正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Reality of robotics: humanoid kung fu is solved before they can open doors with RGB. Here we are. Introducing the frontier of sim2real at NVIDIA GEAR. 100% sim data. RGB input only. Code name: 𝗗𝗼𝗼𝗿𝗠𝗮𝗻. We are opening the sim-to-real door. 🧵

Haoru Xue

2,972 subscribers

373,660 次观看 • 8 个月前 •via X (Twitter)

艺术教育科学技术

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Are you opening doors for humanoids… or is your humanoid opening doors for you? Introducing DoorMan, our humanoid door-opening system powered by: • end-to-end RGB pixel-to-action control • large-scale simulation-only training • teacher–student-bootstrap RL This took our team 6 months of relentless iteration. I wasn’t sure it could be done — now it’s real. Website: ArXiv:

Are you opening doors for humanoids… or is your humanoid opening doors for you? Introducing DoorMan, our humanoid door-opening system powered by: • end-to-end RGB pixel-to-action control • large-scale simulation-only training • teacher–student-bootstrap RL This took our team 6 months of relentless iteration. I wasn’t sure it could be done — now it’s real. Website: ArXiv:

Tairan He

31,920 次观看 • 8 个月前

Robotics: coding agents’ next frontier. So how good are they? We introduce CaP-X: an open-source framework and benchmark for coding agents, where they write code for robot perception and control, execute it on sim and real robots, observe the outcomes, and iteratively improve code reliability. From NVIDIA Berkeley AI Research CMU Robotics Institute Stanford AI Lab 🧵

Robotics: coding agents’ next frontier. So how good are they? We introduce CaP-X: an open-source framework and benchmark for coding agents, where they write code for robot perception and control, execute it on sim and real robots, observe the outcomes, and iteratively improve code reliability. From NVIDIA Berkeley AI Research CMU Robotics Institute Stanford AI Lab 🧵

Max Fu

176,531 次观看 • 4 个月前

Trained a humanoid entirely in a 3D scan of the office. Zero real-world fine-tuning. It just walked in and worked. RL needs hundreds of thousands of attempts, and real robots can't afford to crash. A misjudged gap or a glass door collision breaks hardware and costs hours resetting. So you train in a sim. But sim policies usually train on randomized, untextured geometry; depth is easy to fake. The robot learns structure, not the real world: no materials, no lighting, no idea what anything actually is. RGB cameras carry all of that but training RGB policies in generic fake worlds won’t generalize to the real world. Niantic Spatial 🌎 Scaniverse reconstructs your scan of the real deployment site. One 360° camera walkthrough → photorealistic 3D Gaussian splat at metric scale → collision mesh pulled from the same reconstruction, so vision and physics match exactly. Drops straight into NVIDIA Isaac Sim/Lab, no manual conversion. Flexion simulation-first approach then seamlessly enables the training of RGB-only nav policies inside that reconstruction. With added domain randomization + large image encoders for robustness, this deploys straight to hardware. No real-world fine-tuning. Deployment: months of on-site adaptation → days. Tune into the NVIDIA livestream on 12 August to hear how these companies are closing the sim2real gap: NVIDIA Robotics ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Trained a humanoid entirely in a 3D scan of the office. Zero real-world fine-tuning. It just walked in and worked. RL needs hundreds of thousands of attempts, and real robots can't afford to crash. A misjudged gap or a glass door collision breaks hardware and costs hours resetting. So you train in a sim. But sim policies usually train on randomized, untextured geometry; depth is easy to fake. The robot learns structure, not the real world: no materials, no lighting, no idea what anything actually is. RGB cameras carry all of that but training RGB policies in generic fake worlds won’t generalize to the real world. Niantic Spatial 🌎 Scaniverse reconstructs your scan of the real deployment site. One 360° camera walkthrough → photorealistic 3D Gaussian splat at metric scale → collision mesh pulled from the same reconstruction, so vision and physics match exactly. Drops straight into NVIDIA Isaac Sim/Lab, no manual conversion. Flexion simulation-first approach then seamlessly enables the training of RGB-only nav policies inside that reconstruction. With added domain randomization + large image encoders for robustness, this deploys straight to hardware. No real-world fine-tuning. Deployment: months of on-site adaptation → days. Tune into the NVIDIA livestream on 12 August to hear how these companies are closing the sim2real gap: NVIDIA Robotics ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

118,434 次观看 • 14 天前

For robots to be useful, they must be able to interact with a wide variety of environments; and yet, scaling interaction data is difficult, expensive, and time consuming. Instead, much research revolves around sim-to-real manipulation — but mostly this has not been mobile manipulation. Recently, though, this has begun to change. Two recent papers from Tairan He and Haoru Xue show us how to unlock the potential of this technique, building policies which, without any real data at all, can move objects around in the world and open doors in the real world with a humanoid robot. Watch Episode #60 of RoboPapers now to learn more, hosted by Chris Paxton and Jiafei Duan. In this episode, we cover two papers:. First is VIRAL: Visual Sim-to-Real at Scale for Humanoid Loco-Manipulation; and second is DoorMan: Opening the Sim-to-Real Door for Humanoid Pixel-to-Action Policy Transfer.

