GenAI for Automotive Software Development: From Requirements to Wheels
This addresses the need for faster compliance and re-engineering cycles in automotive software development, particularly for ADAS capabilities, though it appears incremental as it builds on existing LLM and RAG techniques.
This paper tackles the problem of automating automotive software development for autonomous and ADAS systems by introducing a GenAI-empowered workflow that generates test scenario code, simulation code, and target platform code from requirements, aiming to reduce development and testing time.
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.