Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Okay, this is actually insane. 🪜 A humanoid that climbs a ladder — then performs tasks from it. Amazon FAR’s LadderMan learns ladder climbing in simulation, transfers zero-shot to a real Unitree G1, and supports stable on-ladder manipulation under tight ladder constraints. The demo: climb, stabilize, adjust a wall...

XRoboHub's profile picture

RoboHub🤖

19,493 subscribers

11,041 görüntüleme • 1 ay önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Amazon is training humanoids to move boxes. Makes sense! OmniRetarget is a data generation engine that enables complex loco-manipulation for humanoids. It uses offline retargeting from human MoCap datasets and augments data from single demos to produce 8 hours of trajectories that train RL policies in simulation, transferred zero-shot to real robots. Amazon FAR is the primary affiliation for the paper:
1:37

Amazon is training humanoids to move boxes. Makes sense! OmniRetarget is a data generation engine that enables complex loco-manipulation for humanoids. It uses offline retargeting from human MoCap datasets and augments data from single demos to produce 8 hours of trajectories that train RL policies in simulation, transferred zero-shot to real robots. Amazon FAR is the primary affiliation for the paper:

The Humanoid Hub

106,447 görüntüleme • 10 ay önce

The full LadderMan podcast episode is finally live! 🪜 LadderMan is one of the most interesting papers recently: instead of just walking on flat ground or doing flashy demos, it tackles a very real-world capability — letting humanoid robots climb ladders with perception, planning, and whole-body control. To me, this is exactly the kind of work that pushes robots closer to actually operating in human environments. Huge thanks again to Siheng Zhao , Chris Paxton, The Humanoid Hub, and Zifan Xu for joining the discussion. The full episode is a bit long, so I’ll be cutting some of the best moments into shorter clips and sharing them soon.
54:58

The full LadderMan podcast episode is finally live! 🪜 LadderMan is one of the most interesting papers recently: instead of just walking on flat ground or doing flashy demos, it tackles a very real-world capability — letting humanoid robots climb ladders with perception, planning, and whole-body control. To me, this is exactly the kind of work that pushes robots closer to actually operating in human environments. Huge thanks again to Siheng Zhao , Chris Paxton, The Humanoid Hub, and Zifan Xu for joining the discussion. The full episode is a bit long, so I’ll be cutting some of the best moments into shorter clips and sharing them soon.

Eren Chen

10,350 görüntüleme • 1 ay önce

THE LADDER VS THE CHAIR One of the ways I like to explain salvation is with the difference between a ladder and a chair. Too many people think getting right with God is like climbing a ladder — do more good, try harder, be better, get more committed and maybe you’ll make it to the top. As a matter of fact EVERY world religion has a ladder approach to their view of salvation. You work your way to heaven by climbing various rungs to God. Every religion has the same ladder approach, but with different rungs (7 sacraments of Catholicism, 8 fold path of Buddhism, 10 Commandments of Judaism, 5 pillars of Islam, etc.) And, sadly, many Protestants have developed their own ladder approach to God as well (turn, try, cry, commit, surrender, get baptized, etc.) But the RUNG approach is the WRONG approach. Only true Christianity recognizes this. Only true Christianity views salvation as a chair and not a ladder. You don’t try to climb a chair. You simply sit in it and trust it to hold you. In the same way, we can’t earn our salvation (climb the ladder to heaven), we simply rest on what Jesus did for us on the cross. We transfer our trust from our own efforts to his finished work on the cross and, then, we are saved! He gives us eternal life as a free gift through simple faith in Christ and then he begins the transformation process in us. The Bible makes this clear: 📖 “For it is by grace you have been saved, through faith—and this is not from yourselves, it is the gift of God— not by works, so that no one can boast.” Ephesians 2:8–9 📖 “he saved us, not because of righteous things we had done, but because of his mercy. He saved us through the washing of rebirth and renewal by the Holy Spirit…” Titus 3:5 The ladder says: achieve. Jesus says: believe. Stop trying to climb your way to God. Put your full weight on Christ and rest on what He’s already done on your behalf on the cross. This is the good news of the Gospel. This is the message we must share!!! #Gospel #GraceAlone #FaithInChrist #Dare2Share #GoodNews
2:51

