Lane merging in autonomous vehicle urban driving using reinforcement learning models

Abstract

Autonomous vehicle lane merging is a critical task in urban driving, requiring precise navigation through complex and dynamic traffic environments. Challenges such as roadworks, lane reductions, merging from gas stations, low-visibility conditions, and crowded highway on-ramps demand continuous improvements in autonomous driving systems. Effective navigation in these situations, particularly at multi-lane junctions, merging onto high-speed roads, avoiding obstacles, and managing emergency vehicle lanes, requires robust decision-making that can adapt to changing road conditions. This paper compares three popular reinforcement learning (RL) algorithms—Proximal Policy Optimization (PPO), Advantage Actor-Critic (A2C), and Deep Q-Learning (DQL)—to address these challenges. Our findings show that in environments with specific decision points, DQL excels in tasks like lane reduction and obstacle avoidance due to its value-based approach. The A2C model, as an actor-critic policy, is particularly effective in dynamic environments, enabling the optimization of urban traffic control and merging at roundabouts. PPO, known for its policy optimization capabilities, offers a robust solution by balancing safety, efficiency, and adaptability, particularly in complex situations such as high-speed merging and low-visibility conditions. The simulation results confirm that DQL, A2C, and PPO collectively enhance autonomous vehicle performance by improving navigation capabilities, increasing safety, and adapting more effectively to the complexities of urban traffic environments. This work contributes valuable insights into the application of RL for real-world autonomous driving, providing a detailed comparative evaluation that supports the selection of algorithms tailored to specific driving tasks.