A Path Planning Method for Electric Vehicle Based on Q-Learning

The increasing adoption of electric vehicles (EVs) has intensified the demand for efficient navigation methods to locate charging stations, optimizing both user convenience and energy utilization. This paper proposes a Q-learning-based path planning approach that dynamically identifies optimal routes for EVs while considering real-world constraints such as traffic and charging station availability. The proposed model integrates grid-based environmental modeling with reinforcement learning to achieve robust and adaptive path optimization. Experimental results, conducted on simulated urban environments derived from real-world data, demonstrate the algorithm’s ability to effectively navigate diverse scenarios, minimizing travel distance and avoiding obstacles. The findings highlight the potential of this approach to enhance EV navigation systems and lay a foundation for future research in high-complexity transportation networks.