Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

We built a small biped robot you can teach new tricks to. Train it in simulation, run it on the real thing. Meet Microduck 🦆 $399, shipping before Christmas.

pollenrobotics's profile picture

Pollen Robotics

15,656 subscribers

1,420,571 Aufrufe • vor 1 Tag •via X (Twitter)

KunstWissenschaft & TechnologieBildung
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Train in sim. Run it for real. Teach it new tricks. 🦆 This is the sim2real loop that powers Microduck. RL stack open source here : Buy it here : Git : Join our community :
0:23

Train in sim. Run it for real. Teach it new tricks. 🦆 This is the sim2real loop that powers Microduck. RL stack open source here : Buy it here : Git : Join our community :

Pollen Robotics

247,984 Aufrufe • vor 1 Tag

The coolest part of Microduck might not be the robot. It's how it learns to move. This repo shows the full reinforcement learning pipeline behind Microduck. The robot learns in simulation using MuJoCo, PPO and GPU-based training, then the trained policy is exported to ONNX and deployed on the real robot. But the real challenge is sim-to-real. The simulation models things like actuator behavior, battery voltage, command delays, friction and even gear backlash. That helps make the learned policy work when it moves from simulation to the physical robot. The repo includes policies for walking, fall recovery, sitting, standing, kicking, ground picking and even roller skating. Train in simulation. Test the behavior. Export the policy. Run it on a real robot.
1:01

The coolest part of Microduck might not be the robot. It's how it learns to move. This repo shows the full reinforcement learning pipeline behind Microduck. The robot learns in simulation using MuJoCo, PPO and GPU-based training, then the trained policy is exported to ONNX and deployed on the real robot. But the real challenge is sim-to-real. The simulation models things like actuator behavior, battery voltage, command delays, friction and even gear backlash. That helps make the learned policy work when it moves from simulation to the physical robot. The repo includes policies for walking, fall recovery, sitting, standing, kicking, ground picking and even roller skating. Train in simulation. Test the behavior. Export the policy. Run it on a real robot.

Praveen Kumar Verma

111,561 Aufrufe • vor 1 Tag

Home robots are coming. The first ones in will be the small ones that are safe around kids and pets. Hugging Face's Pollen Robotics just opened pre-orders for Microduck, a $399 biped. 25cm, under 800g, 15 motors, a camera, a small LiDAR, two IMUs, and an articulated beak that picks things up. Ships with 7 pre-trained behaviors including walking, kicking, and roller skating. Open on GitHub under Apache-2.0: the SDK, the simulator, and the RL training pipeline. So you can teach it new tricks.
0:45

Home robots are coming. The first ones in will be the small ones that are safe around kids and pets. Hugging Face's Pollen Robotics just opened pre-orders for Microduck, a $399 biped. 25cm, under 800g, 15 motors, a camera, a small LiDAR, two IMUs, and an articulated beak that picks things up. Ships with 7 pre-trained behaviors including walking, kicking, and roller skating. Open on GitHub under Apache-2.0: the SDK, the simulator, and the RL training pipeline. So you can teach it new tricks.

The Humanoid Hub

710,171 Aufrufe • vor 1 Tag

We built a robot brain that nothing can stop. Shattered limbs? Jammed motors? If the bot can move, the Brain will move it— even if it’s an entirely new robot body. Meet the omni-bodied Skild Brain:
1:33

We built a robot brain that nothing can stop. Shattered limbs? Jammed motors? If the bot can move, the Brain will move it— even if it’s an entirely new robot body. Meet the omni-bodied Skild Brain:

Skild AI

2,441,253 Aufrufe • vor 11 Monaten

Asimov is now zero-shot sim2real for locomotion. You train the policy in simulation. It runs on the robot without additional tuning. Blog: Order yours:
0:32

Asimov is now zero-shot sim2real for locomotion. You train the policy in simulation. It runs on the robot without additional tuning. Blog: Order yours:

Asimov

16,043 Aufrufe • vor 2 Tagen

Given the strong community adoption and real-world deployment of MolmoAct2 on YAM, we're introducing zero-shot evaluation of MolmoAct2 Bimanual YAM in simulation. Now you can test out our models without a real-world robot and build on them! Code: Simulation built on Maniskill!
0:20

Given the strong community adoption and real-world deployment of MolmoAct2 on YAM, we're introducing zero-shot evaluation of MolmoAct2 Bimanual YAM in simulation. Now you can test out our models without a real-world robot and build on them! Code: Simulation built on Maniskill!

