This book presents the astonishing potential of deep sensorimotor policies for agile vision-based quadrotor flight. Quadrotors are among the most agile and dynamic machines ever created. However, developing fully autonomous quadrotors that can approach or even outperform the agility of birds or human drone pilots with only onboard sensing and computing is challenging and still unsolved.

Deep sensorimotor policies, generally trained in simulation, enable autonomous quadrotors to fly faster and more agile than what was possible before. While humans and birds still have the advantage over drones, the author shows the current research gaps and discusses possible future solutions.

Shows algorithms to operationalize vision-based high-speed flight of drones in unstructured environments Exploits the synergy between perception and action which characterizes natural and artificial agents alike Winner of the George Giralt PhD award for extraordinary contributions in Robotics

Autorentext

Antonio Loquercio is a robotics scientist and engineer originally from Naples, Italy. He is a recipient of the ETH Medal for outstanding master thesis and the Georges Giralt Ph.D. award, the most prestigious prize for a European dissertation in robotics. He is known for his research on high-performance agile robotics, particularly for drones and legged robots. Growing up in the countryside near Rome, he was always fascinated by the wonders of nature. The desire to understand and recreate such wonders motivated him to embark on a career in robotics. He was an undergraduate at the University of Rome, Tor Vergata, where he studied mechanical and electrical engineering. Afterward, he moved to Zurich, Switzerland, where he was first a master's and then a graduate student at the Swiss Federal Institute of Technology (ETH) and the University of Zurich. He is currently a postdoctoral scholar at the University of California, Berkeley. He has contributed more than 20 scientific papers in robotics and computer vision. His works were awarded several recognitions, including the best system paper award at the conference on robot learning, the best paper award honorable mention at the conference Robotics: Science and Systems, and the Transaction on Robotics Best Paper Award honorable mention.

Inhalt
1: Introduction.- 2: Contribution.- 3: Future Directions.