THE LADDER VS THE CHAIR One of the ways I like to explain salvation is with the difference between a ladder and a chair. Too many people think getting right with God is like climbing a ladder — do more good, try harder, be better, get more committed and maybe you’ll make it to the top. As a matter of fact EVERY world religion has a ladder approach to their view of salvation. You work your way to heaven by climbing various rungs to God. Every religion has the same ladder approach, but with different rungs (7 sacraments of Catholicism, 8 fold path of Buddhism, 10 Commandments of Judaism, 5 pillars of Islam, etc.) And, sadly, many Protestants have developed their own ladder approach to God as well (turn, try, cry, commit, surrender, get baptized, etc.) But the RUNG approach is the WRONG approach. Only true Christianity recognizes this. Only true Christianity views salvation as a chair and not a ladder. You don’t try to climb a chair. You simply sit in it and trust it to hold you. In the same way, we can’t earn our salvation (climb the ladder to heaven), we simply rest on what Jesus did for us on the cross. We transfer our trust from our own efforts to his finished work on the cross and, then, we are saved! He gives us eternal life as a free gift through simple faith in Christ and then he begins the transformation process in us. The Bible makes this clear: 📖 “For it is by grace you have been saved, through faith—and this is not from yourselves, it is the gift of God— not by works, so that no one can boast.” Ephesians 2:8–9 📖 “he saved us, not because of righteous things we had done, but because of his mercy. He saved us through the washing of rebirth and renewal by the Holy Spirit…” Titus 3:5 The ladder says: achieve. Jesus says: believe. Stop trying to climb your way to God. Put your full weight on Christ and rest on what He’s already done on your behalf on the cross. This is the good news of the Gospel. This is the message we must share!!! #Gospel #GraceAlone #FaithInChrist #Dare2Share #GoodNews

Greg Stier

34,528 görüntüleme • 5 ay önce

This work makes a humanoid robot do simple parkour moves by looking with a depth camera and choosing the right move on the fly. The big deal is that it turns lots of small human moves into long, real-time robot behavior, without hand-coding every transition or retraining for each new course. A humanoid robot is usually good at steady walking, but it often fails when it has to do fast moves like jumping up, vaulting, or rolling, and then keep going to the next obstacle. The hard part is that you cannot easily collect training data for every possible obstacle shape, distance, and mistake, so robots end up learning a few moves that only work in a narrow setup. This work starts from short clips of real human parkour moves, like stepping over, vaulting, climbing, and rolling. It uses motion matching, which is basically a smart “pick the next clip that fits best right now” search, to stitch those short clips into a long, smooth plan that looks like a human doing a whole course. Then it trains a controller with reinforcement learning (RL), which means the robot learns by trial and error to copy that plan while staying balanced and not falling. After training separate expert controllers for different moves, it compresses them into 1 controller that uses only onboard depth sensing and a simple “go this fast in this direction” command. In real tests on a Unitree G1 humanoid, it can clear multiple obstacles in a row, adapt when obstacles get moved, and climb a wall up to 1.25m.
0:05

This work makes a humanoid robot do simple parkour moves by looking with a depth camera and choosing the right move on the fly. The big deal is that it turns lots of small human moves into long, real-time robot behavior, without hand-coding every transition or retraining for each new course. A humanoid robot is usually good at steady walking, but it often fails when it has to do fast moves like jumping up, vaulting, or rolling, and then keep going to the next obstacle. The hard part is that you cannot easily collect training data for every possible obstacle shape, distance, and mistake, so robots end up learning a few moves that only work in a narrow setup. This work starts from short clips of real human parkour moves, like stepping over, vaulting, climbing, and rolling. It uses motion matching, which is basically a smart “pick the next clip that fits best right now” search, to stitch those short clips into a long, smooth plan that looks like a human doing a whole course. Then it trains a controller with reinforcement learning (RL), which means the robot learns by trial and error to copy that plan while staying balanced and not falling. After training separate expert controllers for different moves, it compresses them into 1 controller that uses only onboard depth sensing and a simple “go this fast in this direction” command. In real tests on a Unitree G1 humanoid, it can clear multiple obstacles in a row, adapt when obstacles get moved, and climb a wall up to 1.25m.

