TrajAware road networks and trajectories

The VANET-RL Trajectory Dataset is a collection of vehicular mobility traces generated using the Simulation of Urban MObility (SUMO) traffic simulator. The dataset is organized into six folders, each corresponding to a different urban scenario created with SUMO\u2019s built-in OSMWebWizard. Within each folder, the files include the road network map and detailed vehicle trajectories for all simulated agents.The dataset is designed to support research in vehicular ad-hoc networks (VANETs) and intelligent transportation systems. It has been used to train a deep reinforcement learning (DRL) model for routing decisions and a gated recurrent unit (GRU) model for trajectory prediction. While the dataset itself does not directly include communication connection states, connectivity can be inferred using a fixed communication range of 800 meters: two agents are considered connected if the Euclidean distance between them is below this threshold. Researchers can directly load the maps and trajectory files into SUMO for further simulation or extension.