Desenvolvimento de software e design automotivo de ponta a ponta para SDVs / AI-Based End-to-End Automotive Design and Software Development for SDVs (2026) (Portuguese)

Este artigo explora o potencial da Inteligência Artificial (AI) para permitir o design automóvel e o desenvolvimento de software para veículos definidos por software (SDVs) de ponta a ponta. Com base nas nossas contribuições dentro do Central Car Server (CeCaS) e projetos financiados pela UE de seguimento, apresentamos uma cadeia de ferramentas orientada por IA que integra Grandes Modelos de Línguas (LLMs) com Engenharia de Modelos (MDE) para automatizar a transformação de requisitos de linguagem natural em arquiteturas de sistema, software executável e artefatos de validação. A abordagem enfatiza a rastreabilidade, a consistência e a conformidade com os requisitos de desenvolvimento automotivo críticos de segurança. A validação é realizada em uma plataforma de computação centralizada de veículos que suporta controle de cruze

Abstract

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.

Topics: Engineering, Software, Computer science, Automotive industry, Software development, Systems engineering

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: 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.txt