Progressive Graph Convolutional Networks (PGCN) adapt to online traffic data, achieving state-of-the-art performance in traffic forecasting.
PGCN enables robust traffic forecasting by progressively adapting to online input data, achieving state-of-the-art performance.
The author proposes a framework to optimize the operations and charging infrastructure design for Electric Autonomous Mobility-on-Demand systems with ride-pooling, aiming for global optimality and efficiency.