This study introduces a methodology enabling automated vehicles to perform lane changes effectively within complex road systems. It emphasizes a hierarchical driver behavior framework that integrates decision-making with trajectory planning to enhance safety. The approach utilizes reinforcement learning (RL) agents for automated vehicles and the MOBIL model for human-operated vehicles, aiming to optimize the lane change process. The paper introduces the Soft Actor-Critic (SAC), an off-policy actor-critic algorithm, to improve training stability and effectiveness in real-world robotics applications. Additionally, it offers a comprehensive review of existing planning and control algorithms for self-driving vehicles, offering a comprehensive survey of techniques and their strengths and limitations to aid in informed design choices.

Self-driving vehicles are the future of technology which is having the potential to reshape mobility by improving the safety, efficiency, and accessibility of transportation system in 6G networks. Critical task like safety is a crucial factor which is included in the planning of motions of the vehicle through an environment where other vehicles and other objects are part of analysis based on feedback control. This paper mainly focuses on decision-making for autonomous driving, specifically on lane change decisions by using deep reinforcement learning (DRL) in metaverse environment. The challenges of the lane change and path planning addresses the importance of considering both longitudinal speed and lateral lane changes in self-driving vehicle scenarios. The study defines the actions for the autonomous agent like either to stay in the current lane otherwise, changing lanes to the left and right. Thus, safety and efficiency are key concerns in the decision-making process based on rewards and penalties defined to encourage safe driving behavior. The paper limits the self-driving vehicle to drive in the three right lanes of the road to ensure safety and adherence to lane regulations. The goal is to drive as fast as possible within the speed limits, avoid collisions, and minimize unnecessary lane changes in self-driving robots environment. This paper implements longitudinal speed control through rule-based methods while focusing on the lane change decision-making process using reinforcement learning algorithms. Finally, the performance evaluation is performed on Matlab and Simulink to compute the path followed by the proposed model.