N. Petrovic, A. C. Knoll · 2026 · Verein Deutscher Ingenieure e.V. eBooks
DOI: 10.51202/9783181024751-39 · cited by 0 works (OpenAlex) · open-access PDF
Este artículo explora el potencial de la Inteligencia Artificial (AI) para permitir el diseño y el desarrollo de software para vehículos definidos por software (SDV) de extremo a extremo. Basado en nuestras contribuciones dentro del servidor central de vehículos (CeCaS) y los proyectos de seguimiento financiados por la UE, presentamos una cadena de herramientas impulsada por la IA que integra los modelos de idiomas grandes (LLM) con la ingeniería de modelos (MDE) para automatizar la transformación de los requisitos de lengua natural en arquitecturas de sistemas, software ejecutable y artefactos de validación. El enfoque enfatiza la trazabilidad, la coherencia y la conformidad con los requisitos de desarrollo de automóviles críticos para la seguridad. La validación se lleva a cabo en una plataforma de computación centralizada de vehículos que soporta el control de
Machine translation (Meta M2M100); the English original follows.
This paper explores the potential of Artificial Intelligence (AI) to enable end-to-end automotive design and software development for Software-Defined Vehicles (SDVs). Based on our contributions within the Central Car Server (CeCaS) and follow-up EU-funded projects, we present an AI-driven toolchain integrating Large Language Models (LLMs) with Model-Driven Engineering (MDE) to automate the transformation of natural-language requirements into system architectures, executable software, and validation artifacts. The approach emphasizes traceability, consistency, and compliance with safety-critical automotive development requirements. Validation is performed on a centralized vehicle computing platform supporting adaptive cruise control and emergency braking, tested in Hardware-in-the-Loop (HiL) and Software-in-the-Loop (SiL) environments. We discuss current capabilities, practical limitations, and future directions toward increasingly automated, reliable, and quality-assured automotive software development with minimal human intervention.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Engineering, Software, Computer science, Automotive industry, Software development, Systems engineering
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.29160, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange