用大模型动态生成自动驾驶行为树，遇突发障碍自动避让
From Prompts to Pavement: LMMs-based Agentic Behavior-Tree Generation Framework for Autonomous Vehicles
- 用大模型和多模态模型实时生成可执行的行为树
- 在CARLA仿真中成功避开街道堵塞等意外障碍
- 适合研究自动驾驶动态决策与智能体框架的开发者
自动驾驶车辆需在不可预测的真实环境中安全导航。传统行为树（BTs）虽具结构化决策逻辑，但固有静态且需大量人工调参，难以满足SAE Level 5 自动化需求。本文提出一种基于大语言模型（LLMs）和多模态视觉模型（LVMs）的智能体框架，可实时生成与适应行为树。专用描述代理通过符号链提示评估场景关键性，规划代理利用上下文学习构建高层子目标，生成代理则以XML格式合成可执行的子树。该系统集成于CARLA+Nav2仿真环境，仅在基础行为树失效时触发，成功实现对突发障碍（如街道阻塞）的自主绕行，无需人工干预。相较静态行为树基线，本方法验证了在多种驾驶场景下的可行性。
原文摘要 · Abstract (English)
Autonomous vehicles (AVs) require adaptive behavior planners to navigate unpredictable, real-world environments safely. Traditional behavior trees (BTs) offer structured decision logic but are inherently static and demand labor-intensive manual tuning, limiting their applicability at SAE Level 5 autonomy. This paper presents an agentic framework that leverages large language models (LLMs) and multi-modal vision models (LVMs) to generate and adapt BTs on the fly. A specialized Descriptor agent applies chain-of-symbols prompting to assess scene criticality, a Planner agent constructs high-level sub-goals via in-context learning, and a Generator agent synthesizes executable BT sub-trees in XML format. Integrated into a CARLA+Nav2 simulation, our system triggers only upon baseline BT failure, demonstrating successful navigation around unexpected obstacles (e.g., street blockage) with no human intervention. Compared to a static BT baseline, this approach is a proof-of-concept that extends to diverse driving scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。