Towards Single-System Illusion in Software-Defined Vehicles -- Automated, AI-Powered Workflow
This addresses the challenge of complex software development for software-defined vehicles, offering an incremental approach to automate and streamline the process.
The paper tackles the problem of developing vehicle software systems without explicitly defining the end architecture, proposing an automated workflow where the architecture emerges from iterative search and optimization while maintaining a single-system illusion. The result is a pipeline that largely automates development by incorporating Large Language Models (LLMs) to assist in requirements processing, model generation, and test code creation.
We propose a novel model- and feature-based approach to development of vehicle software systems, where the end architecture is not explicitly defined. Instead, it emerges from an iterative process of search and optimization given certain constraints, requirements and hardware architecture, while retaining the property of single-system illusion, where applications run in a logically uniform environment. One of the key points of the presented approach is the inclusion of modern generative AI, specifically Large Language Models (LLMs), in the loop. With the recent advances in the field, we expect that the LLMs will be able to assist in processing of requirements, generation of formal system models, as well as generation of software deployment specification and test code. The resulting pipeline is automated to a large extent, with feedback being generated at each step.