发表机构
Technical University of Munich; Munich Institute of Robotics and Machine Intelligence (MIRMI); University College London（慕尼黑工业大学; 慕尼黑机器人与机器智能研究所; 伦敦大学学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究自动驾驶场景生成难题，提出Chat2Scenic这一基于迭代检索增强生成的框架，通过聊天机器人界面及RAG技术生成DSL场景脚本，构建开放基准，评估结果显示其性能优于现有方法。
AI 中文摘要
验证自动驾驶系统需要多样且符合法规的测试场景。在基于模拟的测试中，场景被定义为可执行脚本。然而，从法规描述中自动生成此类脚本仍是一个开放挑战，现有方法面临基本权衡。我们提出Chat2Scenic，首个用于生成特定领域语言（DSL）场景脚本的迭代检索增强框架。它提供支持交互式场景细化的聊天机器人界面，并集成检索增强生成（RAG）。还提出一个包含123个来自各种法规场景的开放基准。评估显示Chat2Scenic编译成功率达76.42%，框架准确率达58.17%，优于现有方法。
英文摘要
Validating autonomous driving systems requires diverse, regulation-compliant test scenarios. In simulation-based testing, scenarios are defined as executable scripts. Yet automatically generating such scripts from regulatory descriptions remains an open challenge, and existing approaches face fundamental trade-offs. Retrieval-assemble methods achieve reasonable compilation rates but lack scalability, whereas retrieval-based full-script generation suffers from low compilation success rates. We present Chat2Scenic, the first iterative retrieval-augmented framework to generate scenario scripts in Domain Specific Language (DSL). Specifically, Chat2Scenic provides a chatbot interface that supports interactive scenario refinement and integrates Retrieval-augmented Generation (RAG) to ground scenario generation in regulatory knowledge and DSL syntax. Furthermore, we propose an open benchmark for scenario generation comprising 123 scenarios from various regulations, including NHTSA and United Nations Vehicle Regulations, as well as other sources. Extensive evaluation with State-of-the-Art (SOTA) Large Language Models (LLMs) demonstrates that Chat2Scenic achieves 76.42% Compilation Success Rate (CSR) and 58.17% Framework Accuracy (FA), outperforming existing methods (Retrieval Assemble with 30.08% CSR, 11.03% FA and Retrieval full script generation with 16.26% CSR, 10.86% FA). To facilitate future research, we release our code as open source at https://github.com/TUM-AVS/chat2scenic.
CommentsAccepted at 2026 IEEE International Conference on Intelligent Robots and Systems (IROS)
