Req2Road: A GenAI Pipeline for SDV Test Artifact Generation and On-Vehicle Execution

2026-02-17

AI Summary

This work addresses the challenges in functional testing of software-defined vehicles, where natural language requirements are often ambiguous, specifications are heterogeneous, and test assets are fragmented. To overcome these issues, the paper presents the first end-to-end framework that integrates large language models (LLMs) and vision-language models (VLMs) to automatically extract signal and behavioral logic from multimodal requirements. The framework generates Gherkin-style test scenarios and translates them into executable test scripts compliant with the Vehicle Signal Specification (VSS) standard, validated in both simulation and real-vehicle environments. Retrieval-augmented generation (RAG) is employed to enhance cross-platform portability. Evaluated on a child presence detection system, the approach successfully converted 89% (32 out of 36) of requirements into executable tests, demonstrating its feasibility and effectiveness.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Language and Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Testing functionality in Software-Defined Vehicles is challenging because requirements are written in natural language, specifications combine text, tables, and diagrams, while test assets are scattered across heterogeneous toolchains. Large Language Models and Vision-Language Models are used to extract signals and behavioral logic to automatically generate Gherkin scenarios, which are then converted into runnable test scripts. The Vehicle Signal Specification (VSS) integration standardizes signal references, supporting portability across subsystems and test benches. The pipeline uses retrieval-augmented generation to preselect candidate VSS signals before mapping. We evaluate the approach on the safety-relevant Child Presence Detection System, executing the generated tests in a virtual environment and on an actual vehicle. Our evaluation covers Gherkin validity, VSS mapping quality, and end-to-end executability. Results show that 32 of 36 requirements (89\%) can be transformed into executable scenarios in our setting, while human review and targeted substitutions remain necessary. This paper is a feasibility and architectural demonstration of an end-to-end requirements-to-test pipeline for SDV subsystems, evaluated on a CPDS case in simulation and Vehicle-in-the-Loop settings.

Problem

• Software-Defined Vehicle
• requirements-to-test
• test artifact generation
• heterogeneous toolchains
• natural language requirements

Innovation

• GenAI pipeline
• Software-Defined Vehicle (SDV)
• Vehicle Signal Specification (VSS)
• Retrieval-Augmented Generation (RAG)
• Gherkin scenario generation