For robots to be useful, they must be able to interact with a wide variety of environments; and yet, scaling interaction data is difficult, expensive, and time consuming. Instead, much research revolves around sim-to-real manipulation — but mostly this has not been mobile manipulation. Recently, though, this has begun to change. Two recent papers from Tairan He and Haoru Xue show us how to unlock the potential of this technique, building policies which, without any real data at all, can move objects around in the world and open doors in the real world with a humanoid robot. Watch Episode #60 of RoboPapers now to learn more, hosted by Chris Paxton and Jiafei Duan. In this episode, we cover two papers:. First is VIRAL: Visual Sim-to-Real at Scale for Humanoid Loco-Manipulation; and second is DoorMan: Opening the Sim-to-Real Door for Humanoid Pixel-to-Action Policy Transfer.

RoboPapers

30,767 次观看 • 6 个月前

A big part of scaling robot learning to solve real-world problems is that we somehow need to get enough diverse, high-quality data to train our robots to perform useful things. GPT and its fellow large language models were bootstrapped and proved out on a massive dataset of real-world language data. Unfortunately, despite our best efforts, similarly massive datasets don’t really exist for robotics — so, in our unending pursuit of high-quality, useful data, we turn to simulation. I compared a couple recent works on sim-to-real robot manipulation, which discuss how to train perception-driven manipulation policies in simulation, in such a way that they’re useful in the real world. - DextraH-RGB, from NVIDIA - Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation, also from NVIDIA — specifically the GEAR lab - Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids, another GEAR lab paper - Local Policies Enable Zero-shot Long-Horizon Manipulation, from CMU (video from DextrAH-RGB)

A big part of scaling robot learning to solve real-world problems is that we somehow need to get enough diverse, high-quality data to train our robots to perform useful things. GPT and its fellow large language models were bootstrapped and proved out on a massive dataset of real-world language data. Unfortunately, despite our best efforts, similarly massive datasets don’t really exist for robotics — so, in our unending pursuit of high-quality, useful data, we turn to simulation. I compared a couple recent works on sim-to-real robot manipulation, which discuss how to train perception-driven manipulation policies in simulation, in such a way that they’re useful in the real world. - DextraH-RGB, from NVIDIA - Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation, also from NVIDIA — specifically the GEAR lab - Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids, another GEAR lab paper - Local Policies Enable Zero-shot Long-Horizon Manipulation, from CMU (video from DextrAH-RGB)

Chris Paxton

20,486 次观看 • 1 年前

Very excited to share our first public release after I joined Robbyant! We present Lingbot-Depth 👀 — a state-of-the-art depth foundation model trained with RGB-D MAE on millions of real & simulated RGBD pairs. 🔹 Camera depths as natural masks for RGB-D MAE modeling 🔹 Large-scale real + sim RGBD data curation pipeline What surprised us most: ✨ Significant improvement on transparent, reflective surfaces, and thin structures — traditionally the hardest cases for depth models. 👇These are some of hard causal-capture images we tested on. The results are pretty good! #DepthEstimation #FoundationModels #EmbodiedAI #3DVision #Robotics #RobbyAnt

Very excited to share our first public release after I joined Robbyant! We present Lingbot-Depth 👀 — a state-of-the-art depth foundation model trained with RGB-D MAE on millions of real & simulated RGBD pairs. 🔹 Camera depths as natural masks for RGB-D MAE modeling 🔹 Large-scale real + sim RGBD data curation pipeline What surprised us most: ✨ Significant improvement on transparent, reflective surfaces, and thin structures — traditionally the hardest cases for depth models. 👇These are some of hard causal-capture images we tested on. The results are pretty good! #DepthEstimation #FoundationModels #EmbodiedAI #3DVision #Robotics #RobbyAnt

