increase highway capacity. This is mainly because in the proposed CACC, a constant time headway gap policy will be deployed. That is to say, the distance between the following vehicles will be proportional to their speed; the higher the speed, the larger the distance. The third impact of our CACC is reducing fuel consumption because of vehicles' constant speed and less air resistance when following each other. Finally, through this international research collaboration, the University of Windsor in Canada and Leeds University in the UK can share their infrastructure, experiences, data, and methods in the field of fully automated vehicles. It can create a unique opportunity to train HQPs in the emerging fields of vehicular communication and deep learning, and exchange students and researchers in the future. HQPs will expand their network by meeting potential future collaborators, learn new skills, and gain a new perspective.