Program JavaZone

Foredrag Onsdag 2. september

Let's Dance! - Teaching your Robot some Moves with Reinforcement Learning

– Room 5

Engelsk 45 min Robotics AI Reinforcement Learning IsaacLab

Foredragsholdere

Thomas Endres

LinkedIn X

Thomas Endres is a Managing Partner for TNG Technology Consulting in Munich. Besides his normal work for the company and the management of the customers he is creating various prototypes, including real-time deepfakes, an AI for generating presentations or various robotics showcases. He works on applications in the field of AI, robotics, AR/VR and teleoperation. Furthermore, he is involved in Open Source projects.

Thomas studied computer science at TU Munich and is a passionate software developer. As an Intel Software Innovator and Black Belt, he presents new technologies such as AI, AR/VR, and robotics worldwide. For this, he has received awards including a JavaOne Rockstar Award and several Best Speaker Awards.

Dennis Schulz

LinkedIn

Dennis Schulz is a Senior Consultant at TNG Technology Consulting. He holds a PhD in low temperature physics from the University of Heidelberg. Besides being a programmer, he organized and hosted the TV show Quasi Klar for RNF, published a book that was translated to Korean and Russian, and won Science Slam competitions all over Germany. As a part of the Innovation Hacking team at TNG, he worked on different AI showcases, fine-tuning embeddings, and data mining.

Om sesjonen

Has this ever happened to you: You just spent 50k€ on a humanoid robot but it's not very fun at parties so you have to train it to dance using reinforcement learning in a simulation environment on your 100k€ GPU Cluster? What do you mean "NO"?

In this talk, we will teach you how you can train your humanoid robot to dance using reinforcement learning in simulation environments. We're gonna kick things off with an introduction into Reinforcement Learning (RL), covering the basics of policies and rewards. After that, we'll take our first steps in simulation environments with the introduction of NVIDIA Isaac Sim and the Unitree RL Lab. We will run through the steps of shaping a walking policy, one hilarious fall at a time. Finally, we're going to shake things up with a dancing policy: You will learn how you can retarget human motion from videos to the Unitree G1 robot and train an imitation policy that can dance just as poorly as you.

Throughout the talk, we will do a live training of a walking policy on stage, starting early on in the presentation and checking up on the progress from time to time. For the grande finale, our humanoid robot will close the session with a dancing performance, not missing out on a single step.

Passer for

Developers interested in Robotics

Samtidig i programmet

  1. Hacking i "gamle" dager - røverhistorier fra 80- og 90-tallet Room 1
  2. Snake in 10 Lines: Learning More by Coding Less Room 2
  3. How Are We Doing? Practical Metrics that Matter Room 3
  4. Secure-by-Inclusion: Preventing Accessibility Barriers from Becoming Security Vulnerabilities Room 4