Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Automated Cinematography Motion Planning for UAVs

Animesh Nema, Christopher Grontkowski, Derek Calzada, Sanjuksha Nirgude

TL;DR

This project aims to design an algorithm to enable automated cinematography of a desired object of interest to take advantage of the quadcopter's abilities while creating motion paths which satisfy the ultimate goal of capturing aerial video.

Abstract

This project aimed to develop an automated cinematography platform using an unmanned aerial vehicle. Quadcopters are a great platform for shooting aerial scenes but are difficult to maneuver smoothly and can require expertise to pilot. We aim to design an algorithm to enable automated cinematography of a desired object of interest. Given the location of an object and other obstacles in the environment, the drone is able to plan its trajectory while simultaneously keeping the desired object in the video frame and avoiding obstacles. The high maneuverability of quadcopter platforms coupled with the desire for smooth movement and stability from camera platforms means a robust motion planning algorithm must be developed which can take advantage of the quadcopter's abilities while creating motion paths which satisfy the ultimate goal of capturing aerial video. This project aims to research, develop, simulate, and test such an algorithm.

Automated Cinematography Motion Planning for UAVs

TL;DR

This project aims to design an algorithm to enable automated cinematography of a desired object of interest to take advantage of the quadcopter's abilities while creating motion paths which satisfy the ultimate goal of capturing aerial video.

Abstract

This project aimed to develop an automated cinematography platform using an unmanned aerial vehicle. Quadcopters are a great platform for shooting aerial scenes but are difficult to maneuver smoothly and can require expertise to pilot. We aim to design an algorithm to enable automated cinematography of a desired object of interest. Given the location of an object and other obstacles in the environment, the drone is able to plan its trajectory while simultaneously keeping the desired object in the video frame and avoiding obstacles. The high maneuverability of quadcopter platforms coupled with the desire for smooth movement and stability from camera platforms means a robust motion planning algorithm must be developed which can take advantage of the quadcopter's abilities while creating motion paths which satisfy the ultimate goal of capturing aerial video. This project aims to research, develop, simulate, and test such an algorithm.
Paper Structure (21 sections, 6 figures, 2 algorithms)

This paper contains 21 sections, 6 figures, 2 algorithms.

Table of Contents

  1. INTRODUCTION
  2. PROBLEM STATEMENT
  3. LITERATURE REVIEW
  4. Automated Cinematography with Unmanned Aerial Vehicles
  5. Towards a Drone Cinematographer
  6. Real-time Planning for Automated Multi-View Drone Cinematography
  7. Real-Time Motion Planning for Aerial Videography with Dynamic Obstacle Avoidance and Viewpoint Optimization
  8. Follow Moving Things in Virtual World
  9. An interactive tool for designing quadrotor camera shots
  10. Steering Behaviors for Autonomous Cameras
  11. Intelligent Bidirectional Rapidly-exploring Random Trees
  12. Methodology
  13. The Gazebo Environment and World Data
  14. Global Path Generator
  15. RRT* Local Path Planner
  16. ...and 6 more sections

Figures (6)

  • Figure 1: DJI Phantom 4 quadcopter with a forward-facing, gimbal-stabilized camera.
  • Figure 2: Environment in the Gazebo Simulator.
  • Figure 3: Generation of desired quadcopter arc paths.
  • Figure 4: 150(Left) vs. 500(Right) RRT* loops
  • Figure 5: Number of RRT* Loops vs Computation Time
  • ...and 1 more figures