Robotic Systems Lab

🌎Uncertainty-Aware Robotic World Model Makes Offline Model-Based Reinforcement Learning Work on Real Robots 👥Chenhao Li @breadli428, Andreas Krause, Marco Hutter @leggedrobotics 🎯Webpage: sites.google.com/view/uncertain… 📄Paper: arxiv.org/abs/2504.16680

The toughest moment in a PhD: >spend a year building smth you’re proud of >travel across world with advisors’ support to share it >when your moment finally comes >your mic gets cut because the previous schedule ran late Heartbroken, but thanks to whom stayed for me @NeurIPSConf

🌎Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics 👥Chenhao Li @breadli428, Andreas Krause, Marco Hutter @leggedrobotics 🎯Webpage: sites.google.com/view/roboticwo… 📄Paper: arxiv.org/abs/2501.10100 🗣️Oral presentation at EWM @NeurIPSConf.

📢 Call for Papers! We are now inviting contributions to the Workshop on Sim-to-Real Transfer for Humanoid Robots, to be held at #Humanoids2025 @HumanoidsConf in Seoul, South Korea! 🎤 We already have a great lineup of invited speakers and panelists to discuss the current challenges and latest applications in robotics, including Pulkit Agrawal @pulkitology (MIT), Sven Behnke @SvenBehnke (University of Bonn), Marco Hutter (ETH Zurich), Beomjoon Kim @leidenschaft1 (KAIST), and Stephan Pleines (NVIDIA). 🔗 For more details and submission guidelines, please visit: sites.google.com/view/sim-to-re… From the organizers, Julian Eßer, Chenhao Li @breadli428, Gabriel Margolis @gabe_mrgl, Huazhe Xu @HarryXu12.

🐶Motion imitation should never limit itself to simply replaying the motions in the dataset on flat terrains. In our #CoRL2025 work Motion Priors Reimagined, we extend motion tracking to complex locomotion and navigation tasks, to make skills "useful". 🔗anymalprior.github.io

🤖What if you want to train rough terrain humanoid locomotion but have only flat terrain demonstrations? ⛳️In ConsMimic, we introduce a principled pipeline to learn stylistic motions from demonstrations that may not align with task objectives. See you @corl_conf in Seoul!