Chat2Scenic：一種基於迭代式RAG的自動駕駛場景生成框架

摘要

驗證自動駕駛系統需要多樣化且符合法規的測試場景。在基於模擬的測試中，場景被定義為可執行的腳本。然而，從法規描述中自動生成此類腳本仍是一項開放性挑戰，現有方法面臨根本性的權衡取捨。檢索-組裝方法可達到合理的編譯率，但缺乏可擴展性；而基於檢索的完整腳本生成則遭遇編譯成功率低的問題。我們提出Chat2Scenic，首個用於生成領域特定語言（DSL）場景腳本的迭代式檢索增強框架。具體而言，Chat2Scenic提供了一個支援互動式場景優化的聊天機器人介面，並整合了檢索增強生成（RAG），將場景生成建立在法規知識與DSL語法的基礎上。此外，我們提出了一個開放的場景生成基準測試，包含來自美國國家公路交通安全管理局（NHTSA）、聯合國車輛法規及其他來源的123個場景。與最先進（SOTA）大型語言模型（LLM）的廣泛評估顯示，Chat2Scenic實現了76.42%的編譯成功率（CSR）與58.17%的框架準確率（FA），優於現有方法（檢索-組裝：30.08% CSR、11.03% FA；檢索完整腳本生成：16.26% CSR、10.86% FA）。為促進未來研究，我們在https://github.com/TUM-AVS/chat2scenic開源了程式碼。

English

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.