Yinghao Xu

22,664 次观看 • 6 个月前

Zero teleoperation. Zero real-world data. ➔ Autonomous humanoid loco-manipulation in reality. Introducing VIRAL: Visual Sim-to-Real at Scale. We achieved 54 autonomous cycles (walk, stand, place, pick, turn) using a simple recipe: 1. RL 2. Simulation 3. GPUs Website: Arxiv: Deep dive with me: 🧵

Zero teleoperation. Zero real-world data. ➔ Autonomous humanoid loco-manipulation in reality. Introducing VIRAL: Visual Sim-to-Real at Scale. We achieved 54 autonomous cycles (walk, stand, place, pick, turn) using a simple recipe: 1. RL 2. Simulation 3. GPUs Website: Arxiv: Deep dive with me: 🧵

Tairan He

266,215 次观看 • 9 个月前

Introducing Zeroth-01 Bot: the world's smallest open-source end-to-end humanoid robot starting at $350! Fully open-source, including hardware, SDK, sim environments & more. Zeroth-01 is the most hackable humanoid to-date! Join⬇️to shape the future of accessible robotics w/ us

Introducing Zeroth-01 Bot: the world's smallest open-source end-to-end humanoid robot starting at $350! Fully open-source, including hardware, SDK, sim environments & more. Zeroth-01 is the most hackable humanoid to-date! Join⬇️to shape the future of accessible robotics w/ us

JX

143,904 次观看 • 1 年前

We talked to Ritvik Singh about how you can train sim-to-real dexterous manipulation policies using NVIDIA Isaac. This robot is grasping objects using pure RGB stereo: take in images from a camera pair and predict what to do, all without training in the real world.

We talked to Ritvik Singh about how you can train sim-to-real dexterous manipulation policies using NVIDIA Isaac. This robot is grasping objects using pure RGB stereo: take in images from a camera pair and predict what to do, all without training in the real world.

Chris Paxton

20,067 次观看 • 1 年前

Introducing Bitlight RLN, the first product-ready desktop client that brings RGB asset issuance and transfer to the Lightning Network. We are making programmable Bitcoin assets instant, cheap, and real. Issue assets. Open RGB channels. Transfer instantly over Lightning. Settle on-chain. Not a testnet demo. Not a proof of concept. A real product. Watch the full walkthrough.

Introducing Bitlight RLN, the first product-ready desktop client that brings RGB asset issuance and transfer to the Lightning Network. We are making programmable Bitcoin assets instant, cheap, and real. Issue assets. Open RGB channels. Transfer instantly over Lightning. Settle on-chain. Not a testnet demo. Not a proof of concept. A real product. Watch the full walkthrough.

Bitlight Labs⚡️

67,331 次观看 • 5 个月前

Bitlight Wallet Upgraded to v0.0.12.1 We are pleased to inform everyone that Bitlight Wallet has reached a new milestone: Bitcoin mainnet. This progress marks Bitlight Wallet as a fully functional Bitcoin wallet and is our final step towards the RGB protocol mainnet. The RGB protocol is not a blockchain, so strictly speaking, there is no such thing as an RGB mainnet. However, we must work together with Dr. Maxim Maxim Orlovsky and our partners at the LNP/BP Association LNP/BP Labs to complete the audit of the RGB code and ensure the security of RGB assets before pushing the RGB protocol to the mainnet. This choice is a responsible approach for the Bitlight Labs Bitlight Labs⚡️ community, Bitlight Wallet users, and all participants in the RGB ecosystem. As Bitlight Wallet supports the #Bitcoin mainnet, we will launch a Bitcoin mainnet UTXO creation task. Creating UTXOs is a prerequisite for creating RGB20 assets, so we hope to guide everyone in preparing for the RGB mainnet launch through this task. The wind is approaching, and the RGB ship is about to set sail. Make Bitcoin Smart. #RGB #LightningNetwork #BitlightLabs #BitlightWallet #MakeBitcoinSmart #MBS

Bitlight Wallet Upgraded to v0.0.12.1 We are pleased to inform everyone that Bitlight Wallet has reached a new milestone: Bitcoin mainnet. This progress marks Bitlight Wallet as a fully functional Bitcoin wallet and is our final step towards the RGB protocol mainnet. The RGB protocol is not a blockchain, so strictly speaking, there is no such thing as an RGB mainnet. However, we must work together with Dr. Maxim Maxim Orlovsky and our partners at the LNP/BP Association LNP/BP Labs to complete the audit of the RGB code and ensure the security of RGB assets before pushing the RGB protocol to the mainnet. This choice is a responsible approach for the Bitlight Labs Bitlight Labs⚡️ community, Bitlight Wallet users, and all participants in the RGB ecosystem. As Bitlight Wallet supports the #Bitcoin mainnet, we will launch a Bitcoin mainnet UTXO creation task. Creating UTXOs is a prerequisite for creating RGB20 assets, so we hope to guide everyone in preparing for the RGB mainnet launch through this task. The wind is approaching, and the RGB ship is about to set sail. Make Bitcoin Smart. #RGB #LightningNetwork #BitlightLabs #BitlightWallet #MakeBitcoinSmart #MBS

