Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

A generalist model, not a dedicated robot policy, pulled off physical control by reasoning and using tools. Here's the four-step approach Gemini 4 figured out, given high-level instructions and the overall task: 1. Watched a human throw, and mapped the motion to its own joints. 2. Used its cameras...

TheHumanoidHub's profile picture

The Humanoid Hub

118,086 subscribers

10,155 görüntüleme • 15 gün önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

4 Yorum

Rackham Rishel profil fotoğrafı
Rackham Rishel15 gün önce

Watching a person move and mapping that onto its own joints without a dedicated robot policy is quietly enormous

Brian Bellia profil fotoğrafı
Brian Bellia15 gün önce

One thing Apptronik have definitely got right with their humanoid, in my opinion, is the head, which I believe is very important. I love the two camera eyes and the soft flashing LED mouth when it speaks. 👍👍👍

True North Take profil fotoğrafı
True North Take15 gün önce

A general model doing physical control via tool use is a big shift from bespoke policies. If that holds, the value moves to hardware makers like Apptronik and component suppliers. Curious how latency looks in real time.

Fabien Musty profil fotoğrafı
Fabien Musty15 gün önce

Generalist models are at least the glue that will make humanoids coherent in all situations. They need a relatable and flexible default behavior in-between learned skills.

Benzer Videolar

Gemini 4 Argon taught a robot to play cornhole just by watching a video. It mapped the physics, coded its own simulation, and taught Apptronik's Apollo humanoid to sink 7 throws in a row.
1:43

Gemini 4 Argon taught a robot to play cornhole just by watching a video. It mapped the physics, coded its own simulation, and taught Apptronik's Apollo humanoid to sink 7 throws in a row.

Google DeepMind

273,928 görüntüleme • 15 gün önce

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

191,366 görüntüleme • 4 ay önce

I turned Asimov's open-source Asimov 1 into an interactive 3D robotics workshop. Built from 1,184 real CAD parts, with Menlo's own walking policy running in a live physics simulation in your browser. 🟠 BUILD the robot using Menlo's assembly instructions. 🟠 UNDERSTAND its mechanisms, including the parallel ankle linkage. 🟠 TEST its walking policy, apply a push, and freeze the simulation to inspect every joint. Built with Three.js. Fully open-source. Try it yourself:
0:45

I turned Asimov's open-source Asimov 1 into an interactive 3D robotics workshop. Built from 1,184 real CAD parts, with Menlo's own walking policy running in a live physics simulation in your browser. 🟠 BUILD the robot using Menlo's assembly instructions. 🟠 UNDERSTAND its mechanisms, including the parallel ankle linkage. 🟠 TEST its walking policy, apply a push, and freeze the simulation to inspect every joint. Built with Three.js. Fully open-source. Try it yourself:

Sergej Stein

82,774 görüntüleme • 7 gün önce

Control a robot in simulation with the Gemini Robotics Embodied Reasoning model 🤖 Direct tasks like object localization and placement by simply prompting a robotic arm to pick up and place objects.
0:20

Control a robot in simulation with the Gemini Robotics Embodied Reasoning model 🤖 Direct tasks like object localization and placement by simply prompting a robotic arm to pick up and place objects.

Google AI Developers

1,297,082 görüntüleme • 8 ay önce

i gave astra a robot, a paint brush, and a camera then asked it to paint the golden gate bridge in real life! it figured out how to control the robot, and progressively got better throughout its attempts. the timelapse is sick
1:08

i gave astra a robot, a paint brush, and a camera then asked it to paint the golden gate bridge in real life! it figured out how to control the robot, and progressively got better throughout its attempts. the timelapse is sick

thijs

5,007,959 görüntüleme • 1 ay önce

A robot stole the spotlight with its killer dance moves during an Erling Haaland lookalike contest in Miami. Despite its best efforts, the robot Haaland did not win, and the title went to a human.
0:50

A robot stole the spotlight with its killer dance moves during an Erling Haaland lookalike contest in Miami. Despite its best efforts, the robot Haaland did not win, and the title went to a human.

