Загрузка видео...

Не удалось загрузить видео

На главную

A humanoid robot must recover from any fall or stabilize itself using arms and torso while tripping. MPC and sim-to-real methods often struggle with this. A new study by Tsinghua University researchers tackles uncertain contact scenarios using a rigid-body simulator and RL.

TheHumanoidHub's profile picture

The Humanoid Hub

57,236 subscribers

129,671 просмотров • 1 год назад •via X (Twitter)

Наука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 8

Фото профиля The Humanoid Hub
The Humanoid Hub1 год назад

Project page (the paper is not available yet.)

Фото профиля Yang
Yang1 год назад

Want to learn how practical AI skills and automations for your business and work? Check out our 50+ step-by-step video tutorials 100% FREE 20+ hours of Ai and Automation goodness absolutely free 🥳

Фото профиля David Hansen 🇺🇸🇳🇿🤖
David Hansen 🇺🇸🇳🇿🤖1 год назад

Something like this soon

Фото профиля Joshua BlueMoon
Joshua BlueMoon1 год назад

He's preparing to fight Kai Cenat

Фото профиля Paul Foreman ♥️
Paul Foreman ♥️1 год назад

Put the sensors on a human doing the movements & map it for the robot :)

Фото профиля alejandro
alejandro1 год назад

I foreseeing a Jiu Jitsu training bot.

Фото профиля Yane
Yane1 год назад

I understand building and creating new things and trying to make life more efficient but are people not worried about replaced?

Фото профиля Morten Haulik ᯅ
Morten Haulik ᯅ1 год назад

@cixliv

Похожие видео

Need a new tennis partner? This robot from Tsinghua University researchers has some serious skills:
1:27

Need a new tennis partner? This robot from Tsinghua University researchers has some serious skills:

The Rundown AI

16,184 просмотров • 3 месяцев назад

Northwestern University researchers developed modular robots using AI that can adapt to damage and navigate unpredictable terrain, according to a new study
0:55

Northwestern University researchers developed modular robots using AI that can adapt to damage and navigate unpredictable terrain, according to a new study

Reuters

3,838,681 просмотров • 3 месяцев назад

Tomorrow’s Science, Today’s Robot A humanoid robot is a type of robot designed to look and act like a human being. It usually has a body structure with a head, torso, arms, and legs, and may be programmed to walk, talk, or perform tasks similar to humans. Some humanoid robots are made mainly for research and testing, while others are used in healthcare, customer service, education, or entertainment. Advanced ones even use artificial intelligence (AI) to recognise speech, facial expressions, and interact naturally with people.
0:57

Tomorrow’s Science, Today’s Robot A humanoid robot is a type of robot designed to look and act like a human being. It usually has a body structure with a head, torso, arms, and legs, and may be programmed to walk, talk, or perform tasks similar to humans. Some humanoid robots are made mainly for research and testing, while others are used in healthcare, customer service, education, or entertainment. Advanced ones even use artificial intelligence (AI) to recognise speech, facial expressions, and interact naturally with people.

NTANetwork

349,326 просмотров • 9 месяцев назад

HDMI (HumanoiD iMitation for Interaction) is a framework enabling humanoid robots to learn whole-body object interaction skills from monocular RGB human videos. It extracts and retargets human poses and object trajectories using GVHMR and LocoMujoco, building reference datasets with contact annotations. The data is used to train an RL policy via robot-object co-tracking. HDMI achieved 67 consecutive door traversals.
0:45

HDMI (HumanoiD iMitation for Interaction) is a framework enabling humanoid robots to learn whole-body object interaction skills from monocular RGB human videos. It extracts and retargets human poses and object trajectories using GVHMR and LocoMujoco, building reference datasets with contact annotations. The data is used to train an RL policy via robot-object co-tracking. HDMI achieved 67 consecutive door traversals.

