智能体航拍：从对话提示到电影级轨迹
Agentic Aerial Cinematography: From Dialogue Cues to Cinematic Trajectories
AI总结：
本文提出ACDC系统，利用大语言模型与视觉基础模型将自然语言对话直接转化为室内无人机电影级拍摄轨迹，并通过视觉-语言检索、基于偏好的贝叶斯优化和运动规划实现无需专业知识的自主航拍。
摘要：
我们提出智能体航拍系统ACDC（Agentic Aerial Cinematography: From Dialogue Cues to Cinematic Trajectories），这是一个由人类导演与无人机之间的自然语言交流驱动的自主无人机摄影系统。以往无人机摄影工作流的主要局限在于，它们需要基于预定义的人类意图手动选择航路点和视角，这既耗费人力又导致性能不一致。在本文中，我们提出采用大语言模型（LLMs）和视觉基础模型（VFMs），将自由形式的自然语言提示直接转换为可执行的室内无人机视频导览。具体而言，我们的方法包括：一个用于初始航路点选择的视觉-语言检索流程，一个利用美学反馈来优化位姿的基于偏好的贝叶斯优化框架，以及一个生成安全四旋翼轨迹的运动规划器。我们通过仿真和硬件在环实验验证了ACDC，证明它能够在多样的室内场景中稳健地生成专业质量的画面，而无需机器人学或摄影方面的专业知识。这些结果凸显了具身AI智能体在从开放词汇对话到真实世界自主航拍的闭环中的潜力。
英文摘要：
We present Agentic Aerial Cinematography: From Dialogue Cues to Cinematic Trajectories (ACDC), an autonomous drone cinematography system driven by natural language communication between human directors and drones. The main limitation of previous drone cinematography workflows is that they require manual selection of waypoints and view angles based on predefined human intent, which is labor-intensive and yields inconsistent performance. In this paper, we propose employing large language models (LLMs) and vision foundation models (VFMs) to convert free-form natural language prompts directly into executable indoor UAV video tours. Specifically, our method comprises a vision-language retrieval pipeline for initial waypoint selection, a preference-based Bayesian optimization framework that refines poses using aesthetic feedback, and a motion planner that generates safe quadrotor trajectories. We validate ACDC through both simulation and hardware-in-the-loop experiments, demonstrating that it robustly produces professional-quality footage across diverse indoor scenes without requiring expertise in robotics or cinematography. These results highlight the potential of embodied AI agents to close the loop from open-vocabulary dialogue to real-world autonomous aerial cinematography.
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。
