Selfie Drone Stick: A Natural Interface for Quadcopter Photography

TL;DR

This paper introduces SelfieDroneStick, a natural interface that enables users to guide quadcopters to optimal vantage points for photography using smartphone sensors, combining deep reinforcement learning with simulation for real-world deployment.

Contribution

It presents a novel interface for quadcopter photography and advances deep reinforcement learning techniques for transferring control policies from simulation to real robots.

Findings

Successful transfer of deep RL models from simulation to real quadcopters

Effective abstract state representation for sim-to-real transfer

Training paradigms that improve controller performance in real-world deployment

Abstract

A physical selfie stick extends the user's reach, enabling the acquisition of personal photos that include more of the background scene. Similarly, a quadcopter can capture photos from vantage points unattainable by the user; but teleoperating a quadcopter to good viewpoints is a difficult task. This paper presents a natural interface for quadcopter photography, the SelfieDroneStick that allows the user to guide the quadcopter to the optimal vantage point based on the phone's sensors. Users specify the composition of their desired long-range selfies using their smartphone, and the quadcopter autonomously flies to a sequence of vantage points from where the desired shots can be taken. The robot controller is trained from a combination of real-world images and simulated flight data. This paper describes two key innovations required to deploy deep reinforcement learning models on a real robot: 1) an abstract state representation for transferring learning from simulation to the hardware platform, and 2) reward shaping and staging paradigms for training the controller. Both of these improvements were found to be essential in learning a robot controller from simulation that transfers successfully to the real robot.