ABC News

61,086 görüntüleme • 3 ay önce

Additionally, looking towards the future, we’re releasing PARTNR: a benchmark for Planning And Reasoning Tasks in humaN-Robot collaboration. Built on Habitat 3.0, it’s the largest benchmark of its kind to study and evaluate human-robot collaboration in household activities By providing a standardized benchmark and dataset we hope to enable new research on robots that can not only operate in isolation, but in collaboration with people. Details and code ➡️
1:01

Additionally, looking towards the future, we’re releasing PARTNR: a benchmark for Planning And Reasoning Tasks in humaN-Robot collaboration. Built on Habitat 3.0, it’s the largest benchmark of its kind to study and evaluate human-robot collaboration in household activities By providing a standardized benchmark and dataset we hope to enable new research on robots that can not only operate in isolation, but in collaboration with people. Details and code ➡️

AI at Meta

20,244 görüntüleme • 2 yıl önce

The future of sports is evolving in China. A robot just played tennis against a human at the World Humanoid Robot Games in Beijing with zero human control, tracking the ball and returning shots entirely on its own. How long before robots have their own Olympics?
1:19

The future of sports is evolving in China. A robot just played tennis against a human at the World Humanoid Robot Games in Beijing with zero human control, tracking the ball and returning shots entirely on its own. How long before robots have their own Olympics?

Coin Bureau

57,188 görüntüleme • 2 ay önce

An interactive world model developed by NVIDIA in collaboration with academic partners. - DreamDojo turns egocentric human video data into physical intelligence. - Human data is more scalable than robotics data but lacks action labels. - To solve this, a dedicated action model extracts latent actions by identifying physics and motion deltas between frames. Training - A massive 44k hours of video data are used for pre-training. - Post-training on small-scale robot datasets maps human physics to specific robot embodiments. - An additional distillation stage converts the model into an autoregressive, few-step diffusion model, enabling real-time, action-controllable simulation. Primary Use Cases - Live Teleoperation: Controlling a robot inside a world simulation in real-time. - Model-based Planning: Previewing and curating the best actions for improved success. - Policy Evaluation: Testing robot policies in realistic, out-of-distribution scenarios. Everything that's open-sourced: weights, code, post-training dataset, eval set, and details to reproduce.
1:14

An interactive world model developed by NVIDIA in collaboration with academic partners. - DreamDojo turns egocentric human video data into physical intelligence. - Human data is more scalable than robotics data but lacks action labels. - To solve this, a dedicated action model extracts latent actions by identifying physics and motion deltas between frames. Training - A massive 44k hours of video data are used for pre-training. - Post-training on small-scale robot datasets maps human physics to specific robot embodiments. - An additional distillation stage converts the model into an autoregressive, few-step diffusion model, enabling real-time, action-controllable simulation. Primary Use Cases - Live Teleoperation: Controlling a robot inside a world simulation in real-time. - Model-based Planning: Previewing and curating the best actions for improved success. - Policy Evaluation: Testing robot policies in realistic, out-of-distribution scenarios. Everything that's open-sourced: weights, code, post-training dataset, eval set, and details to reproduce.

The Humanoid Hub

11,575 görüntüleme • 8 ay önce

Want to see Gemini 2.0 Flash Thinking in action? Check out this demo where the model solves a physics problem and explains its reasoning.
1:24

Want to see Gemini 2.0 Flash Thinking in action? Check out this demo where the model solves a physics problem and explains its reasoning.

Jeff Dean

105,766 görüntüleme • 1 yıl önce

WUJI is showcasing its dexterous robotic hands at IROS 2026, demonstrating how human hand movements can control a robot through glove-based teleoperation. Its WUJI Hand 2 can also perform precise tasks like pen spinning using a policy trained in simulation and transferred to a real robot. These demonstrations highlight advances in robotic finger coordination, dexterity, and fine manipulation.
0:29

WUJI is showcasing its dexterous robotic hands at IROS 2026, demonstrating how human hand movements can control a robot through glove-based teleoperation. Its WUJI Hand 2 can also perform precise tasks like pen spinning using a policy trained in simulation and transferred to a real robot. These demonstrations highlight advances in robotic finger coordination, dexterity, and fine manipulation.