Bitlight Wallet⚡️

88,897 次观看 • 2 年前

The "sim-to-real" gap just got a massive 2,300m² bridge. 🤖🏗️ NEURA Robotics and TUM are launching the TUM RoboGym at Munich Airport—Europe’s largest training center for Physical AI. Starting mid-2026, a fleet of humanoid robots will begin real-world training to fuel the Neuraverse ecosystem with high-quality, sovereign data.

The "sim-to-real" gap just got a massive 2,300m² bridge. 🤖🏗️ NEURA Robotics and TUM are launching the TUM RoboGym at Munich Airport—Europe’s largest training center for Physical AI. Starting mid-2026, a fleet of humanoid robots will begin real-world training to fuel the Neuraverse ecosystem with high-quality, sovereign data.

Humanoids daily

25,560 次观看 • 5 个月前

Historically, RL policies for robots have been trained in synthetic, untextured environments, limiting perceptive policies to depth images where the sim-to-real gap is manageable. RGB has always had more potential, but leveraging it to train policies in simulation remained an open problem. Partnering with Niantic Spatial 🌎 and NVIDIA Robotics, we built a pipeline that addresses exactly that. We can now scan a real deployment site with off-the-shelf hardware, reconstruct it into a photorealistic Gaussian splat, and run massively parallel RL training. The policies trained in our Gym environment then transfer zero-shot to the real robot and environments they were trained for. This enables faster deployment of more capable and robust policies for the end user. The new resulting capabilities are a big step towards solving sim-to-real and also apply well beyond navigation. Read the full technical breakdown on our blog; link in the comments. #HumanoidRobots #Flexion #NianticSpatial #NVIDIA

Historically, RL policies for robots have been trained in synthetic, untextured environments, limiting perceptive policies to depth images where the sim-to-real gap is manageable. RGB has always had more potential, but leveraging it to train policies in simulation remained an open problem. Partnering with Niantic Spatial 🌎 and NVIDIA Robotics, we built a pipeline that addresses exactly that. We can now scan a real deployment site with off-the-shelf hardware, reconstruct it into a photorealistic Gaussian splat, and run massively parallel RL training. The policies trained in our Gym environment then transfer zero-shot to the real robot and environments they were trained for. This enables faster deployment of more capable and robust policies for the end user. The new resulting capabilities are a big step towards solving sim-to-real and also apply well beyond navigation. Read the full technical breakdown on our blog; link in the comments. #HumanoidRobots #Flexion #NianticSpatial #NVIDIA

Flexion

71,773 次观看 • 1 个月前

Data is the core bottleneck for robotics, here is the solution: Introducing MicroAGI00: We open sourced 1M+ frames of egocentric human long horizon mobile manipulation data. Scaling to 300M by Dec '25 and 100B frames Q4 2026 dm if you want your robot to wipe your office 🧵

Data is the core bottleneck for robotics, here is the solution: Introducing MicroAGI00: We open sourced 1M+ frames of egocentric human long horizon mobile manipulation data. Scaling to 300M by Dec '25 and 100B frames Q4 2026 dm if you want your robot to wipe your office 🧵

Bercan

39,646 次观看 • 10 个月前

TESTING UPDATE: BitMask is RGB main-net ready. The video below is a bitcoin, RGB20 mainnet transfers between BitMask and Iris wallet by Bitfinex Labs. Bitfinex RGB Protocol Association Special thanks to all the devs in different teams working in collaboration to make RGB 0.11 the future of bitcoin utility. the assets in this video are only for internal testing. HERE IS WHAT TO EXPECT thread🧵

TESTING UPDATE: BitMask is RGB main-net ready. The video below is a bitcoin, RGB20 mainnet transfers between BitMask and Iris wallet by Bitfinex Labs. Bitfinex RGB Protocol Association Special thanks to all the devs in different teams working in collaboration to make RGB 0.11 the future of bitcoin utility. the assets in this video are only for internal testing. HERE IS WHAT TO EXPECT thread🧵

BitMask ⚡

10,129 次观看 • 9 个月前

Gemini Robotics 2 by Google DeepMind uses sim-only post-training on a mixed-data base model to handle automotive kitting. Contact-rich tasks like these have long been considered one of the hardest challenges in Sim2Real. Gemini Robotics 2 shows simulation can work even here. General robot intelligence needs much more data than real-robot collection alone can provide. Simulation has proven to be an effective way to fill that gap.

