Seminar | February 28 | 4-5 p.m. | 540 Cory Hall
Antonio Loquercio, Postdoc, EECS, UC Berkeley
Electrical Engineering and Computer Sciences (EECS)
Quadcopters are among the most agile and dynamic machines ever created. In this talk, Ill show how data-driven sensorimotor controllers can push quadcopters with only onboard sensing and computation to their physical limits. Such controllers enable quadcopters to fly faster and more agile than what was possible before in unstructured environments like cities, forests, and disaster scenarios. The insights acquired from quadcopter flight transfer to other domains, including legged locomotion and bio-inspired vision. However, fundamental research questions still need to be addressed to make agile robots adaptable, robust, and safe, and enable their wider application in homes, search and surveillance, and inspection. Teaser videos of the results I will present are
Deep Drone Acrobatics and Agile Autonomy.
Antonio Loquercio is a postdoc at UC Berkeley. He received his PhD and M.Sc. from UZH and ETH Zurich in 2021 and 2017. His research interests include learning-based robotics, computer vision, and machine learning. His work includes seminal results on vision-based agile flight via learning sensorimotor policies, low-latency vision based on event cameras, and continual learning in legged locomotion. He is the recipient of the 2017 ETH Medal for Outstanding Master Thesis, the best system paper award at the conference on robot learning (CORL) 2018, the RSS20 Best paper award honorable mention, and the T-RO20 Best Paper Award Honorable mention. He received the Georges Giralt PhD Award, the most prestigious award for Ph.D. dissertations in robotics in Europe.
Heather Levien, heather@berkeley.edu, 510-883-4013