LLM-Empowered Event-Chain Driven Code Generation for ADAS in SDV systems
This addresses the problem of reliable code generation for automotive systems, but it appears incremental as it builds on existing LLM and RAG methods for a specific domain.
The paper tackles generating validated automotive code from natural-language requirements for Advanced Driver-Assistance Systems (ADAS) in Software-Defined Vehicle (SDV) systems, achieving valid signal usage and consistent code generation without LLM retraining in an emergency braking case study.
This paper presents an event-chain-driven, LLM-empowered workflow for generating validated, automotive code from natural-language requirements. A Retrieval-Augmented Generation (RAG) layer retrieves relevant signals from large and evolving Vehicle Signal Specification (VSS) catalogs as code generation prompt context, reducing hallucinations and ensuring architectural correctness. Retrieved signals are mapped and validated before being transformed into event chains that encode causal and timing constraints. These event chains guide and constrain LLM-based code synthesis, ensuring behavioral consistency and real-time feasibility. Based on our initial findings from the emergency braking case study, with the proposed approach, we managed to achieve valid signal usage and consistent code generation without LLM retraining.