This research introduces a Retrieval-Augmented Reasoning framework that enables autonomous vehicles to make interpretable decisions using traffic regulations.

• Develops a Traffic Regulation Retrieval Agent that automatically accesses relevant rules from comprehensive regulatory databases
• Creates interpretable decision justifications by connecting vehicle actions to specific traffic regulations
• Enables regional adaptation of autonomous systems to different traffic laws without reprogramming
• Demonstrates superior performance compared to traditional rule-based systems

This engineering breakthrough addresses a critical challenge in autonomous vehicle deployment: creating systems that can demonstrably follow traffic laws while adapting to different regulatory environments - essential for scalable, trustworthy autonomous transportation.

Driving with Regulation: Interpretable Decision-Making for Autonomous Vehicles with Retrieval-Augmented Reasoning via LLM