Space and Technology

12,420 görüntüleme • 17 gün önce

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

138,017 görüntüleme • 2 ay önce

We trained a robot dog to balance and walk on top of a yoga ball purely in simulation, and then transfer zero-shot to the real world. No fine-tuning. Just works. I’m excited to announce DrEureka, an LLM agent that writes code to train robot skills in simulation, and writes more code to bridge the difficult simulation-reality gap. It fully automates the pipeline from new skill learning to real-world deployment. The Yoga ball task is particularly hard because it is not possible to accurately simulate the bouncy ball surface. Yet DrEureka has no trouble searching over a vast space of sim-to-real configurations, and enables the dog to steer the ball on various terrains, even walking sideways! Traditionally, the sim-to-real transfer is achieved by domain randomization, a tedious process that requires expert human roboticists to stare at every parameter and adjust by hand. Frontier LLMs like GPT-4 have tons of built-in physical intuition for friction, damping, stiffness, gravity, etc. We are (mildly) surprised to find that DrEureka can tune these parameters competently and explain its reasoning well. DrEureka builds on our prior work Eureka, the algorithm that teaches a 5-finger robot hand to do pen spinning. It takes one step further on our quest to automate the entire robot learning pipeline by an AI agent system. One model that outputs strings will supervise another model that outputs torque control. We open-source everything! Welcome you all to check out the paper, more videos, and try the codebase today: Code:
0:24

We trained a robot dog to balance and walk on top of a yoga ball purely in simulation, and then transfer zero-shot to the real world. No fine-tuning. Just works. I’m excited to announce DrEureka, an LLM agent that writes code to train robot skills in simulation, and writes more code to bridge the difficult simulation-reality gap. It fully automates the pipeline from new skill learning to real-world deployment. The Yoga ball task is particularly hard because it is not possible to accurately simulate the bouncy ball surface. Yet DrEureka has no trouble searching over a vast space of sim-to-real configurations, and enables the dog to steer the ball on various terrains, even walking sideways! Traditionally, the sim-to-real transfer is achieved by domain randomization, a tedious process that requires expert human roboticists to stare at every parameter and adjust by hand. Frontier LLMs like GPT-4 have tons of built-in physical intuition for friction, damping, stiffness, gravity, etc. We are (mildly) surprised to find that DrEureka can tune these parameters competently and explain its reasoning well. DrEureka builds on our prior work Eureka, the algorithm that teaches a 5-finger robot hand to do pen spinning. It takes one step further on our quest to automate the entire robot learning pipeline by an AI agent system. One model that outputs strings will supervise another model that outputs torque control. We open-source everything! Welcome you all to check out the paper, more videos, and try the codebase today: Code:

Jim Fan

909,637 görüntüleme • 2 yıl önce

The next frontier of autonomous driving is unlocked by reasoning models. NVIDIA Alpamayo brings together open AI models with reasoning capabilities, closed-loop simulation tools, and massive real-world driving datasets. Alpamayo 1 is a vision–language–action model that explains its own decisions through explicit reasoning traces, enabling trustworthy, humanlike decision-making. Together with NVIDIA’s Physical AI dataset and AlpaSim simulation, Alpamayo provides the tools and scale required to enable level 4 autonomous vehicles. ▶️ Watch now:
0:45

The next frontier of autonomous driving is unlocked by reasoning models. NVIDIA Alpamayo brings together open AI models with reasoning capabilities, closed-loop simulation tools, and massive real-world driving datasets. Alpamayo 1 is a vision–language–action model that explains its own decisions through explicit reasoning traces, enabling trustworthy, humanlike decision-making. Together with NVIDIA’s Physical AI dataset and AlpaSim simulation, Alpamayo provides the tools and scale required to enable level 4 autonomous vehicles. ▶️ Watch now:

