LATIDIA · Robótica

DriveMCP: un marco de IA agéntica para un sistema avanzado de asistencia al conductor

arXiv: 2609.17247v1Tipo de anuncio: nuevo Resumen: Un marco de asistencia al conductor de IA auténtico que integra la percepción, el razonamiento de cumplimiento, la interpretación del estado del vehículo y el arbitraje de seguridad en un marco modular y auditabl

La noticia

arXiv:2609.17247v1 Announce Type: new 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