# Can a Robot Become a Movie Director? Learning Artistic Principles for Aerial Cinematography

arXiv: https://arxiv.org/abs/1904.02579 · HTML: https://mlsanity.com/paper/1904.02579/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Apr 2019.

## Built on by (most cited first, 10 of 10)

- [Dynamic Storyboard Generation in an Engine-based Virtual Environment for Video Production](https://mlsanity.com/paper/2301.12688/) (2023)
- [DanceCamera3D: 3D Camera Movement Synthesis with Music and Dance](https://mlsanity.com/paper/2403.13667/) (2024)
- [A Reinforcement Learning-Based Automatic Video Editing Method Using Pre-trained Vision-Language Model](https://mlsanity.com/paper/2411.04942/) (2024)
- [AutoPhoto: Aesthetic Photo Capture using Reinforcement Learning](https://mlsanity.com/paper/2109.09923/) (2021)
- [3D Human Reconstruction in the Wild with Collaborative Aerial Cameras](https://mlsanity.com/paper/2108.03936/) (2021)
- [DanceCamAnimator: Keyframe-Based Controllable 3D Dance Camera Synthesis](https://mlsanity.com/paper/2409.14925/) (2024)
- [VERTIGO: Visual Preference Optimization for Cinematic Camera Trajectory Generation](https://mlsanity.com/paper/2604.02467/) (2026)
- [Agentic Aerial Cinematography: From Dialogue Cues to Cinematic Trajectories](https://mlsanity.com/paper/2509.16176/) (2025)
- [Automatic Camera Trajectory Control with Enhanced Immersion for Virtual Cinematography](https://mlsanity.com/paper/2303.17041/) (2023)
- [Reinforcement Learning of Dolly-In Filming Using a Ground-Based Robot](https://mlsanity.com/paper/2509.00564/) (2025)

## Abstract (arXiv)

Aerial filming is constantly gaining importance due to the recent advances in drone technology. It invites many intriguing, unsolved problems at the intersection of aesthetical and scientific challenges. In this work, we propose a deep reinforcement learning agent which supervises motion planning of a filming drone by making desirable shot mode selections based on aesthetical values of video shots. Unlike most of the current state-of-the-art approaches that require explicit guidance by a human expert, our drone learns how to make favorable viewpoint selections by experience. We propose a learning scheme that exploits aesthetical features of retrospective shots in order to extract a desirable policy for better prospective shots. We train our agent in realistic AirSim simulations using both a hand-crafted reward function as well as reward from direct human input. We then deploy the same agent on a real DJI M210 drone in order to test the generalization capability of our approach to real world conditions. To evaluate the success of our approach in the end, we conduct a comprehensive user study in which participants rate the shot quality of our methods. Videos of the system in action can be seen at https://youtu.be/qmVw6mfyEmw.