Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Watch AthenaZero juggle barehanded using on-board sensory feedback only. No motion capture. No funnels. No help adding the third ball. The robot learns to adapt to the uncertainties from contact and the appropriate hand-eye coordination. Learn more:

rai_inst's profile picture

RAI Institute

8,075 subscribers

14,032 Aufrufe • vor 5 Monaten •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

1 Kommentare

Profilbild von Ribik Khoteja
Ribik Khotejavor 4 Monaten

Really impressive work on AthenaZero, dynamic manipulation without motion capture is not easy. We work with robotics teams in Shenzhen. Maybe there’s a way we could support the hardware/manufacturing side as things scale?

Ähnliche Videos

Humanoid robots can now play tennis in the style of Nadal, Federer, and Djokovic, learned from broadcast footage. AdaPT (Noitom Robotics, Shanghai AI Lab, Dobot, SJTU) extracts professional player motions from TV broadcasts, retargets them to a humanoid, and learns both rallying and serving while preserving each player's distinctive style. The core problem: decoupled planning-and-tracking works in sim but degrades badly on real hardware. Their fix is speed adaptation, training the tracker on randomized execution speeds while the planner learns to adjust motion speed to the incoming ball. Deployed on Unitree G1 and the full-size Dobot Atom. Worth noting on the sensing: the robot has no onboard vision. Ball and robot position both come from external infrastructure, a 35-camera motion-capture arena in the lab. Paper:
1:10

Humanoid robots can now play tennis in the style of Nadal, Federer, and Djokovic, learned from broadcast footage. AdaPT (Noitom Robotics, Shanghai AI Lab, Dobot, SJTU) extracts professional player motions from TV broadcasts, retargets them to a humanoid, and learns both rallying and serving while preserving each player's distinctive style. The core problem: decoupled planning-and-tracking works in sim but degrades badly on real hardware. Their fix is speed adaptation, training the tracker on randomized execution speeds while the planner learns to adjust motion speed to the incoming ball. Deployed on Unitree G1 and the full-size Dobot Atom. Worth noting on the sensing: the robot has no onboard vision. Ball and robot position both come from external infrastructure, a 35-camera motion-capture arena in the lab. Paper:

The Humanoid Hub

86,311 Aufrufe • vor 1 Monat

The eye contact No showing of the first hand The 3b with a shit hand This hand feels very weird to me. thoughts?
0:36

The eye contact No showing of the first hand The 3b with a shit hand This hand feels very weird to me. thoughts?

Rob Kuhn

98,962 Aufrufe • vor 1 Jahr

Watch this robot dog learn to walk from scratch in real time! Our new method, APRL, dynamically adjusts exploration constraints to enable fast and performant RL directly in the real world. APRL can also adapt to changes in the terrain. No simulation, no demos. A thread 👇
0:57

Watch this robot dog learn to walk from scratch in real time! Our new method, APRL, dynamically adjusts exploration constraints to enable fast and performant RL directly in the real world. APRL can also adapt to changes in the terrain. No simulation, no demos. A thread 👇

Sergey Levine

105,579 Aufrufe • vor 2 Jahren

The Vicarious Surgical robot is designed to replicate a surgeon's movements and perform minimally invasive operations inside the body while providing stereoscopic imaging data and sensory feedback. The surgeon controls it remotely through immersive 3D view using hand controllers.
0:58

The Vicarious Surgical robot is designed to replicate a surgeon's movements and perform minimally invasive operations inside the body while providing stereoscopic imaging data and sensory feedback. The surgeon controls it remotely through immersive 3D view using hand controllers.

Valerio Pergola

17,663 Aufrufe • vor 3 Jahren

Any2Track tracks diverse motions under various disturbances. The two-stage RL framework learns to track contact-rich human motions from motion capture datasets and adds adaptability to disturbances via dynamics-aware model prediction.
1:19

Any2Track tracks diverse motions under various disturbances. The two-stage RL framework learns to track contact-rich human motions from motion capture datasets and adds adaptability to disturbances via dynamics-aware model prediction.

The Humanoid Hub

146,181 Aufrufe • vor 1 Jahr

'LATENT' learns tennis skills for humanoid robots from human motion data. The robot can sustain multi-shot rallies, handle ball speeds of 15+ m/s, and showed a 90.9% success rate for the forehand. No onboard cameras or vision models, relies on external MoCap for high-precision, low-latency ball tracking. Paper:
1:31

'LATENT' learns tennis skills for humanoid robots from human motion data. The robot can sustain multi-shot rallies, handle ball speeds of 15+ m/s, and showed a 90.9% success rate for the forehand. No onboard cameras or vision models, relies on external MoCap for high-precision, low-latency ball tracking. Paper:

The Humanoid Hub

64,030 Aufrufe • vor 6 Monaten

Drive characters’ bodies, faces, and more from regular video with the MetaHuman Animator Markerless Motion Capture plugin on @Fab. No suits or markers needed!:
0:55

Drive characters’ bodies, faces, and more from regular video with the MetaHuman Animator Markerless Motion Capture plugin on @Fab. No suits or markers needed!:

Unreal Engine

216,527 Aufrufe • vor 3 Monaten

Apart from solving new tasks, memory also allows our policies to be more robust: we show early signs of in-context adaptation, where the robot learns to adapt its behavior on-the-fly by learning from its past mistakes.
0:22

Apart from solving new tasks, memory also allows our policies to be more robust: we show early signs of in-context adaptation, where the robot learns to adapt its behavior on-the-fly by learning from its past mistakes.

