AI automates automotive software design and testing for safe vehicles
AI-Based End-to-End Automotive Design and Software Development for SDVs
Software EngineeringArtificial Intelligence
Summary
Designing software for modern cars is complicated and must be very safe. The authors show how artificial intelligence can help turn simple descriptions of what a car should do into actual software and tests automatically. They tested their AI-based system on car features like cruise control and emergency braking using realistic simulations. The paper explains what the AI can do now, what limits remain, and ideas for future automation in car software development.
What this means in practice
- •For automotive software developers: Automatically generate vehicle software and tests from natural-language requirements to speed up development while ensuring safety compliance.
- •For automotive testing teams: Use AI-generated validation scenarios in hardware-in-the-loop and software-in-the-loop setups for comprehensive vehicle feature testing.
Authors
Nenad Petrovic, Alois Knoll
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.