Rohan Paul

37,121 görüntüleme • 5 ay önce

OK this is nuts. Unitree just demonstrated a humanoid successfully riding a skateboard for the first time ever. HUSKY, developed by Chinese researchers, is a new framework that enables the Unitree G1 to push, steer, and balance on an actual skateboard outdoors. The breakthrough is physics-aware control on an unstable, wheeled platform. And it matters way beyond a cool demo... Balancing on unpredictable moving surfaces is *exactly* what's needed for construction sites, disaster zones, and unstructured environments. What happens when robots can handle any surface, in any condition?
0:28

OK this is nuts. Unitree just demonstrated a humanoid successfully riding a skateboard for the first time ever. HUSKY, developed by Chinese researchers, is a new framework that enables the Unitree G1 to push, steer, and balance on an actual skateboard outdoors. The breakthrough is physics-aware control on an unstable, wheeled platform. And it matters way beyond a cool demo... Balancing on unpredictable moving surfaces is *exactly* what's needed for construction sites, disaster zones, and unstructured environments. What happens when robots can handle any surface, in any condition?

Ole Lehmann

68,115 görüntüleme • 5 ay önce

Chelsea Green On her Money in the Bank fall: “Seriously, that ladder is high, it’s very high, because I think it was a 20-foot ladder — dear life as I’m going up it trying to look all like I’m a badass, and I’m like, Dear God, please let this be over. I want to go home. I need a glass of wine. But it was all worth it. I knew what that moment was going to be. I died on that hill getting that moment because the boys tried to take it away from me.” “The boys tried to have that exact same moment. So we bargained. We gave Chad Gable a spot, and I took my spot. Also, and this might not be that popular of a thing to say, but also, IYO was going to be on the ladder with me. I said no. I came up with the spot. I wanted the spot, and I didn’t think going through it a second time with somebody else was going to be as impactful....So I wanted the moment, and I fought for it to be just me, and I fought for it to be the very, very, very last spot before Tiffany won.” (Chris Van Vliet)
2:22

Chelsea Green On her Money in the Bank fall: “Seriously, that ladder is high, it’s very high, because I think it was a 20-foot ladder — dear life as I’m going up it trying to look all like I’m a badass, and I’m like, Dear God, please let this be over. I want to go home. I need a glass of wine. But it was all worth it. I knew what that moment was going to be. I died on that hill getting that moment because the boys tried to take it away from me.” “The boys tried to have that exact same moment. So we bargained. We gave Chad Gable a spot, and I took my spot. Also, and this might not be that popular of a thing to say, but also, IYO was going to be on the ladder with me. I said no. I came up with the spot. I wanted the spot, and I didn’t think going through it a second time with somebody else was going to be as impactful....So I wanted the moment, and I fought for it to be just me, and I fought for it to be the very, very, very last spot before Tiffany won.” (Chris Van Vliet)

J O H N

509,245 görüntüleme • 7 ay önce

Not a preplanned motion sequence. A robot deciding mid-jump what to do next. [📍 paper + demo] Researchers just showed a humanoid doing real parkour using only onboard perception. No motion script, no fixed obstacle layout. The system is called Perceptive Humanoid Parkour (PHP). Instead of memorizing a path, the robot reads depth from its cameras and continuously chooses actions. Step, vault, climb, or roll depending on what geometry appears in front of it. To make that possible, they combine three ideas: First, they stitch together human motion clips into long movement references so the robot learns fluid transitions instead of isolated tricks. Second, they train tracking policies with reinforcement learning so contacts land at the right time and the robot keeps balance during dynamic moves. Finally, everything is distilled into one perception policy that runs directly from depth input to action selection. The result on a Unitree G1: about 3 m/s vaults wall climbs up to 1.25 m nearly one minute continuous obstacle traversal adapting when obstacles move What matters is not the tricks. It is the shift in capability. Earlier humanoids executed motions. This one navigates situations. Once robots react to geometry instead of replaying trajectories, environments stop needing to be predictable. Warehouses, homes, and outdoors suddenly become the same problem. Thanks for sharing, Zhen Wu! Paper + demo: ——— Weekly robotics and AI insights. Subscribe free:
0:29

