The Robotic Systems Lab designs machines, creates actuation principles, and builds up control technologies for autonomous operation in challenging environments.
Zurich, Switzerland
- Tweets 704
- Following 171
- Followers 38,363
- Likes 589
VLMs don't understand a robot's body. How can a robot learn from its failures without retraining?
PragmaBot: online in-context learning from real-world experience. The robot reflects on failures, stores lessons in memory, and retrieves them for new tasks.
RA-L · #IROS2026
1
7
53
4,486
How much memory belongs in the context? 5 random memories: 17% first-action accuracy on unseen tasks. Entire memory in the prompt: 74%, at 7.5x the tokens. Top-k relevant via RAG: 89%. Relevant context beats more context. As memory grows, what should a robot forget?
1
1
343
Congrats to Kaixian Qu, Guowei Lan, René Zurbrügg, Changan Chen, Christopher Mower, Haitham Bou-Ammar & Marco Hutter. Say hi at IROS 2026!
ieeexplore.ieee.org/document…
arxiv.org/abs/2507.16713
pragmabot.github.io
github.com/leggedrobotics/pr…
1
303
We are releasing EgoHTR, a dataset with both human motions and terrain references, accepted @corl_conf.
📖 Paper: lnkd.in/eeepUefs
🌐 Project Page: egohtr.github.io
• 55 scene-aligned sequences • 150k+ frames • rough-terrain environments • multi-modal 3D scene
3
9
42
11,231
We’re open-sourcing the dataset and the full data pipeline to make this resource accessible to the community and hopefully enable new directions in learning-based robotics.
1
1
952
By Alex Brandes, Haig Conti Georges Sajelian, Manthan Patel @patelm99, Dominik Hollidt, Chenhao Li @breadli428, Matthias Heyrman, Oliver Hausdörfer, Manuel Kaufmann, Xi Wang, Jonas Frey, Angela Schoellig @angelaschoellig, Christian Holz, Marc Pollefeys @mapo1, and Marco Hutter.
1
2
567
PPO has long dominated robot locomotion training in simulation. SAC, despite its sample efficiency, couldn't keep up.
We analyze why:
🔗sabagian.github.io/sac_relea…
🔥Integrated into RSL-RL, our approach requires only minimal changes, making SAC a drop-in alternative out of the box.
7
42
343
45,683
This project focuses on understanding the performance gap between PPO and SAC in massively parallel robot learning.
While efforts like FlashSAC @hojoon_ai and FastSAC @younggyoseo explore separate development, RSL-RL-SAC is made to stay close to the widely used RSL-RL codebase.
1
5
1,598
This project is led by Gianluca Sabatini, supported by Chenhao Li @breadli428 and Marco Hutter @leggedrobotics. We thank Clemens Schwarke's implementation insights.
Check out the paper!
arxiv.org/abs/2605.24975
8
1,191
We’re excited to be receiving one of these platforms for our research. Looking forward to exploring what we can build with it and contributing to the next wave of humanoid robotics.
NVIDIA announces the first open humanoid robot reference design built for robotics research.
The NVIDIA Isaac GR00T Reference Humanoid Robot combines the @UnitreeRobotics H2 humanoid robot, @SharpaRobotics Wave five-fingered hands for dexterous manipulation, Jetson Thor onboard compute, and Isaac GR00T open software and models, giving researchers a full-stack platform from data capture to model deployment.
Read the #NVIDIAGTC Taipei announcement: nvda.ws/4ef9VOr
3
4
50
7,644
Advancing dexterous manipulation through scalable visual sim-to-real transfer.
We are excited to share our RSS paper, “ViserDex: Visual Sim-to-Real for Robust Dexterous In-hand Reorientation.”
🌐 Project page: rffr.leggedrobotics.com/work…
1/N 🧵
6
20
199
40,390
4/N
This work highlights 3D Gaussian Splatting as a practical path toward scalable RGB-only dexterous manipulation.
For more details: arxiv.org/abs/2604.11138
This work was led by Arjun Bhardwaj (@ThougthShot )
2
6
2,115