NVIDIA DRIVE

35,324 görüntüleme • 9 ay önce

UBTech Robotics has showcased its humanoid robot Walker S2 playing tennis with a human. Using real-time vision sensors, it tracks the ball, adjusts its position, and returns shots with good accuracy. The robot can also swap its own batteries, allowing it to operate continuously without human help.
0:33

UBTech Robotics has showcased its humanoid robot Walker S2 playing tennis with a human. Using real-time vision sensors, it tracks the ball, adjusts its position, and returns shots with good accuracy. The robot can also swap its own batteries, allowing it to operate continuously without human help.

Space and Technology

16,121 görüntüleme • 5 ay önce

An LLM robot agent’s success rate goes up as it practices. Did it learn anything, or did it just try more often? And do the skills and memories it saves still help on new tasks, in a new simulator, on a real robot? We built SEAR to answer both. To our knowledge, it’s the first large scale controlled study of self-evolving robot agents. The paper is now on arXiv 📄 The agent improves a robot in one of three ways: it writes code that becomes the policy, it acts live in the control loop, or it trains its own VLA. 7 frontier LLMs, 330 sim tasks, 5 real-robot tasks, 4+ years of agent runtime, with a matched control for every comparison and a sealed judge on unseen scenes. A few findings surprised us 🧵 1/7
0:23

An LLM robot agent’s success rate goes up as it practices. Did it learn anything, or did it just try more often? And do the skills and memories it saves still help on new tasks, in a new simulator, on a real robot? We built SEAR to answer both. To our knowledge, it’s the first large scale controlled study of self-evolving robot agents. The paper is now on arXiv 📄 The agent improves a robot in one of three ways: it writes code that becomes the policy, it acts live in the control loop, or it trains its own VLA. 7 frontier LLMs, 330 sim tasks, 5 real-robot tasks, 4+ years of agent runtime, with a matched control for every comparison and a sealed judge on unseen scenes. A few findings surprised us 🧵 1/7

Xinyi Wang

16,971 görüntüleme • 13 gün önce

I built this little #robot I ordered from Hugging Face Pollen Robotics and connected it to the Google Gemini AI model through its API gateway. The robot wanted its own personality - so I gave it an #ATX (Texas) vibe and you can see the result in the video. Really awesome - it even answers questions and carries on a conversion. The vision and hearing are great - it can identify and follow what it sees (with a reasonable delay). My next goal is to get it to work with a 100% local AI model. Specs: 2 cameras, 4 microphones, a speaker, and a wifi interface to a Raspberry Pi built-in controller. I plan to demo it at the InnoTech #InnoTechAUS event on May 12th. Texas McCombs Austin Tech Council TechRanch
2:44

I built this little #robot I ordered from Hugging Face Pollen Robotics and connected it to the Google Gemini AI model through its API gateway. The robot wanted its own personality - so I gave it an #ATX (Texas) vibe and you can see the result in the video. Really awesome - it even answers questions and carries on a conversion. The vision and hearing are great - it can identify and follow what it sees (with a reasonable delay). My next goal is to get it to work with a 100% local AI model. Specs: 2 cameras, 4 microphones, a speaker, and a wifi interface to a Raspberry Pi built-in controller. I plan to demo it at the InnoTech #InnoTechAUS event on May 12th. Texas McCombs Austin Tech Council TechRanch

Russ Finney

29,103 görüntüleme • 5 ay önce

A garage collapsed in lower Manhattan, and the FDNY sent its $75,000 robot dog in. Watch to the end and see what spending 75k on a robot dog gets you.
0:20

A garage collapsed in lower Manhattan, and the FDNY sent its $75,000 robot dog in. Watch to the end and see what spending 75k on a robot dog gets you.

Read Jackson Rising

1,639,638 görüntüleme • 3 yıl önce