Not a preplanned motion sequence. A robot deciding mid-jump what to do next. [📍 paper + demo] Researchers just showed a humanoid doing real parkour using only onboard perception. No motion script, no fixed obstacle layout. The system is called Perceptive Humanoid Parkour (PHP). Instead of memorizing a path, the robot reads depth from its cameras and continuously chooses actions. Step, vault, climb, or roll depending on what geometry appears in front of it. To make that possible, they combine three ideas: First, they stitch together human motion clips into long movement references so the robot learns fluid transitions instead of isolated tricks. Second, they train tracking policies with reinforcement learning so contacts land at the right time and the robot keeps balance during dynamic moves. Finally, everything is distilled into one perception policy that runs directly from depth input to action selection. The result on a Unitree G1: about 3 m/s vaults wall climbs up to 1.25 m nearly one minute continuous obstacle traversal adapting when obstacles move What matters is not the tricks. It is the shift in capability. Earlier humanoids executed motions. This one navigates situations. Once robots react to geometry instead of replaying trajectories, environments stop needing to be predictable. Warehouses, homes, and outdoors suddenly become the same problem. Thanks for sharing, Zhen Wu! Paper + demo: ——— Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

22,080 görüntüleme • 5 ay önce

JUST IN: Unitree Robotics just unveiled the GD01, a manned "mecha" robot that transforms between two legs and four legs in real time. This is not a concept. This is a product. Starting price: $574,000. This robot weighs 500kg, is built from high-strength alloy, and has a torso-mounted cockpit. The demo video shows it walking upright, knocking down a brick wall with its hand, then reconfiguring into a four-legged crawl. Unitree calls it the world's first mass-produced transformable mecha. But the real story here is the bigger picture. Chinese companies accounted for nearly 90% of global humanoid robot sales in 2025. Unitree alone shipped 5,500+ humanoid robots last year. In the same period, Tesla, Figure AI and Agility Robotics each shipped around 150. And Unitree is now filing for an IPO on Shanghai's Star Market, targeting 4.2 billion yuan, 85% of which goes straight into R&D. The West is building incredible humanoid robots. China is building them faster, cheaper and at a scale nobody else is close to matching. Read more here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
1:06

JUST IN: Unitree Robotics just unveiled the GD01, a manned "mecha" robot that transforms between two legs and four legs in real time. This is not a concept. This is a product. Starting price: $574,000. This robot weighs 500kg, is built from high-strength alloy, and has a torso-mounted cockpit. The demo video shows it walking upright, knocking down a brick wall with its hand, then reconfiguring into a four-legged crawl. Unitree calls it the world's first mass-produced transformable mecha. But the real story here is the bigger picture. Chinese companies accounted for nearly 90% of global humanoid robot sales in 2025. Unitree alone shipped 5,500+ humanoid robots last year. In the same period, Tesla, Figure AI and Agility Robotics each shipped around 150. And Unitree is now filing for an IPO on Shanghai's Star Market, targeting 4.2 billion yuan, 85% of which goes straight into R&D. The West is building incredible humanoid robots. China is building them faster, cheaper and at a scale nobody else is close to matching. Read more here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