Gemini Robotics 2 by Google DeepMind uses sim-only post-training on a mixed-data base model to handle automotive kitting. Contact-rich tasks like these have long been considered one of the hardest challenges in Sim2Real. Gemini Robotics 2 shows simulation can work even here. General robot intelligence needs much more data than real-robot collection alone can provide. Simulation has proven to be an effective way to fill that gap.

Axis Robotics

14,454 次观看 • 12 天前

Big news! World Labs' Marble is officially compatible with NVIDIA Robotics' Isaac Sim. Instead of showcasing their highlight reel, our team at Lightwheel created a full environment from a 360 pano using Marble and showed you can train directly in sim. The only non-generated assets are the robot arms, coffee, and bowl. Everything else was generated with Marble. Not sure how to do this yourself? NVIDIA wrote a technical blog with full instructions. You will learn how to: 1. Export scenes from World Labs' Marble as Gaussian splats 2. Convert to USD using NVIDIA Omniverse NuRec 3. Import into NVIDIA Isaac Sim 4. Add a robot and run the simulation Read the guide ➡️ #WorldModels #Robotics

Big news! World Labs' Marble is officially compatible with NVIDIA Robotics' Isaac Sim. Instead of showcasing their highlight reel, our team at Lightwheel created a full environment from a 360 pano using Marble and showed you can train directly in sim. The only non-generated assets are the robot arms, coffee, and bowl. Everything else was generated with Marble. Not sure how to do this yourself? NVIDIA wrote a technical blog with full instructions. You will learn how to: 1. Export scenes from World Labs' Marble as Gaussian splats 2. Convert to USD using NVIDIA Omniverse NuRec 3. Import into NVIDIA Isaac Sim 4. Add a robot and run the simulation Read the guide ➡️ #WorldModels #Robotics

Jonathan Stephens

13,783 次观看 • 8 个月前

The next frontier of AI is physical. 🤖 From simulation to synthetic data, developers are training robots to understand the real world with NVIDIA Cosmos, Isaac simulation frameworks and open-source physics engine, Newton. Watch the video to see how partners like Hon Hai Technology Group (Foxconn), Hexagon, Humanoid, Noble Machines, and Skild AI are building the future. 🎥

The next frontier of AI is physical. 🤖 From simulation to synthetic data, developers are training robots to understand the real world with NVIDIA Cosmos, Isaac simulation frameworks and open-source physics engine, Newton. Watch the video to see how partners like Hon Hai Technology Group (Foxconn), Hexagon, Humanoid, Noble Machines, and Skild AI are building the future. 🎥

NVIDIA Robotics

21,664 次观看 • 4 个月前

We need to stop mass immigration. Not reduce it to 70%. Im saying we bring it down to Zero until we can take care of our ow.n first. Canadians First! We need to be more selective with who we bring into the country and vet them, know who they are, and what they are bringing to our country! Our systems are being strained enough. Once we take care of our own, then we can open the doors again, until then shut the door. ZERO. We are closed. We are FULL!🇨🇦

We need to stop mass immigration. Not reduce it to 70%. Im saying we bring it down to Zero until we can take care of our ow.n first. Canadians First! We need to be more selective with who we bring into the country and vet them, know who they are, and what they are bringing to our country! Our systems are being strained enough. Once we take care of our own, then we can open the doors again, until then shut the door. ZERO. We are closed. We are FULL!🇨🇦

Joe Anidjar

24,452 次观看 • 10 个月前

Introducing the USC Physical Superintelligence (PSI) Lab ( We are rebranding to better reflect our current focus. From here on out, we are tackling one thing: solving robotics and physical intelligence with every model, every bug, and every line of code. And yes, we are hiring at all levels, especially PhDs in this cycle and potential PostDocs who are excited about robotics. We hope you can join us in this journey! 1/9

Introducing the USC Physical Superintelligence (PSI) Lab ( We are rebranding to better reflect our current focus. From here on out, we are tackling one thing: solving robotics and physical intelligence with every model, every bug, and every line of code. And yes, we are hiring at all levels, especially PhDs in this cycle and potential PostDocs who are excited about robotics. We hope you can join us in this journey! 1/9

Yue Wang

25,561 次观看 • 8 个月前