In this talk, we present our work on learning control policies directly in simulation that are deployed onto real drones without any fine tuning. The presentation covers autonomous drone racing, drone acrobatics, and uncertainty estimation in deep networks.

This presentation is based on the following three papers:
E. Kaufmann*, A. Loquercio*, R. Ranftl, M. Müller, V. Koltun, D. Scaramuzza
Deep Drone Acrobatics
Robotics: Science and Systems (RSS), 2020
Best Paper Award finalist
PDF: http://rpg.ifi.uzh.ch/docs/RSS20_Kauf...
YouTube:    • Deep Drone Acrobatics (RSS 2020)  
RSS2020 Pitch:    • Deep Drone Acrobatics (RSS 2020 Video...  
VideoBlog Post: https://sim2realai.github.io/deep-dro...
Code: https://github.com/uzh-rpg/deep_drone...

A. Loquercio*, E. Kaufmann*, R. Ranftl, A. Dosovitskiy, V. Koltun, D. Scaramuzza
Deep Drone Racing: From Simulation to Reality with Domain Randomization
IEEE Transactions on Robotics, 2019
PDF: http://rpg.ifi.uzh.ch/docs/RSS20_Kauf...
YouTube 1:    • Deep Drone Racing: Learning Agile Fli...  
YouTube 2:    • Deep Drone Racing: From Simulation to...  
Code: https://github.com/uzh-rpg/sim2real_d...

A. Loquercio*, M. Segu*, D. Scaramuzza
A General Framework for Uncertainty Estimation in Deep Learning
IEEE Robotics and Automation Letters, 2020.
PDF: http://rpg.ifi.uzh.ch/docs/RAL20_Loqu...
YouTube:    • A General Framework for Uncertainty E...  
ICRA2020 Pitch:    • ICRA2020 Pitch Video: A General Frame...  
Code: https://tinyurl.com/v3jb64k

* = These authors contributed equally.

More about our research on Deep Learning: http://rpg.ifi.uzh.ch/research_learni...
More about our research on Drone Racing: http://rpg.ifi.uzh.ch/research_drone_...

Affiliations:
Antonio Loquercio and Davide Scaramuzza are with the Robotics and Perception Group, Dep. of Informatics, University of Zurich, and Dep. of Neuroinformatics, University of Zurich and ETH Zurich, Switzerland.

Lab website: http://rpg.ifi.uzh.ch/