ManeuverGPT 代理控制用于安全的自动驾驶特技动作
ManeuverGPT Agentic Control for Safe Autonomous Stunt Maneuvers
AI总结：
本文提出ManeuverGPT框架，利用大语言模型代理生成并执行高动态特技动作，通过迭代提示法优化车辆控制参数，实现安全的J-turn等特技动作执行。
摘要：
下一代自动驾驶车辆主动安全功能应能安全执行类似专业特技驾驶员的避险动作，以实现车辆极限操控下的高敏捷运动。本文提出ManeuverGPT框架，利用大语言模型（LLM）代理作为控制器，生成并执行高动态特技动作。我们针对CARLA仿真环境中的激进动作（如J-turns）进行实验，展示一种基于提示的迭代方法，从零开始优化车辆控制参数，无需重新训练模型权重。我们提出由三个专用代理组成的架构：（1）查询丰富代理用于上下文化用户指令，（2）驾驶员代理生成动作参数，（3）参数验证代理强制执行物理和安全约束。实验结果表明，通过文本提示在多种车辆模型上成功执行J-turn动作。我们通过已建立的成功标准评估性能，并讨论数值精度和场景复杂性方面的限制。我们的发现强调了LLM驱动控制在灵活高动态动作中的潜力，同时突显了结合语言推理与算法验证的混合方法的重要性。
英文摘要：
The next generation of active safety features in autonomous vehicles should be capable of safely executing evasive hazard-avoidance maneuvers akin to those performed by professional stunt drivers to achieve high-agility motion at the limits of vehicle handling. This paper presents a novel framework, ManeuverGPT, for generating and executing high-dynamic stunt maneuvers in autonomous vehicles using large language model (LLM)-based agents as controllers. We target aggressive maneuvers, such as J-turns, within the CARLA simulation environment and demonstrate an iterative, prompt-based approach to refine vehicle control parameters, starting tabula rasa without retraining model weights. We propose an agentic architecture comprised of three specialized agents (1) a Query Enricher Agent for contextualizing user commands, (2) a Driver Agent for generating maneuver parameters, and (3) a Parameter Validator Agent that enforces physics-based and safety constraints. Experimental results demonstrate successful J-turn execution across multiple vehicle models through textual prompts that adapt to differing vehicle dynamics. We evaluate performance via established success criteria and discuss limitations regarding numeric precision and scenario complexity. Our findings underscore the potential of LLM-driven control for flexible, high-dynamic maneuvers, while highlighting the importance of hybrid approaches that combine language-based reasoning with algorithmic validation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
