ICRA 2025 Satellite Conference Center at Lodz University of Technology, Day 3
International Conference on Robotics and Automation is the most prestigious conference in the world sponsored by
IEEE Robotics and Automation Society
Satellite Conference Center organized at the Lodz University of Technology (Poland) in the Design-4-All center (A7 building) offers joint participation in the first day of the Conference.
draft program (Warsaw Time):
14:30 – 15:30 Opening Session
15:55 – 17:05 Keynote Session
17:15 – 18:15 Keynote Session
19:45 – 20:45 Plenary Session - Prof. Raffaello (Raff) D’Andrea, Models are dead, long live models!
more details: IEEE ICRA 2025 | Plenary Sessions
You have to register for the event.
International Conference on Robotics and Automation to najbardziej prestiżowa konferencja na świecie sponsorowana przez IEEE Robotics and Automation Society.
Satelitarne Centrum Konferencyjne, zorganizowane na Politechnice Łódzkiej (Polska) w centrum Design-4-All (budynek A7), umożliwia wspólne uczestnictwo w pierwszym dniu konferencji.
Program (czas warszawski):
-
14:30 – 15:30 Sesja otwierająca
-
15:55 – 17:05 Sesja plenarna
-
17:15 – 18:15 Sesja plenarna
-
19:45 – 20:45 Sesja plenarna – Prof. Raffaello (Raff) D’Andrea, Models are dead, long live models!
Więcej szczegółów: IEEE ICRA 2025 | Plenary Sessions
Aby wziąć udział w wydarzeniu, należy się zarejestrować.
Date and Time
Location
Hosts
Registration
- Date: 22 May 2025
- Time: 12:30 PM UTC to 07:00 PM UTC
-
Add Event to Calendar
Speakers
Raffaello (Raff) D’Andrea of Professor of dynamic systems and control, ETH Zurich
Models are dead, long live models!
Abstract: Mathematical models are indispensable for system design. Until recently, one could argue that this was also true for robot control design. Recent advances in AI are calling this basic assumption into question. In this talk, I will present my first-hand experiences in model-based control design, ranging from soccer playing robots to fleets of autonomous mobile robots in warehouses – on the ground and in the air — to acrobatic flying robots. I will conclude by introducing CyberRunner, an opensource ML platform developed at ETH based on the popular “Labyrinth” dexterity game in which a ball is guided through a maze and must avoid traps. CyberRunner learns through experience and can beat any human with only 1 hour of training and without any priors.