Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

🚀 Looking forward to a foundtional humanoid motion tracker? 📢Meet Any2Track — Track Any Motions under Any Disturbances! 💡Any2Track shows SOTA performance on diverse motions under multiple disturbances. Project: Codebase:

Zhikai Zhang

1,886 subscribers

45,061 views • 1 year ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

15 Comments

Zhikai Zhang1 year ago

We open-source our motion tracking codebase: Directly train in MuJoCo（you don't have to do the sim2sim now!）and support multi-GPU parallel training.

Michael Black1 year ago

Cool results. For people needing good labels for actions in AMASS, please check out BABEL. Unlike HumanML3D, it has frame-accurate labels of actions for 43 hours of Mocap.

NH_MAGA1 year ago

we are so screwed

Naveen1 year ago

really wish I had a G1 now to test. this is awesome addition to OSS collection.

Nate1 year ago

That robot is never going to forget what you’ve done to it! Watch your back 🤪

Hafiza1 year ago

Next chapter.

Carlos DP 🤖🇺🇸1 year ago

Really cool results! Adding to my growing reading list this week lol

Abhijeet Chavan1 year ago

This is quite informative 👌 thanks

Ricardo FERREIRA MIRANDA1 year ago

I need one only for house chores. No need to show off.

Saïd Aitmbarek1 year ago

based :) !

Guowei Xu1 year ago

Quite amazing

Zhikai Zhang1 year ago

thank you Guowei!

Yuze Zhai1 year ago

Excellent!

Reza Sayar1 year ago

awesome job! 🔥😎 i can only imagine the things they've been through during RL😅

Chenghuai Lin1 year ago

The actor has arrived 😉 Excited to be part of this amazing project!

Related Videos

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.

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 views • 1 year ago

Any2Track: Galbot’s whole-body motion tracking system.

Any2Track: Galbot’s whole-body motion tracking system.

The Humanoid Hub

66,766 views • 1 year ago

RobotMDM, by Disney Research, combines diffusion-based motion generation with RL to produce physics-aware humanoid motions from text prompts. Trained on human motion data with a reward surrogate for physical feasibility, it ensures realistic motions.

RobotMDM, by Disney Research, combines diffusion-based motion generation with RL to produce physics-aware humanoid motions from text prompts. Trained on human motion data with a reward surrogate for physical feasibility, it ensures realistic motions.

The Humanoid Hub

22,943 views • 2 years ago

When you combined multiple motions to make a mega project… Motions belongs to dea(でぃあ) ,Granbein and Y’s🔞 , with other motions from Aplaybox. PS: Majority is from Y’s🔞

When you combined multiple motions to make a mega project… Motions belongs to dea(でぃあ) ,Granbein and Y’s🔞 , with other motions from Aplaybox. PS: Majority is from Y’s🔞

Sinothreebody

12,485 views • 1 year ago

A new paper by Disney Research introduces a 2-stage technique for motion tracking in physics-based character animation, using a pretrained latent space and RL to control diverse and unseen motions on both virtual and real-world humanoid robots. Paper:

A new paper by Disney Research introduces a 2-stage technique for motion tracking in physics-based character animation, using a pretrained latent space and RL to control diverse and unseen motions on both virtual and real-world humanoid robots. Paper:

The Humanoid Hub

20,117 views • 2 years ago

OH! GYM! Students Bring Humanoid Motions from Simulation to Reality (Obstacle Running, Taekwondo, K-POP & Parkour)! 🎬 Video: 💬 Project:

OH! GYM! Students Bring Humanoid Motions from Simulation to Reality (Obstacle Running, Taekwondo, K-POP & Parkour)! 🎬 Video: 💬 Project:

Yoonseok Pyo

15,389 views • 2 months ago

TextOp: A real-time text-to-motion framework for humanoid robots. It allows users to instruct the robot using natural language and to modify commands on the fly, producing smooth, whole-body motions instantly.

TextOp: A real-time text-to-motion framework for humanoid robots. It allows users to instruct the robot using natural language and to modify commands on the fly, producing smooth, whole-body motions instantly.

The Humanoid Hub

25,125 views • 11 months ago

📢 Excited to share our latest work Conference on Robot Learning: Motion Priors Reimagined: Adapting Flat-Terrain Skills for Complex Quadruped Mobility! #CoRL2025 🐶Now ANYmal learns to walk (hop) from real dog motions! 📄Paper: 🌐Project Website:

📢 Excited to share our latest work Conference on Robot Learning: Motion Priors Reimagined: Adapting Flat-Terrain Skills for Complex Quadruped Mobility! #CoRL2025 🐶Now ANYmal learns to walk (hop) from real dog motions! 📄Paper: 🌐Project Website:

Robotic Systems Lab

15,863 views • 1 year ago

✨Battle Motion Updates✨ Introducing the characters whose battle motions have been updated! Be sure to check out their new motions! 👀 #dokkanbattle #dragonball

✨Battle Motion Updates✨ Introducing the characters whose battle motions have been updated! Be sure to check out their new motions! 👀 #dokkanbattle #dragonball