The Humanoid Hub

17,395 просмотров • 9 месяцев назад

All right, who wants a robot worm? 🪱 Researchers at Case Western Reserve University developed a robot inspired by earthworms. Worms move by using wave-like muscle contractions called peristalsis. This version of the worm-inspired robot has a flexible outer mesh that can continuously change shape. Using this mesh, the robot's fixed parts can move smoothly between each other, providing power and control. This project is referred to as a "soft hyper-redundant robot," due to its highly flexible nature and ability to adapt to various environments. This design could prove useful in scenarios where traditional rigid robots struggle, such as navigating tight spaces or uneven terrain. Please let me know what your thoughts are! 👀 🔔 Hit the bell on my profile to never miss a robot story!
0:51

All right, who wants a robot worm? 🪱 Researchers at Case Western Reserve University developed a robot inspired by earthworms. Worms move by using wave-like muscle contractions called peristalsis. This version of the worm-inspired robot has a flexible outer mesh that can continuously change shape. Using this mesh, the robot's fixed parts can move smoothly between each other, providing power and control. This project is referred to as a "soft hyper-redundant robot," due to its highly flexible nature and ability to adapt to various environments. This design could prove useful in scenarios where traditional rigid robots struggle, such as navigating tight spaces or uneven terrain. Please let me know what your thoughts are! 👀 🔔 Hit the bell on my profile to never miss a robot story!

Lukas Ziegler

24,755 просмотров • 1 год назад

Whether teleoperated or autonomous, whole body movements like picking objects from the ground are challenging for humanoid robots. A UC San Diego paper introduces a framework that combines sim-to-real RL and trajectory optimization for adaptive, real-time whole body control.
1:05

Whether teleoperated or autonomous, whole body movements like picking objects from the ground are challenging for humanoid robots. A UC San Diego paper introduces a framework that combines sim-to-real RL and trajectory optimization for adaptive, real-time whole body control.

The Humanoid Hub

27,879 просмотров • 1 год назад

RoboBall is a spherical robot developed by researchers at Texas A&M University to explore lunar craters. It moves using a pendulum system inside the ball, allowing it to roll and steer in any direction. The robot can reach speeds of up to 20 mph, and researchers are working to make it faster and more autonomous for future space missions.
0:34

RoboBall is a spherical robot developed by researchers at Texas A&M University to explore lunar craters. It moves using a pendulum system inside the ball, allowing it to roll and steer in any direction. The robot can reach speeds of up to 20 mph, and researchers are working to make it faster and more autonomous for future space missions.

Space and Technology

20,739 просмотров • 1 месяц назад

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:
0:46

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

20,051 просмотров • 1 год назад

LimX Dynamics unveiled COSA, a unified brain and body OS for humanoid robots. It lets their OLI robot think and act in real time from walking to manipulating objects using natural language. Cognition and control, fused.
1:18

LimX Dynamics unveiled COSA, a unified brain and body OS for humanoid robots. It lets their OLI robot think and act in real time from walking to manipulating objects using natural language. Cognition and control, fused.

XMAQUINA

15,125 просмотров • 5 месяцев назад

Oli, a humanoid robot by LimX Dynamics, can walk across rough construction debris without losing balance. It can even hit a rock and quickly recover while continuing forward. Using 3D cameras, LiDAR, and sensors, it maps the area and adjusts its steps to move safely.
0:27

Oli, a humanoid robot by LimX Dynamics, can walk across rough construction debris without losing balance. It can even hit a rock and quickly recover while continuing forward. Using 3D cameras, LiDAR, and sensors, it maps the area and adjusts its steps to move safely.

Space and Technology

33,141 просмотров • 2 месяцев назад

Excited to share a new humanoid robot platform we’ve been working on. Berkeley Humanoid is a reliable and low-cost mid-scale research platform for learning-based control. We demonstrate the robot walking on various terrains and dynamic hopping with a simple RL controller.
0:49

Excited to share a new humanoid robot platform we’ve been working on. Berkeley Humanoid is a reliable and low-cost mid-scale research platform for learning-based control. We demonstrate the robot walking on various terrains and dynamic hopping with a simple RL controller.

Qiayuan Liao

80,436 просмотров • 1 год назад

Researchers have developed Humanoid-GPT, a new AI system that helps humanoid robots perform complex movements and tasks. Tested on the Unitree G1 robot, it enables real-time whole-body control and can perform new actions without special training. During demonstrations, the robot successfully carried out a variety of movements and tasks, showing strong potential for real-world applications.
0:28

Researchers have developed Humanoid-GPT, a new AI system that helps humanoid robots perform complex movements and tasks. Tested on the Unitree G1 robot, it enables real-time whole-body control and can perform new actions without special training. During demonstrations, the robot successfully carried out a variety of movements and tasks, showing strong potential for real-world applications.

