EnduRL: Enhancing Safety, Stability, and Efficiency of Mixed Traffic Under Real-World Perturbations Via Reinforcement Learning
This work addresses traffic congestion and safety issues for road users by enhancing robot vehicle controllers, though it is incremental as it builds on existing reinforcement learning methods with new data integration.
The paper tackled the problem of congestion in mixed traffic with human-driven and robot vehicles by training robot vehicles using real-world acceleration profiles, resulting in improvements of up to 66% in safety, 54% in efficiency, and 97% in stability compared to prior controllers.
Human-driven vehicles (HVs) amplify naturally occurring perturbations in traffic, leading to congestion--a major contributor to increased fuel consumption, higher collision risks, and reduced road capacity utilization. While previous research demonstrates that Robot Vehicles (RVs) can be leveraged to mitigate these issues, most such studies rely on simulations with simplistic models of human car-following behaviors. In this work, we analyze real-world driving trajectories and extract a wide range of acceleration profiles. We then incorporates these profiles into simulations for training RVs to mitigate congestion. We evaluate the safety, efficiency, and stability of mixed traffic via comprehensive experiments conducted in two mixed traffic environments (Ring and Bottleneck) at various traffic densities, configurations, and RV penetration rates. The results show that under real-world perturbations, prior RV controllers experience performance degradation on all three objectives (sometimes even lower than 100% HVs). To address this, we introduce a reinforcement learning based RV that employs a congestion stage classifier to optimize the safety, efficiency, and stability of mixed traffic. Our RVs demonstrate significant improvements: safety by up to 66%, efficiency by up to 54%, and stability by up to 97%.