11,580 görüntüleme • 2 ay önce

.travis kalanick on why specialized robots beat humanoids for real work: "I'm not anti-humanoid, I'm non-humanoid. There are tasks that are good for humanoids, low scale, high diversity, in human environments, humanoid all the way. But the minute you have a machine doing a high-scale task, we're no longer in humanoid land, we're in specialized robotics land." "There was a moment nine months ago where humanoids were the mega rage of all time. When your hairdresser says he's getting into the humanoid business, we know something's wrong." "If I had to make 1,000 pancakes an hour, I'd never have a humanoid do it, you'd need 100 humanoids going gg-gg-gg. It's like the humanoid Olympics in Beijing, they're doing the marathon and it's cool, but all I could think is, imagine if you put wheels on them. Would you ever put a humanoid in a car to drive it?" "High scale, repetitive tasks do not need to be in human form, and they won't be, because humans are meant to do lots of things at low scale."
2:17

.travis kalanick on why specialized robots beat humanoids for real work: "I'm not anti-humanoid, I'm non-humanoid. There are tasks that are good for humanoids, low scale, high diversity, in human environments, humanoid all the way. But the minute you have a machine doing a high-scale task, we're no longer in humanoid land, we're in specialized robotics land." "There was a moment nine months ago where humanoids were the mega rage of all time. When your hairdresser says he's getting into the humanoid business, we know something's wrong." "If I had to make 1,000 pancakes an hour, I'd never have a humanoid do it, you'd need 100 humanoids going gg-gg-gg. It's like the humanoid Olympics in Beijing, they're doing the marathon and it's cool, but all I could think is, imagine if you put wheels on them. Would you ever put a humanoid in a car to drive it?" "High scale, repetitive tasks do not need to be in human form, and they won't be, because humans are meant to do lots of things at low scale."

MTS

52,573 görüntüleme • 11 gün önce

Monica and I visited the Devil's Ladder on the old Kit Carson Pioneer Trail, just east of Carson Pass. This was a year or two ago, and we decided to walk down the trail just a bit. This was a section of trail that was notorious back in the 1840s and 50s. A pioneer diary says, "…just ahead was a wall several thousand feet high which had to be climbed to get out of this valley….come to the conclusion this was the end of the road…It was called Devil’s Ladder." What impressed us was how steep the trail was, and the fact that the pioneers would have to unload their wagons, carry all their belongings up the trail, while their wagons were pulled up by a team of oxen and a series of ropes. Rope scars on the trees are still visible. We hope to walk the whole Devil's Ladder, from Red Lake to Carson Pass, this summer and record our progress. Map of location: 38°41'32.8"N 119°59'05.8"W
1:29

Monica and I visited the Devil's Ladder on the old Kit Carson Pioneer Trail, just east of Carson Pass. This was a year or two ago, and we decided to walk down the trail just a bit. This was a section of trail that was notorious back in the 1840s and 50s. A pioneer diary says, "…just ahead was a wall several thousand feet high which had to be climbed to get out of this valley….come to the conclusion this was the end of the road…It was called Devil’s Ladder." What impressed us was how steep the trail was, and the fact that the pioneers would have to unload their wagons, carry all their belongings up the trail, while their wagons were pulled up by a team of oxen and a series of ropes. Rope scars on the trees are still visible. We hope to walk the whole Devil's Ladder, from Red Lake to Carson Pass, this summer and record our progress. Map of location: 38°41'32.8"N 119°59'05.8"W

Adventures in California History

92,126 görüntüleme • 3 ay önce

What if robots could learn real-world tasks from your perspective… without ever touching a robot? This is a system that trains robot policies using nothing but human-first, egocentric video data from smart glasses. No robots, no teleop, no sensors, just humans doing real tasks in the real world. Why it matters ✅ Learns robot policies from 20 minutes of human video; zero robot demos ✅ Generalizes to new objects, views, and even robot morphologies ✅ Uses 3D points for interpretable, spatially grounded learning ✅ Deploys directly to real-world robots with strong zero-shot success Thank you, Vincent Liu, for sharing!!! Learn more here: 🔗 Paper: 🌐 Website: 📍 BOOKMARK FOR LATER
0:30

