This is a page that curates AI-related papers published worldwide. All content here is summarized using Google Gemini and operated on a non-profit basis. Copyright for each paper belongs to the authors and their institutions; please make sure to credit the source when sharing.
Survey of GenAI for Automotive Software Development: From Requirements to Executable Code
Created by
Haebom
Author
Nenad Petrovic, Vahid Zolfaghari, Andre Schamschurko, Sven Kirchner, Fengjunjie Pan, Chengdng Wu, Nils Purschke, Aleksei Velsh, Krzysztof Lebioda, Yinglei Song, Yi Zhang, Lukasz Mazur, Alois Knoll
Outline
This paper explores the application of generative artificial intelligence (GenAI) to automotive software development. We explore whether GenAI can improve various steps in the complex and expensive automotive software development process, including requirements processing, compliance, and code generation. In particular, we discuss three GenAI technologies: large-scale language models (LLMs), search-augmented generation (RAGs), and vision language models (VLMs), as well as prompting techniques for code generation. Based on a literature review, we present a GenAI-based automotive software development workflow, and summarize the results of a survey of automotive industry partners.
Takeaways, Limitations
•
Takeaways:
◦
Presenting the possibility of increasing the efficiency of automotive software development using GenAI.
◦
Presenting GenAI application methods for various stages such as requirements processing, compliance, and code generation.
◦
Proposing a GenAI-based automotive software development workflow.
◦
Provides insight into the current state of GenAI adoption in the automotive industry.
•
Limitations:
◦
This study is based on a literature review and lacks verification for application to actual industrial settings.
◦
Difficulty in generalizing due to limitations in the survey subjects.
◦
Given the pace of development of GenAI technology, there is a possibility that the research results will change rapidly over time.
