DriveMCP integrates AI to improve driver assistance systems safety
DriveMCP: An Agentic AI framework for Advanced Driver Assistance System
Robotics
Summary
Driver assistance systems help make driving safer but often lack deep understanding and reasoning about road rules and conditions. The authors present DriveMCP, a framework that uses AI to combine vision, traffic rules knowledge, weather conditions, and vehicle diagnostics into a clear decision-making process. This system can ask and answer questions about the driving scene, interpret local laws from visual cues, and decide the safest action to take. When tested in a driving simulator, DriveMCP showed better safety outcomes and quicker hazard responses than some existing AI methods.
What this means in practice
- •For automotive software developers: Build advanced driver assistance tools that integrate AI reasoning about traffic laws, weather, and vehicle state for safer driving decisions.
- •For fleet safety managers: Monitor and enhance vehicle compliance with local traffic regulations and environmental conditions by deploying AI-informed advisory and safety systems.
Authors
Farzad Nadiri, Mehdi Cina, Ahmad B. Rad
Abstract
An agentic AI driver-assistance framework that integrates perception, compliance reasoning, vehicle-state interpretation, and safety arbitration into a modular and auditable pipeline. The architecture, referred to as DriveMCP, incorporates a sensor-like perception stack alongside DriveLM as the vision-language front end to generate a graph-structured scene understanding (Graph Visual Question Answering) and language-grounded driving information. Key compliance elements in world_state, including posted speed limits and jurisdiction cues, are derived from DriveLM outputs through a structured parsing layer rather than being injected as simulator ground truth. A stateful orchestration layer coordinates specialized experts exposed as Model Context Protocol (MCP) servers: (i) a Rules server that performs retrieval-augmented compliance reasoning over jurisdiction-specific traffic codes and sign conventions, (ii) a Weather server that estimates traction risk and contextual speed advisories, and (iii) an MCP-CAN server that surfaces Controller Area Network (CAN)/On-Board Diagnostics (OBD) telemetry and diagnostic context for health-aware risk shaping. These outputs are fused to generate a structured decision that prompts a recommended course of action. The outcome is then further filtered by a Responsibility-Sensitive Safety (RSS)-inspired guardrail that arbitrates speak versus act decisions under bounded online adaptation. In CARLA simulation across multilingual, cross-border, and dynamic speed-limit scenarios, DriveMCP reduces traffic infractions and overspeed relative to the VLM-Direct, VLM-Direct+RAG, and VLM-Tools-NoArbiter baselines, while improving hazard response time and maintaining sub-second advisory latency.