GenAI for Automotive Software Development: From Requirements to Wheels

TL;DR

This paper presents a GenAI-driven workflow for automotive software development that automates requirements processing, test scenario creation, and code generation for ADAS, improving efficiency and compliance in vehicle software engineering.

Contribution

It introduces a novel GenAI-based approach integrating Model-Driven Engineering and Retrieval Augmented Generation for automating automotive software development tasks.

Findings

Reduced development and testing time for ADAS features

Enhanced requirements consistency checking using MDE

Effective test scenario generation from regulations

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.