The Electric Dial-a-Ride Problem (E-DARP) is an NP-hard optimization challenge that combines vehicle routing, passenger service, and electric vehicle charging constraints. Traditional methods often fail to scale to realistic, city-sized systems. This project proposes a deep learning–based approach, using graph neural networks and reinforcement learning to learn efficient routing and charging strategies from data. To manage the intensive computation required for large-scale training and evaluation, we will leverage cluster computing resources. The project aims to deliver scalable, sustainable solutions for future autonomous, electric mobility-on-demand services.