Jiafei Duan

37,104 Aufrufe • vor 2 Monaten

We gave a robot body to a GPT-4o AI agent. Here serving a glass from a human to another🍹 With only: • 30mn of arm demonstrations • A language prompt to guide it You can also teach it to clean, play, check in on you. What would you teach it? with Vignesh Anand
0:46

We gave a robot body to a GPT-4o AI agent. Here serving a glass from a human to another🍹 With only: • 30mn of arm demonstrations • A language prompt to guide it You can also teach it to clean, play, check in on you. What would you teach it? with Vignesh Anand

Axel

54,640 Aufrufe • vor 1 Jahr

I placed 🥈 2nd in the LeHome Challenge (at IEEE ICRA 2026) earlier this month, and before that I was 🥇 1st of 62 teams in the simulation round. Now I am sharing my solution — with a detailed logic walkthrough and open-source code. The task was to teach a cheap two-armed robot to fold different garments in simulation and on a real robot. I trained a VLA policy with an RL loop to make it work. Let's break it down 👇
0:33

I placed 🥈 2nd in the LeHome Challenge (at IEEE ICRA 2026) earlier this month, and before that I was 🥇 1st of 62 teams in the simulation round. Now I am sharing my solution — with a detailed logic walkthrough and open-source code. The task was to teach a cheap two-armed robot to fold different garments in simulation and on a real robot. I trained a VLA policy with an RL loop to make it work. Let's break it down 👇

Ilia

21,948 Aufrufe • vor 2 Monaten

15–30 minutes of real-world robot data. That's now enough to go from sim-to-real failure to working robot. Let’s see… You train a robot in simulation. You deploy it in the real world. It fails. The physics don't match. So you try to fine-tune it with real data, but… you never have enough real data, and the fine-tuning breaks everything the simulation taught it. SimDist fixes this with one key decision: don't transfer the policy. Transfer the world model. Keep the reward and value knowledge from simulation frozen. Only update the part that's actually wrong, how the robot predicts physics. Now the robot doesn't have to relearn the entire task in the real world. It already knows what success looks like. It just needs to correct its understanding of how the real world moves. The part that makes this work: they also trained on failures and recoveries; not just perfect demonstrations. Without that, the planner finds the gaps and exploits them. With it, the robot can tell a good future from a bad one. That's all it needs. Results on peg insertion, table leg assembly, locomotion on slippery and uneven surfaces. Tasks that require precision, force, and quick reaction. Thanks for sharing, Tyler Westenbroek ([Tyler Westenbroek]. Interactive visualization + paper: ——- Weekly robotics and AI insights. Subscribe free:
0:41

15–30 minutes of real-world robot data. That's now enough to go from sim-to-real failure to working robot. Let’s see… You train a robot in simulation. You deploy it in the real world. It fails. The physics don't match. So you try to fine-tune it with real data, but… you never have enough real data, and the fine-tuning breaks everything the simulation taught it. SimDist fixes this with one key decision: don't transfer the policy. Transfer the world model. Keep the reward and value knowledge from simulation frozen. Only update the part that's actually wrong, how the robot predicts physics. Now the robot doesn't have to relearn the entire task in the real world. It already knows what success looks like. It just needs to correct its understanding of how the real world moves. The part that makes this work: they also trained on failures and recoveries; not just perfect demonstrations. Without that, the planner finds the gaps and exploits them. With it, the robot can tell a good future from a bad one. That's all it needs. Results on peg insertion, table leg assembly, locomotion on slippery and uneven surfaces. Tasks that require precision, force, and quick reaction. Thanks for sharing, Tyler Westenbroek ([Tyler Westenbroek]. Interactive visualization + paper: ——- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