Space and Technology

22,052 просмотров • 23 дней назад

Boston Dynamics has released a new video showing its Atlas humanoid robot using hand-like grippers to pick up and drop objects.
0:38

Boston Dynamics has released a new video showing its Atlas humanoid robot using hand-like grippers to pick up and drop objects.

CNN

1,266,145 просмотров • 3 лет назад

Turning video into humanoid robot motion! 🤳🏼 Training humanoid robots needs huge amounts of motion data, but real-world capture doesn’t scale. Mocap is expensive, dangerous edge cases are rare, and you can’t ask humans to repeatedly fall or crash. Video2Robot tackles this by converting videos into physics-grounded humanoid simulations. Motion is generated to respect balance, inertia, ground contact, and joint limits, then directly retargeted to robot simulators. One prompt can generate a full humanoid motion sequence, including multi-agent interactions and failure cases like falls or collisions, scenarios that are hard or impossible to capture safely in the real world. The pipeline is model-agnostic and works with existing video generators, making it a practical way to scale data for robots. If robots are going to operate in the real world, they need to be trained on the failures too, not just the perfect demos. Here's the GitHub: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:26

Turning video into humanoid robot motion! 🤳🏼 Training humanoid robots needs huge amounts of motion data, but real-world capture doesn’t scale. Mocap is expensive, dangerous edge cases are rare, and you can’t ask humans to repeatedly fall or crash. Video2Robot tackles this by converting videos into physics-grounded humanoid simulations. Motion is generated to respect balance, inertia, ground contact, and joint limits, then directly retargeted to robot simulators. One prompt can generate a full humanoid motion sequence, including multi-agent interactions and failure cases like falls or collisions, scenarios that are hard or impossible to capture safely in the real world. The pipeline is model-agnostic and works with existing video generators, making it a practical way to scale data for robots. If robots are going to operate in the real world, they need to be trained on the failures too, not just the perfect demos. Here's the GitHub: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

59,708 просмотров • 6 месяцев назад

Researchers at Duke University developed Argus, a spherical robot with 20 legs and 20 eye-like sensors that can see and move in any direction. Using a concept called dynamic symmetry, it stays balanced and agile while traveling across rough terrain and climbing obstacles. The robot can also track objects and keep working even if some of its legs or sensors fail, making it useful for exploring dangerous environments and other planets.
0:29

Researchers at Duke University developed Argus, a spherical robot with 20 legs and 20 eye-like sensors that can see and move in any direction. Using a concept called dynamic symmetry, it stays balanced and agile while traveling across rough terrain and climbing obstacles. The robot can also track objects and keep working even if some of its legs or sensors fail, making it useful for exploring dangerous environments and other planets.

Space and Technology

19,688 просмотров • 28 дней назад

A humanoid robot policy trained solely on synthetic data generated by a world model. Research Scientist Joel Jang presents NVIDIA's DreamGen pipeline: ⦿ Post-train the world model Cosmos-Predict2 with a small set of real teleoperation demos. ⦿ Prompt the world model to generate synthetic video data with verbs and scenarios not used in the world model’s post-training. ⦿ Auto-label synthetic video data with action sequences. ⦿ Train robot policies using only synthetic data. That's it. Deploy zero-shot to a real humanoid robot.
2:05

A humanoid robot policy trained solely on synthetic data generated by a world model. Research Scientist Joel Jang presents NVIDIA's DreamGen pipeline: ⦿ Post-train the world model Cosmos-Predict2 with a small set of real teleoperation demos. ⦿ Prompt the world model to generate synthetic video data with verbs and scenarios not used in the world model’s post-training. ⦿ Auto-label synthetic video data with action sequences. ⦿ Train robot policies using only synthetic data. That's it. Deploy zero-shot to a real humanoid robot.

The Humanoid Hub

20,968 просмотров • 1 год назад

If you see this, post a robot. Or a video of you controlling a robot using a Steam Deck 🤘 (Using #ROS and Foxglove - blog coming soon)
0:45

If you see this, post a robot. Or a video of you controlling a robot using a Steam Deck 🤘 (Using #ROS and Foxglove - blog coming soon)

Aditya Kamath

24,195 просмотров • 2 лет назад