Safe, Efficient, and Comfortable Autonomous Driving Based on Cooperative Vehicle Infrastructure System

Abstract

Traffic crashes, heavy congestion, and discomfort often occur on rough pavements due to human drivers’ imperfect decision-making for vehicle control. Autonomous vehicles (AVs) will flood onto urban roads to replace human drivers and improve driving performance in the near future. With the development of the cooperative vehicle infrastructure system (CVIS), multi-source road and traffic information can be collected by onboard or roadside sensors and integrated into a cloud. The information is updated and used for decision-making in real-time. This study proposes an intelligent speed control approach for AVs in CVISs using deep reinforcement learning (DRL) to improve safety, efficiency, and ride comfort. First, the irregular and fluctuating road profiles of rough pavements are represented by maximum comfortable speeds on segments via vertical comfort evaluation. A DRL-based speed control model is then designed to learn safe, efficient, and comfortable car-following behavior based on road and traffic information. Specifically, the model is trained and tested in a stochastic environment using data sampled from 1341 car-following events collected in California and 110 rough pavements detected in Shanghai. The experimental results show that the DRL-based speed control model can improve computational efficiency, driving efficiency, longitudinal comfort, and vertical comfort in cars by 93.47%, 26.99%, 58.33%, and 6.05%, respectively, compared to a model predictive control-based adaptive cruise control. The results indicate that the proposed intelligent speed control approach for AVs is effective on rough pavements and has excellent potential for practical application.

Evaluate the performance of attention DDPG-based adaptive cruise control system in all weather conditions

“…For TTC we have put 4sec, as it is considered safe. 32 The agent will be penalized if the TTC is less than that.…”

A Systematic Survey of Control Techniques and Applications in Connected and Automated Vehicles

“…In order to utilize the advantages of reinforcement learning, various researchers have trained their driving agents which have the ability to make decisions based on their own observations. For example, Chen et al propose an intelligent speed control approach using deep reinforcement learning for CAVs with the purpose of improving safety, efficiency, and ride comfort [268]. Additionally, Valiente et al propose a decentralized framework for training CAVs to operate with human-driven vehicles by formulating the mixed-autonomy problem as a multi-agent reinforcement learning (MARL) problem.…”

Data-Driven Indoor Positioning Correction for Infrastructure-Enabled Autonomous Driving Systems: A Lifelong Framework

“…This section describes how we elaborated the proposed PCS based on lifelong learning in a real underground parking garage and conducted experiments to test the system performance, for enhancing the data quality of perception and service quality of cooperative control [36], [37], [38]. The parking garage floor area exceeded 4,000 m 2 and included over 80 parking spots, as illustrated in Fig.…”