14,222 Aufrufe • vor 3 Monaten

🚀 We just shipped a big upgrade to our imitation-learning-in-simulation playground in LeRobot, built together with Lightwheel ! You can now teleoperate robots in sim (keyboard or real robot) and collect training demos instantly. This makes it possible to run real IL research on harder, more realistic manipulation tasks, even if you don’t have hardware. New tasks: 🟠 pick orange to the plate 🧺 fold cloth (yes!) 📦 pick 2 “e” toys to the box 🔴 lift red cube Through our partnership with Lightwheel, LeIsaac was integrated into EnvHub on day one, a best-practice integration that strengthens both ecosystems and pushes simulation-first robotics forward. 👉 Load a task via EnvHub, start teleop-ing, record your demo, upload the data on the hub and you’re ready to train or test.
0:22

🚀 We just shipped a big upgrade to our imitation-learning-in-simulation playground in LeRobot, built together with Lightwheel ! You can now teleoperate robots in sim (keyboard or real robot) and collect training demos instantly. This makes it possible to run real IL research on harder, more realistic manipulation tasks, even if you don’t have hardware. New tasks: 🟠 pick orange to the plate 🧺 fold cloth (yes!) 📦 pick 2 “e” toys to the box 🔴 lift red cube Through our partnership with Lightwheel, LeIsaac was integrated into EnvHub on day one, a best-practice integration that strengthens both ecosystems and pushes simulation-first robotics forward. 👉 Load a task via EnvHub, start teleop-ing, record your demo, upload the data on the hub and you’re ready to train or test.

LeRobot

44,647 Aufrufe • vor 9 Monaten

Evaluating robot policies is hard. Ideally, instead of testing every new policy on a real robot, you could test in simulation; but simulations rarely correlate well with real-world performance. In order to make good, useful simulations, you need to spend a great deal of time and effort. That’s where PolaRiS comes in: it’s a toolkit that lets you take a short video of a real scene and turn it into a high-fidelity simulation. It provides what you need to build a good evaluation environment, and it “ships” with off-the-shelf environments that already show strong sim-to-real correlation, meaning that they can be used to inform policy performance. Arhan Jain and Karl Pertsch join us to talk about what they have built, why, and how you can use it. Watch Episode #62 of RoboPapers, with Chris Paxton and Jiafei Duan, now!
59:36

Evaluating robot policies is hard. Ideally, instead of testing every new policy on a real robot, you could test in simulation; but simulations rarely correlate well with real-world performance. In order to make good, useful simulations, you need to spend a great deal of time and effort. That’s where PolaRiS comes in: it’s a toolkit that lets you take a short video of a real scene and turn it into a high-fidelity simulation. It provides what you need to build a good evaluation environment, and it “ships” with off-the-shelf environments that already show strong sim-to-real correlation, meaning that they can be used to inform policy performance. Arhan Jain and Karl Pertsch join us to talk about what they have built, why, and how you can use it. Watch Episode #62 of RoboPapers, with Chris Paxton and Jiafei Duan, now!

RoboPapers

14,689 Aufrufe • vor 6 Monaten

POV: You didn’t use Antioch to run test simulations on your robot before deploying it
0:21

POV: You didn’t use Antioch to run test simulations on your robot before deploying it

Historic Vids

346,409 Aufrufe • vor 2 Monaten

Boston Dynamics has demonstrated its new Atlas humanoid robot lifting and carrying a 50-pound fridge. The robot uses its whole body to balance and move the heavy object in a natural, human-like way. Before doing it in the real world, Atlas practiced the task for millions of hours in a virtual simulation.
0:26

Boston Dynamics has demonstrated its new Atlas humanoid robot lifting and carrying a 50-pound fridge. The robot uses its whole body to balance and move the heavy object in a natural, human-like way. Before doing it in the real world, Atlas practiced the task for millions of hours in a virtual simulation.