Dragon Ball Z Dokkan Battle

110,451 views • 10 months ago

Researchers from RAI Institute present Diffuse-CLoC, a new control policy that fuses kinematic motion diffusion models with physics-based control to produce motions that are both physically realistic and precisely controllable. This breakthrough moves us closer to developing generalist policies that enable humanoid robots to perform diverse tasks, including dynamic locomotion and contact-rich manipulation, in a natural-looking and robust way. Learn more at

Researchers from RAI Institute present Diffuse-CLoC, a new control policy that fuses kinematic motion diffusion models with physics-based control to produce motions that are both physically realistic and precisely controllable. This breakthrough moves us closer to developing generalist policies that enable humanoid robots to perform diverse tasks, including dynamic locomotion and contact-rich manipulation, in a natural-looking and robust way. Learn more at

RAI Institute

13,580 views • 1 year ago

One of the things that makes Playbooks so great this year in College Football 26... BRAND NEW MOTION PLAYS In this video we showcase: - Reload Motions - DBL Motions - Bounce Motions These plays will open up your Playbooks a TON

Civ

162,197 views • 1 year ago

TWIST: a real-time teleoperation system for humanoid robots to mimic whole-body motions. Reference motion data is generated by retargeting human motion-capture data to the robot. Then, the controller is trained in simulation using reinforcement learning and behavior cloning.

TWIST: a real-time teleoperation system for humanoid robots to mimic whole-body motions. Reference motion data is generated by retargeting human motion-capture data to the robot. Then, the controller is trained in simulation using reinforcement learning and behavior cloning.

The Humanoid Hub

46,715 views • 1 year ago

🚀 Galbot just released AstraBrain-WBC 0.5, the world’s first humanoid robot cerebellum foundation model. Trained on 20,000 hours of human motion data, it validates a Scaling Law for robot motion control and demonstrates zero-shot execution of unseen motions on real humanoids. The era of robot control foundation models is getting closer.

🚀 Galbot just released AstraBrain-WBC 0.5, the world’s first humanoid robot cerebellum foundation model. Trained on 20,000 hours of human motion data, it validates a Scaling Law for robot motion control and demonstrates zero-shot execution of unseen motions on real humanoids. The era of robot control foundation models is getting closer.

Eren Chen

10,270 views • 4 months ago

Don't motion just to motion. Every shift and motion should force the defense to communicate, adjust, or give up a gap. A lesson from Air Raid Masters: Motions & Shifts.

Don't motion just to motion. Every shift and motion should force the defense to communicate, adjust, or give up a gap. A lesson from Air Raid Masters: Motions & Shifts.

Air Raid Certification 🏴‍☠️

13,099 views • 3 months ago

How do you give a humanoid the general motion capability? Not just single motions, but all motion? Introducing SONIC, our new work on supersizing motion tracking for natural humanoid control. We argue that motion tracking is the scalable foundation task for humanoids. So we "supersized" it: 9k+ GPU hours and 100M+ motion frames. But tracking alone is not enough; we show how to make a useful control system out of it: - Universal Kinematic Planner: Enables game-like gamepad control and high-level teleoperation, just like controlling a character in a game. - VR Full-Body Teleop: Direct, real-time whole-body control by a human wearing a VR headset. - VR Keypoint Teleop: Control the upper body (hands/head) while our planner handles robust locomotion automatically. - VLA Integration: We connect this motion tracker to autonomous Visual-Language-Action (VLA) models for autonomous task execution! We use a Universal Token Space to UNIFY this command space, turning our robust tracker into a general-purpose, programmable humanoid brain. This is the generalist "System 1" for humanoids. 🚀 Project: #Humanoids #Robotics #AI #FoundationModels #NVIDIAResearch 🧠🔥

How do you give a humanoid the general motion capability? Not just single motions, but all motion? Introducing SONIC, our new work on supersizing motion tracking for natural humanoid control. We argue that motion tracking is the scalable foundation task for humanoids. So we "supersized" it: 9k+ GPU hours and 100M+ motion frames. But tracking alone is not enough; we show how to make a useful control system out of it: - Universal Kinematic Planner: Enables game-like gamepad control and high-level teleoperation, just like controlling a character in a game. - VR Full-Body Teleop: Direct, real-time whole-body control by a human wearing a VR headset. - VR Keypoint Teleop: Control the upper body (hands/head) while our planner handles robust locomotion automatically. - VLA Integration: We connect this motion tracker to autonomous Visual-Language-Action (VLA) models for autonomous task execution! We use a Universal Token Space to UNIFY this command space, turning our robust tracker into a general-purpose, programmable humanoid brain. This is the generalist "System 1" for humanoids. 🚀 Project: #Humanoids #Robotics #AI #FoundationModels #NVIDIAResearch 🧠🔥

Zhengyi “Zen” Luo

62,932 views • 11 months ago

Peter Obi alongside thousands of Asaba residents walking on the street of Asaba, Delta state this evening while they heavily chant his name without any disturbances 👀

Peter Obi alongside thousands of Asaba residents walking on the street of Asaba, Delta state this evening while they heavily chant his name without any disturbances 👀

Oyindamola🙄

21,506 views • 1 month ago