Proactive Longitudinal Control to Assist Lane Changes of Human-Driven Vehicles in Mixed Traffic: Human-Emulation Approach

In the era of connected and autonomous vehicles (CAVs), the coexistence of CAVs and human-driven vehicles (HDVs) in mixed traffic presents key challenges to CAV operations. The dynamics of HDV lane changes in proximity to CAV platoons can induce traffic oscillations and disrupt the CAV platoon performance. To address this issue, this study introduces an innovative human-emulation-based proactive longitudinal control (HPC) strategy for CAVs, to assist HDV lane changes and counteract their negative effects on CAV platoon smoothness. It constructs a Transformer-based behavior predictor to predict the HDV lane change behavior. If a lane change is anticipated, a lane-change assistance model is developed using the proximal policy optimization, which enables the CAV to emulate the lane-change assistance maneuver of human drivers. If no lane change by the HDV is anticipated, a multi-anticipative car-following model is adopted, through which the CAV executes cooperative platooning control. Driving simulator experiments involving 36 participants illustrate that the HPC strategy can enhance traffic smoothness (e.g., an 84.3% reduction in speed perturbation) and facilitate smooth lane changes by HDV drivers with enhanced safety (e.g., a 32.6% increase in time-to-collision) and improved mental comfort (e.g., a 13.9% decrease in self-reported workload). Numerical experiments further demonstrate that the HPC is effective in assisting HDV lane changes and enhancing CAV platoon smoothness (e.g., a 19.1% reduction in speed perturbation) across different lane-change scenarios, HDV driver types, and CAV control setups.