OPRADI: Applying Security Game to Fight Drive under the Influence in Real-World

Driving under the influence (DUI) is one of main causes traffic accidents, often leading to severe life and property losses. Setting up sobriety checkpoints on certain roads most commonly used practice identify DUI-drivers in many countries worldwide. However, setting according police's experiences may not be effective for ignoring strategic interactions between police DUI-drivers, particularly when inspecting resources are limited. To remedy this situation, we adapt classic Stackelberg security game (SSG) a new SSG-DUI describe catching DUI-drivers. features drivers' bounded rationality social knowledge sharing among them, thus realizing improved real-world fidelity. With SSG-DUI, propose OPRADI, systematic approach advising better strategies checkpoints. We perform extensive experiments evaluate it both simulated environments contexts, collaborating with Chinese city's bureau. The results reveal its effectiveness improving operations, having significant practical potentials.