Space and Technology

180,505 Aufrufe • vor 2 Monaten

We set out to collect 10M hours of on-embodiment data as a starting point for robotics models, but couldn’t find a robot reliable enough at a price that made it possible. So, we built one. Meet Pandroid: an accessible hardware platform for AI. Small enough to safely experiment with, durable enough to run in fleets. Connect it to any model or coding agent over SSH to let it interact with the world. Join the waitlist:
0:30

We set out to collect 10M hours of on-embodiment data as a starting point for robotics models, but couldn’t find a robot reliable enough at a price that made it possible. So, we built one. Meet Pandroid: an accessible hardware platform for AI. Small enough to safely experiment with, durable enough to run in fleets. Connect it to any model or coding agent over SSH to let it interact with the world. Join the waitlist:

Pantograph

124,433 Aufrufe • vor 24 Tagen

Asimov 1 is built to hack. It ships with a basic policy to control the robot, but you can customize it however you want.
0:25

Asimov 1 is built to hack. It ships with a basic policy to control the robot, but you can customize it however you want.

Asimov

19,122 Aufrufe • vor 3 Monaten

Tired of teleoperation? One human video → 1,000s of robot demos. (📍GitHub ) Scaling Robot Data Without Dynamics Simulation or Robot Hardware Real2Render2Real (R2R2R) is a new way to scale robot data without physics simulation or hardware. You take a phone scan + a single monocular human demo. It tracks the motion, renders photorealistic scenes, and generates diverse, robot-agnostic trajectories ready for training. > No teleop, no sim, no robot, just a phone and a video > Train VLA models and diffusion policies directly on the output > Supports multiple robot embodiments with kinematic consistency > 1000s of demos in 1/27 the time of real-world collection Thank you, Max Fu, for sharing!! Project: Paper: Code coming soon: It shows that with the right pipeline, you can scale robot learning data without touching a robot. One of the most interesting directions in scalable robotics today. —— Weekly robotics and AI insights. Subscribe free:
0:29

Tired of teleoperation? One human video → 1,000s of robot demos. (📍GitHub ) Scaling Robot Data Without Dynamics Simulation or Robot Hardware Real2Render2Real (R2R2R) is a new way to scale robot data without physics simulation or hardware. You take a phone scan + a single monocular human demo. It tracks the motion, renders photorealistic scenes, and generates diverse, robot-agnostic trajectories ready for training. > No teleop, no sim, no robot, just a phone and a video > Train VLA models and diffusion policies directly on the output > Supports multiple robot embodiments with kinematic consistency > 1000s of demos in 1/27 the time of real-world collection Thank you, Max Fu, for sharing!! Project: Paper: Code coming soon: It shows that with the right pipeline, you can scale robot learning data without touching a robot. One of the most interesting directions in scalable robotics today. —— Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

42,864 Aufrufe • vor 6 Monaten

Michael Knowles: Before, you could teach the Bible in schools, [but] not teach pornography. Today, you can teach pornography in schools, [but] not the Bible. I think we had it right the first time.
1:20

Michael Knowles: Before, you could teach the Bible in schools, [but] not teach pornography. Today, you can teach pornography in schools, [but] not the Bible. I think we had it right the first time.

Defiant L’s

229,638 Aufrufe • vor 1 Monat

Still the coolest and most challenging thing I’ve ever built. Threejs (r3f) + arduino simulation + analog simulation all happening in the browser simultaneously. It was a wild ride to say the least.
0:48

Still the coolest and most challenging thing I’ve ever built. Threejs (r3f) + arduino simulation + analog simulation all happening in the browser simultaneously. It was a wild ride to say the least.

Austin Malerba

753,892 Aufrufe • vor 2 Jahren

The wait is finally over!!! 😁 We just dropped an in-depth tutorial on how to build your own robot! Teach it new skills by showing it a few moves with just a laptop. Then watch your homemade robot act autonomously 🤯 1/🧵👇
1:10

The wait is finally over!!! 😁 We just dropped an in-depth tutorial on how to build your own robot! Teach it new skills by showing it a few moves with just a laptop. Then watch your homemade robot act autonomously 🤯 1/🧵👇

Remi Cadene

400,449 Aufrufe • vor 2 Jahren