Merging and Diverging Impact on Mixed Traffic of Regular and Autonomous Vehicles

In the context of Connected and Autonomous Vehicles (CAVs), this paper aims to examine the impacts of CAVs on mixed regular-automated traffic flow with the increase of the market penetration rate, in consideration of on-ramp merging and off-ramp diverging of vehicles. Lane changes are a major part of lateral motions, affecting surrounding vehicles locally and traffic flow collectively. On the basis of reinforcement learning technique, a cooperative lane-changing strategy was first developed to enable farsighted lane-changing behavior by CAVs in favor of traffic efficiency. The 3-lane highway stretch with one on-ramp and one off-ramp was applied in this study. With extensive simulations, the results suggest that the inclusion of CAVs considerably improves traffic flow, mean speed, and traffic capacity. Meanwhile, the existence of on/off-ramps has substantial impacts on the lane-changing processes. This work can shed some light on an aspect of the mixed traffic network dynamics for future mobility.

Automated summary

This paper examines the impacts of Connected and Autonomous Vehicles (CAVs) on mixed regular-automated traffic flow, introducing a cooperative lane-changing strategy to improve traffic efficiency. Results suggest that CAVs considerably enhance traffic flow, mean speed, and traffic capacity, while the presence of on/off-ramps significantly affects lane-changing processes.