What if robots could learn real-world tasks from your perspective… without ever touching a robot? This is a system that trains robot policies using nothing but human-first, egocentric video data from smart glasses. No robots, no teleop, no sensors, just humans doing real tasks in the real world. Why it matters ✅ Learns robot policies from 20 minutes of human video; zero robot demos ✅ Generalizes to new objects, views, and even robot morphologies ✅ Uses 3D points for interpretable, spatially grounded learning ✅ Deploys directly to real-world robots with strong zero-shot success Thank you, Vincent Liu, for sharing!!! Learn more here: 🔗 Paper: 🌐 Website: 📍 BOOKMARK FOR LATER

Ilir Aliu - eu/acc

10,509 görüntüleme • 1 yıl önce

Your New Tennis Sparring Partner is Here!🥳 UBTECH just kicked off 2026 by putting their Walker S2 on the court for a live tennis rally against a human. 🎾🤖 Watching a humanoid handle high-impact strokes with this much balance and precision is wild. It’s officially time to trade in the ball machine for a partner that actually moves. Ready for a game against a robot? Source: UBTECH
0:26

Your New Tennis Sparring Partner is Here!🥳 UBTECH just kicked off 2026 by putting their Walker S2 on the court for a live tennis rally against a human. 🎾🤖 Watching a humanoid handle high-impact strokes with this much balance and precision is wild. It’s officially time to trade in the ball machine for a partner that actually moves. Ready for a game against a robot? Source: UBTECH

RoboHub🤖

47,853 görüntüleme • 7 ay önce

Foundation models are enough to solve robotics! Unfortunately, this is not true. We keep hearing that Vision-Language-Action (VLA) models struggle because of the gap between static training and the dynamic real world. A German startup (Sereact) just released a solution that bridges this gap perfectly. They are introducing a new paradigm called Interactive RL Policy Patching. It's a distributed framework that allows robots to self-learn from human corrections without needing full retraining. When a robot fails, a human operator provides a brief "patch" or demonstration. The system then uses online off-policy reinforcement learning to update the behavior instantly. This is powered by a massive foundation model trained on hundreds of millions of interactions from over 100 deployed robot stations. The best part is the distributed parameter synchronization... When one robot learns a fix, the update is published fleet-wide... meaning the entire swarm gets smarter from a single human intervention. They are already proving this on complex manipulation tasks like shoe unboxing and screw sorting, drastically reducing the data needed to handle edge cases. Real-world environments are unforgiving, and I love seeing systems that can actually adapt on the fly! 📍 More info:
0:38

Foundation models are enough to solve robotics! Unfortunately, this is not true. We keep hearing that Vision-Language-Action (VLA) models struggle because of the gap between static training and the dynamic real world. A German startup (Sereact) just released a solution that bridges this gap perfectly. They are introducing a new paradigm called Interactive RL Policy Patching. It's a distributed framework that allows robots to self-learn from human corrections without needing full retraining. When a robot fails, a human operator provides a brief "patch" or demonstration. The system then uses online off-policy reinforcement learning to update the behavior instantly. This is powered by a massive foundation model trained on hundreds of millions of interactions from over 100 deployed robot stations. The best part is the distributed parameter synchronization... When one robot learns a fix, the update is published fleet-wide... meaning the entire swarm gets smarter from a single human intervention. They are already proving this on complex manipulation tasks like shoe unboxing and screw sorting, drastically reducing the data needed to handle edge cases. Real-world environments are unforgiving, and I love seeing systems that can actually adapt on the fly! 📍 More info:

Ilir Aliu

18,210 görüntüleme • 6 ay önce

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)
0:33

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 görüntüleme • 1 yıl önce

Who can say no to a humanoid robot that can actually feel a hug? 🤖 JQ Industries just built a fabric-based electronic skin for Unitree G1 — covering the torso, hands, and feet. This is not about appearance. It’s about giving robots real tactile sensing and pressure feedback. According to the company, the system includes tactile gloves, upper-body skin, and foot sensors. That means the robot can feel contact through its hands, detect pressure across its body, and use foot feedback to adjust balance. This is the missing layer in most humanoids. Vision alone can’t handle physical interaction. Robots need touch to grip safely, react to humans, and stay stable in real-world environments. JQ says its fiber sensors can detect forces as low as 0.01N, handle up to 3500kPa, and bend below 0.1mm radius. The system can also integrate with Isaac Sim, making tactile data usable for training and deployment. Unitree G1 is already built for manipulation and control — this adds the sensing layer it lacked. JQ says it’s now working with multiple humanoid companies, with some systems already shipping at scale. This is what happens when robots stop just seeing the world — and start physically feeling it.
1:56

