Jan Schneider (@JanS1854) profile picture

ELLIS PhD student at MPI-IS & University of Oxford | Google PhD Fellow | Working on sim-to-real transfer for tendon-driven and muscle-actuated robots 🦾

Tübingen
Joined December 2023
Photo by Jan Schneider (@JanS1854)Photo by Jan Schneider (@JanS1854)Photo by Jan Schneider (@JanS1854)
Thrilled to announce that I was selected as a Google PhD Fellow in Machine Learning and ML Foundations for my research on tendon-driven and muscle-actuated robots 🦾 I am grateful to @Google and to @dtrbchlr, @IngmarPosner, and @bschoelkopf for their support! #GooglePhDFellowship
4
1
62
3,097
I'll be presenting tomorrow at poster session P3 (10:30 - 12:00) at @corl_conf. Find me at 𝗽𝗼𝘀𝘁𝗲𝗿 𝟭𝟬𝟴 if you'd like to chat about sim-to-real transfer for tendon-driven and muscle-actuated robots 🦾
First sim-to-real transfer for muscle-actuated robots 🦾 Muscle-actuated robots are powerful but hard to model. GeAN addresses this longstanding challenge by learning muscle and tendon dynamics, enabling sim-to-real transfer. arxiv.org/abs/2604.09487 youtu.be/EOgdJxghYaw 🧵👇
1
17
640
Accepted at @corl_conf 🥳 Looking forward to discussing our work on sim-to-real transfer for muscle-actuated robots!
First sim-to-real transfer for muscle-actuated robots 🦾 Muscle-actuated robots are powerful but hard to model. GeAN addresses this longstanding challenge by learning muscle and tendon dynamics, enabling sim-to-real transfer. arxiv.org/abs/2604.09487 youtu.be/EOgdJxghYaw 🧵👇
13
732
First sim-to-real transfer for muscle-actuated robots 🦾 Muscle-actuated robots are powerful but hard to model. GeAN addresses this longstanding challenge by learning muscle and tendon dynamics, enabling sim-to-real transfer. arxiv.org/abs/2604.09487 youtu.be/EOgdJxghYaw 🧵👇
7
28
7
115
22,054
(5/5) Many thanks to my amazing collaborators, @mridulmahajan_ , @clthegoat , @simonguist , @bschoelkopf , @IngmarPosner , and @dtrbchlr .
5
317
(4/5) Deploying the GeAN with a GPU-based simulator enables massive parallelization and efficient RL training. The learned policies transfer zero-shot to the real robot (4-DoF, tendon-driven, actuated by pneumatic artificial muscles), producing dynamic and precise motions.
6
355
(3/5) GeAN uses the known arm dynamics to learn the mapping from commands to joint torques from joint position trajectories alone. No torque sensors needed → the method is applicable to a wide range of robots (with all kinds of actuators).
6
297
(2/5) Our method first collects a dataset of randomized open-loop motions to explore the robot's actuator dynamics. This data is used to train the Generalized Actuator Network (GeAN).
1
9
493
Pushing for #icra but still missing real robot experiments? 😰 Skip the ROS headaches — get your Franka robot running in minutes with franky! 🦾 Super beginner-friendly, Pythonic, and fast to set up. 🔗 github.com/TimSchneider42/fr… @ias_tudarmstadt @Jan_R_Peters 🧵👇
1
15
68
4,137
Jan Schneider retweeted
#ThrowbackThursday: We welcomed Federal Minister Hubertus Heil to Cyber Valley! After viewing projects from @MPI_IS, he spoke with the Cyber Valley Community about the challenges faced by qualified specialists from abroad 👉 cyber-valley.de/en/news/bund… #BetterTogether #AI #AIFuture
2
5
680
Jan Schneider retweeted
Learning to play the piano with two robot hands is super challenging, even in simulation! It requires coping with bimanual coordination at high speed to achieve human-level dexterity. We introduce RP1M, a large-scale robot piano-playing motion dataset, featuring ~1M trajectories over 2k music pieces. Website: rp1m.github.io/ Paper: arxiv.org/abs/2408.11048
9
37
10
171
27,190
Jan Schneider retweeted
We presented our work on a novel open-source (mostly) 3D-printable tendon-driven robot arm at #RSS2024 today. Our design enables safety through reduced inertia and passive compliance, while addressing challenges regarding friction and robustness youtube.com/watch?v=5vH2_TAa…
2
3
10
899
If you are at #ICLR2024 and want to hear more about our work on gradient subspaces for RL, come to poster #167 tomorrow from 10:45 to 12:45. Looking forward to chatting with you!
Gradient subspace optimization unlocked for RL 🔒➡️🔓 Used only for supervised learning so far, our #ICLR2024 paper illustrates that policy gradients evolve in a small, slowly-changing subspace, opening up many opportunities for more efficient RL. arxiv.org/abs/2401.06604
2
9
866
Gradient subspace optimization unlocked for RL 🔒➡️🔓 Used only for supervised learning so far, our #ICLR2024 paper illustrates that policy gradients evolve in a small, slowly-changing subspace, opening up many opportunities for more efficient RL. arxiv.org/abs/2401.06604
1
6
2
35
3,159
Many thanks to my amazing collaborators @rlfromlux, @simonguist, @clthegoat, @HaeufleLab, @bschoelkopf, @dtrbchlr.
1
6
596