Automating Automotive Software Development: A Synergy of Generative AI and Model-Based Methods
Fengjunjie Pan, Yinglei Song, Long Wen, Nenad Petrovic, Krzysztof Lebioda, Alois Knoll
TL;DR
The paper addresses automating automotive software development by integrating Generative AI (LLMs) with model-based formal methods. It introduces an event-chain driven agentic workflow where requirements are transformed into event chains, platform-independent components are generated, and formal models enable early validation and model-driven integration code. A proof-of-concept using GPT-4o, CARLA, and ROS2 demonstrates an Autonomous Emergency Braking scenario, showing complementary strengths across LLMs and the value of formal methods for deterministic integration. The study highlights how formal modeling can provide reliable system validation while GenAI accelerates design and coding, with future work focusing on scalability and automated test generation.
Abstract
As the automotive industry shifts its focus toward software-defined vehicles, the need for faster and reliable software development continues to grow. However, traditional methods show their limitations. The rise of Generative Artificial Intelligence (GenAI), particularly Large Language Models (LLMs), introduces new opportunities to automate automotive software development tasks such as requirement analysis and code generation. However, due to the complexity of automotive systems, where software components must interact with each other seamlessly, challenges remain in software integration and system-level validation. In this paper, we propose to combine GenAI with model-driven engineering to automate automotive software development. Our approach uses LLMs to convert free-text requirements into event chain descriptions and to generate platform-independent software components that realize the required functionality. At the same time, formal models are created based on event chain descriptions to support system validation and the generation of integration code for integrating generated software components in the whole vehicle system through middleware. This approach increases development automation while enabling formal analysis to improve system reliability. As a proof of concept, we used GPT-4o to implement our method and tested it in the CARLA simulation environment with ROS2 middleware. We evaluated the system in a simple Autonomous Emergency Braking scenario.