Who can say no to a humanoid robot that can actually feel a hug? 🤖 JQ Industries just built a fabric-based electronic skin for Unitree G1 — covering the torso, hands, and feet. This is not about appearance. It’s about giving robots real tactile sensing and pressure feedback. According to the company, the system includes tactile gloves, upper-body skin, and foot sensors. That means the robot can feel contact through its hands, detect pressure across its body, and use foot feedback to adjust balance. This is the missing layer in most humanoids. Vision alone can’t handle physical interaction. Robots need touch to grip safely, react to humans, and stay stable in real-world environments. JQ says its fiber sensors can detect forces as low as 0.01N, handle up to 3500kPa, and bend below 0.1mm radius. The system can also integrate with Isaac Sim, making tactile data usable for training and deployment. Unitree G1 is already built for manipulation and control — this adds the sensing layer it lacked. JQ says it’s now working with multiple humanoid companies, with some systems already shipping at scale. This is what happens when robots stop just seeing the world — and start physically feeling it.

RoboHub🤖

10,952 görüntüleme • 3 ay önce

Can a dexterous hand still function after being run over by a 2-ton car? The dexterous hand is the most expensive component of a humanoid robot, and if it breaks, the task is interrupted. Hangzhou BrainCo conducted a rigorous test on its latest dexterous hand, Revo2: it was run over by a nearly 2-ton Volvo car, dropped from a height of 5m, dropped 30m, and subjected to forceful impacts from a Unitree G1 robot. It still managed to maintain a stable grip and continue operating. Revo2 is BrainCo's next-generation dexterous/bionic hand, released last year. yes, a human-robot hybrid hand. It's very light, only 383g, 20kg payload,capable of precision manipulation down to 0.1mm (such as threading a needle), and possesses multi-dimensional tactile perception (hardness, texture, direction, proximity, etc.). This test also demonstrates that after achieving breakthroughs in performance, a dexterous hand also needs to be extremely durable and able to function under extreme environmental pressures.
1:17

Can a dexterous hand still function after being run over by a 2-ton car? The dexterous hand is the most expensive component of a humanoid robot, and if it breaks, the task is interrupted. Hangzhou BrainCo conducted a rigorous test on its latest dexterous hand, Revo2: it was run over by a nearly 2-ton Volvo car, dropped from a height of 5m, dropped 30m, and subjected to forceful impacts from a Unitree G1 robot. It still managed to maintain a stable grip and continue operating. Revo2 is BrainCo's next-generation dexterous/bionic hand, released last year. yes, a human-robot hybrid hand. It's very light, only 383g, 20kg payload,capable of precision manipulation down to 0.1mm (such as threading a needle), and possesses multi-dimensional tactile perception (hardness, texture, direction, proximity, etc.). This test also demonstrates that after achieving breakthroughs in performance, a dexterous hand also needs to be extremely durable and able to function under extreme environmental pressures.

CyberRobo

45,434 görüntüleme • 5 ay önce

In a no-win situation, Nick Fuentes asks what’s next for America in the war with Iran. “We are now stuck on this escalation ladder which we have no control over…Trump got elected and it sealed our fate.” “I think the only way, if there is one, out of this is regime change in Israel and America.” “Let Israel and the United States replace their leadership with a population that wants to be free, that doesn’t want a war.” “That’s the only solution from day one that was ever going to work.”
4:47

In a no-win situation, Nick Fuentes asks what’s next for America in the war with Iran. “We are now stuck on this escalation ladder which we have no control over…Trump got elected and it sealed our fate.” “I think the only way, if there is one, out of this is regime change in Israel and America.” “Let Israel and the United States replace their leadership with a population that wants to be free, that doesn’t want a war.” “That’s the only solution from day one that was ever going to work.”