Physical Intelligence

14,923 Aufrufe • vor 6 Monaten

Reward AI just came out of stealth and unveiled OM-1, a robot policy learned entirely from humans. No teleoperation, no on-robot data. One Model, Any Body. 1. Capture. A wearable 7-DoF hand (Omnibody Hand) lets people demonstrate manipulation naturally while working, cooking, or sorting. Sensors record tactile, proximity, force and hand pose at full human speed. 2. Learn. OM-1 trains on this human data alone. No teleop, no on-robot experience. Then it runs across bodies from industrial arms to humanoids, and scaling is just adding more human data. 3. Control. A high-frequency control layer, trained with RL in sim, executes those actions on any robot, holding steady through unknown loads like a stuck fridge door. The result: OM-1 picks up a brand-new task from under 30 minutes of data.
0:27

Reward AI just came out of stealth and unveiled OM-1, a robot policy learned entirely from humans. No teleoperation, no on-robot data. One Model, Any Body. 1. Capture. A wearable 7-DoF hand (Omnibody Hand) lets people demonstrate manipulation naturally while working, cooking, or sorting. Sensors record tactile, proximity, force and hand pose at full human speed. 2. Learn. OM-1 trains on this human data alone. No teleop, no on-robot experience. Then it runs across bodies from industrial arms to humanoids, and scaling is just adding more human data. 3. Control. A high-frequency control layer, trained with RL in sim, executes those actions on any robot, holding steady through unknown loads like a stuck fridge door. The result: OM-1 picks up a brand-new task from under 30 minutes of data.

The Humanoid Hub

35,064 Aufrufe • vor 11 Tagen

Imagine if you have an object in hand, you can rotate the object by feeling without even looking. This is what we enable the robot to do now: Rotating without Seeing. Our multi-finger robot hand learns to rotate diverse objects using only touch sensing.
2:19

Imagine if you have an object in hand, you can rotate the object by feeling without even looking. This is what we enable the robot to do now: Rotating without Seeing. Our multi-finger robot hand learns to rotate diverse objects using only touch sensing.

Xiaolong Wang

65,293 Aufrufe • vor 3 Jahren

Here’s the windmill assembly demo we showed at CES 2026 — the one no one saw coming. North executes a fully autonomous, long-horizon dexterous sequence with sustained hand–eye–tactile coordination and assembly-level precision enabled by tactile feedback. It’s also robust to disturbance: you can reposition the objects, and North will still identify them and recover the task. This is powered by CraftNet (VTLA) — using tactile feedback to continuously fine-tune the last-millimeter interaction, enabling reliable execution across 30+ steps. Read more about CraftNet: #Sharpa #SharpaWave #SharpaNorth #CraftNet #System0 #CES2026
0:53

Here’s the windmill assembly demo we showed at CES 2026 — the one no one saw coming. North executes a fully autonomous, long-horizon dexterous sequence with sustained hand–eye–tactile coordination and assembly-level precision enabled by tactile feedback. It’s also robust to disturbance: you can reposition the objects, and North will still identify them and recover the task. This is powered by CraftNet (VTLA) — using tactile feedback to continuously fine-tune the last-millimeter interaction, enabling reliable execution across 30+ steps. Read more about CraftNet: #Sharpa #SharpaWave #SharpaNorth #CraftNet #System0 #CES2026

Sharpa

88,304 Aufrufe • vor 8 Monaten

Bringing performances to the digital world is now easier than ever. This is a behind the scenes look at 3D animator Keymyon Kim using Move Multi-Cam to capture and create the #BaddieChallenge. Motion capture powered by AI. No suits or markers required.
0:21

Bringing performances to the digital world is now easier than ever. This is a behind the scenes look at 3D animator Keymyon Kim using Move Multi-Cam to capture and create the #BaddieChallenge. Motion capture powered by AI. No suits or markers required.

Move AI

349,031 Aufrufe • vor 2 Jahren

....uhm guys.... the eye contact....the deadly zoom....yeah. yeah no i refuse to speak further
0:21

....uhm guys.... the eye contact....the deadly zoom....yeah. yeah no i refuse to speak further

슙국. 🥢

25,914 Aufrufe • vor 3 Monaten

No, really. You got 7 seconds from the time the pitcher gets the ball to be in the box and alert to him no matter what he's doing and no matter what happened on the previous pitch. 7 seconds.
0:23

No, really. You got 7 seconds from the time the pitcher gets the ball to be in the box and alert to him no matter what he's doing and no matter what happened on the previous pitch. 7 seconds.

Codify

1,400,161 Aufrufe • vor 3 Jahren

The whole sequence leading to Everton’s goal is simply embarrassing. Pickford near the halfway line with time on the ball & free players everywhere. No coordination, no pressure, midfielders with no clear jobs, and a back 5 stuck in the mud vs 10 men.
0:54

The whole sequence leading to Everton’s goal is simply embarrassing. Pickford near the halfway line with time on the ball & free players everywhere. No coordination, no pressure, midfielders with no clear jobs, and a back 5 stuck in the mud vs 10 men.

Fathalli

46,816 Aufrufe • vor 10 Monaten

Every US Open Tennis ball crew tryout tells a story of determination. She may be too young, but Jessie brings lightning reflexes, elite hand-eye coordination, and mentorship from tennis legend Andre Agassi to the court. For more than two decades as the Official Outfitter of the #USOpen, Ralph Lauren has proudly dressed those at the heart of the game—the ball crew. Watch the full video on YouTube: #RLTennis #RLKids
1:00

Every US Open Tennis ball crew tryout tells a story of determination. She may be too young, but Jessie brings lightning reflexes, elite hand-eye coordination, and mentorship from tennis legend Andre Agassi to the court. For more than two decades as the Official Outfitter of the #USOpen, Ralph Lauren has proudly dressed those at the heart of the game—the ball crew. Watch the full video on YouTube: #RLTennis #RLKids

Ralph Lauren

17,221 Aufrufe • vor 26 Tagen