Survey of GenAI for Automotive Software Development: From Requirements to Executable Code

2025-07-20

AI Summary

To address high manual dependency, cumbersome compliance verification, and low code-generation efficiency in automotive software development, this paper proposes the first generative AI (GenAI) application framework spanning the entire software lifecycle. Methodologically, it integrates large language models (LLMs), retrieval-augmented generation (RAG), vision-language models (VLMs), and structured prompt engineering to enable intelligent requirements parsing, automated functional safety/ASPICE compliance checking, and executable code generation. Key contributions include: (1) a standardized, extensible GenAI-augmented development workflow; (2) an industry survey validating current tooling practices and adoption gaps; and (3) the first empirically validated technical pathway covering the end-to-end闭环 from requirements specification → compliance validation → code generation. The framework provides theoretical foundations and industrial implementation guidance for efficient, trustworthy, and regulation-compliant AI-assisted development of automotive-grade software.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Adoption of state-of-art Generative Artificial Intelligence (GenAI) aims to revolutionize many industrial areas by reducing the amount of human intervention needed and effort for handling complex underlying processes. Automotive software development is considered to be a significant area for GenAI adoption, taking into account lengthy and expensive procedures, resulting from the amount of requirements and strict standardization. In this paper, we explore the adoption of GenAI for various steps of automotive software development, mainly focusing on requirements handling, compliance aspects and code generation. Three GenAI-related technologies are covered within the state-of-art: Large Language Models (LLMs), Retrieval Augmented Generation (RAG), Vision Language Models (VLMs), as well as overview of adopted prompting techniques in case of code generation. Additionally, we also derive a generalized GenAI-aided automotive software development workflow based on our findings from this literature review. Finally, we include a summary of a survey outcome, which was conducted among our automotive industry partners regarding the type of GenAI tools used for their daily work activities.

Problem

• Exploring GenAI adoption in automotive software development
• Focusing on requirements handling, compliance, and code generation
• Surveying GenAI tools used in automotive industry workflows

Innovation

• Uses LLMs for requirements and compliance
• Applies RAG for enhanced code generation
• Integrates VLMs for visual data processing