A warning system for warning vulnerable road users (VRUs) includes an edge computing device having a graphics processing unit (GPU), one or more sensors that acquire spatial-temporal data of road users, and one or more warning devices that output a warning to warn targeted VRUs of danger. The GPU uses one or more artificial intelligence (AI) algorithms to process the spatial-temporal data of the road users to predict a path, trajectory, behavior, and intent for the road users. The GPU then analyzes the predictions of the road users to determine convergences between the predictions to determine threat interactions and identify targeted VRUs. In response to determining threat interactions and identifying the targeted VRUs, the edge computing device outputs targeting instructions and warning response instructions to the one or more warning devices to deploy the one or more warning devices to warn the targeted VRUs.