Leveraging AI for Automated Code Generation from Systems Engineering Specifications Porsche AG

Format:

Book

Conference/Event

Author/Creator:

Padubrin, Marcel, author.

Contributor:

Brosi, Frank

Guerocak, Erol

Menz, Leonhard

Reuss, Hans-Christian

Conference Name:

2025 Stuttgart International Symposium (2025-07-02 : Stuttgart, Germany)

Language:

English

Physical Description:

1 online resource cm

Place of Publication:

Warrendale, PA SAE International 2025

Summary:

The increasing complexity of modern vehicles and the automotive industry's shift towards Software Defined Vehicles (SDVs) require innovative solutions to streamline development processes. Traditional methods of software development often struggle to meet the demands for agility, scalability, and precision in this context. In response, this paper presents a novel approach utilizing Artificial Intelligence (AI), specifically Large Language Models (LLMs), to automate the generation of executable code directly from Systems Engineering (SE) specifications. This novel approach aims to transform how SE requirements are converted into implementation-ready code, reducing the inefficiencies and potential errors associated with manual translation. LLMs trained on domain-specific data are capable of interpreting complex requirements, managing dependencies, and generating consistent and accurate code. By integrating LLMs into the automotive software pipeline, companies can improve productivity, shorten development cycles, and maintain high-quality standards. Deploying and fine-tuning LLMs for domain-specific tasks in the resource-constrained environments typical of the automotive industry remains a significant challenge. To address this, the paper investigates Parameter-Efficient Fine-Tuning (PEFT) techniques. These methods help reduce computational resource requirements during model adaptation while maintaining strong performance. Experimental results illustrate how PEFT techniques enable LLMs to be effectively tailored for code generation tasks within SE workflows. By combining AI-driven automation with resource-efficient fine-tuning strategies, this research outlines a practical framework to enhance software development in the automotive sector. It provides insights into integrating advanced AI technologies into real-world, resource-constrained industrial environments, supporting the industry's ability to deliver innovative and reliable SDVs

Notes:

Vendor supplied data

Publisher Number:

2025-01-0295

Access Restriction:

Restricted for use by site license