GenAI for Automotive Software Development: From Requirements to Wheels

2025-07-24

AI Summary

To address the prolonged requirement-to-implementation cycle, high compliance verification costs, and error-prone manual coding in autonomous driving and ADAS software development, this paper proposes a generative-AI–driven end-to-end automated development framework. Methodologically, it integrates large language models (LLMs) with retrieval-augmented generation (RAG) to support Ecore modeling, automatic OCL constraint generation, semantic parsing of regulatory documents, test scenario synthesis, and Python/C++ code generation; it further introduces a model-driven requirement consistency verification mechanism to ensure regulatory compliance. Experimental evaluation demonstrates that the framework significantly reduces compliance verification and re-engineering cycles for ADAS features—by an average of 42%—while cutting development and testing time by over 35%. Moreover, it improves the accuracy and standards conformance of generated code.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Application Domains: Mobility, Driving & Flight
• Computer Vision: Generative Adversarial Networks (GANs) for Vision

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search

Abstract

This paper introduces a GenAI-empowered approach to automated development of automotive software, with emphasis on autonomous and Advanced Driver Assistance Systems (ADAS) capabilities. The process starts with requirements as input, while the main generated outputs are test scenario code for simulation environment, together with implementation of desired ADAS capabilities targeting hardware platform of the vehicle connected to testbench. Moreover, we introduce additional steps for requirements consistency checking leveraging Model-Driven Engineering (MDE). In the proposed workflow, Large Language Models (LLMs) are used for model-based summarization of requirements (Ecore metamodel, XMI model instance and OCL constraint creation), test scenario generation, simulation code (Python) and target platform code generation (C++). Additionally, Retrieval Augmented Generation (RAG) is adopted to enhance test scenario generation from autonomous driving regulations-related documents. Our approach aims shorter compliance and re-engineering cycles, as well as reduced development and testing time when it comes to ADAS-related capabilities.

Problem

• Automating automotive software development for ADAS using GenAI
• Generating test scenarios and code from requirements via LLMs
• Enhancing compliance and reducing development time with RAG

Innovation

• GenAI automates automotive software development
• LLMs generate test scenarios and code
• RAG enhances scenario generation from regulations