Learning Agile, Vision-based Drone Flight: from Simulation to Reality

Davide Scaramuzza; Elia Kaufmann

Learning Agile, Vision-based Drone Flight: from Simulation to Reality

Robotics 2023-04-11 v1

Authors: Davide Scaramuzza , Elia Kaufmann

Abstract

We present our latest research in learning deep sensorimotor policies for agile, vision-based quadrotor flight. We show methodologies for the successful transfer of such policies from simulation to the real world. In addition, we discuss the open research questions that still need to be answered to improve the agility and robustness of autonomous drones toward human-pilot performance.

Keywords

autonomous drone quadrotor control sim-to-real transfer

Cite

@article{arxiv.2304.04128,
  title  = {Learning Agile, Vision-based Drone Flight: from Simulation to Reality},
  author = {Davide Scaramuzza and Elia Kaufmann},
  journal= {arXiv preprint arXiv:2304.04128},
  year   = {2023}
}

Related papers

View all related →