cs.ROSep 19, 2025

Agentic Aerial Cinematography: From Dialogue Cues to Cinematic Trajectories

Authors: Yifan Lin, Sophie Ziyu Liu, Ran Qi, George Z. Xue, Xinping Song, Chao Qin, Hugh H. -T. Liu

Organizations: Division of Engineering Science, University of Toronto · Institute for Aerospace Studies, University of Toronto

Abstract

Agents have demonstrated strong capabilities in digital environments, yet their reasoning abilities alone are insufficient to accomplish tasks in the physical world. We present Agentic Aerial Cinematography: From Dialogue Cues to Cinematic Trajectories (ACDC), an agentic framework that bridges this gap for autonomous aerial cinematography. ACDC provides an execution harness that grounds an agent's interpretation of cinematic intent and visual judgment in scene geometry and flight constraints. Given a natural-language request and a 3D scene representation, the agent selects relevant viewpoints and guides their refinement through visual feedback, while optimization and motion planning translate these decisions into executable drone trajectories. Experiments across a variety of simulated indoor scenes and hardware-in-the-loop flight tests demonstrate how this framework connects open-ended user intent to prompt-aligned video tours and physical drone execution.

Figures & tables

Explore similar work

CardsList
  1. FilmFlow: Agentic System for 3D Virtual Film Cinematography

    Oct 22, 2026Yiming Zhang, Jiarui Guo, Haojia Wei +5

  2. CinemaTraj: Composing Atomic Camera Trajectories for 3D Scenes with LLM Agents

    Jul 29, 2026Qianru Li, Xuyang Chen, Erkin Türköz +5Trajectory GenerationLLM Agent Trajectory Synthesis

  3. Camera Artist: A Multi-Agent Framework for Cinematic Language Storytelling Video Generation

    Apr 10, 2026Haobo Hu, Qi Mao, Yuanhang Li +1Agentic Video GenerationVideo Generation