Fractured Light

208,239 görüntüleme • 4 ay önce

Elon Musk revealed the 3 hardest challenges for humanoid robots and how Tesla is solving them There are really only three hard things for humanoid robots: - Real-world intelligence - ⁠The hand and - ⁠Scale manufacturing "I haven’t seen any demo robots that have a great hand with all the degrees of freedom of a human hand. But Optimus does have that" To reach human-level dexterity, Tesla had to design custom actuators, motors, gears, power electronics, controls, and sensors, everything from physics first principles There is no supply chain for this "From an electromechanical standpoint, the hand is more difficult than everything else combined. The human hand turns out to be quite something" This is why Optimus is on a completely different level. Tesla is solving the hardest problems from the ground up
0:55

Elon Musk revealed the 3 hardest challenges for humanoid robots and how Tesla is solving them There are really only three hard things for humanoid robots: - Real-world intelligence - ⁠The hand and - ⁠Scale manufacturing "I haven’t seen any demo robots that have a great hand with all the degrees of freedom of a human hand. But Optimus does have that" To reach human-level dexterity, Tesla had to design custom actuators, motors, gears, power electronics, controls, and sensors, everything from physics first principles There is no supply chain for this "From an electromechanical standpoint, the hand is more difficult than everything else combined. The human hand turns out to be quite something" This is why Optimus is on a completely different level. Tesla is solving the hardest problems from the ground up

X Freeze

20,796 görüntüleme • 4 ay önce

The power of generative models — now embodied in humanoids. Announcing DreamControl –– After a year-long research effort at General Robotics — we present a scalable framework for whole-body humanoid control that fuses diffusion priors with reinforcement learning to unlock real-world scene interaction. Diffusion + RL → natural whole-body skills on real robots. DreamControl enables humanoids to move beyond locomotion demos → performing natural, human-like skills such as –– Picking & lifting objects, Opening drawers & doors, Precise punching, kicking, and jumping, Bimanual manipulation tasks Our key innovation: a diffusion prior over human motion that guides RL, eliminating the need for massive teleoperation datasets, and producing motions that look human while transferring to real hardware. Trained purely in simulation, deployed on the Unitree G1 humanoid, DreamControl policies run in real time, bridging sim-to-real with unprecedented naturalness. We leverage a novel hybrid edge + cloud infrastructure that runs RL-trained policies on the edge backed by powerful AI models running in the cloud This is the next step in General Robotics’ journey toward general-purpose humanoid assistants that interact, adapt, and assist autonomously. Paper: Blog: 1/n
1:54

The power of generative models — now embodied in humanoids. Announcing DreamControl –– After a year-long research effort at General Robotics — we present a scalable framework for whole-body humanoid control that fuses diffusion priors with reinforcement learning to unlock real-world scene interaction. Diffusion + RL → natural whole-body skills on real robots. DreamControl enables humanoids to move beyond locomotion demos → performing natural, human-like skills such as –– Picking & lifting objects, Opening drawers & doors, Precise punching, kicking, and jumping, Bimanual manipulation tasks Our key innovation: a diffusion prior over human motion that guides RL, eliminating the need for massive teleoperation datasets, and producing motions that look human while transferring to real hardware. Trained purely in simulation, deployed on the Unitree G1 humanoid, DreamControl policies run in real time, bridging sim-to-real with unprecedented naturalness. We leverage a novel hybrid edge + cloud infrastructure that runs RL-trained policies on the edge backed by powerful AI models running in the cloud This is the next step in General Robotics’ journey toward general-purpose humanoid assistants that interact, adapt, and assist autonomously. Paper: Blog: 1/n

Ashish Kapoor

118,133 görüntüleme • 10 ay önce

"'Jacob’s Ladder' (1990) came out at a time when it was just not right for that movie to be seen. We were about to go into the Gulf War, and the country did not want to see a movie about a Vietnam veteran involved in drug experiments" --- Tim Robbins Full Excerpt: "There are many different factors determining whether or not a film reaches a mass audience. How much the studio’s behind it, which other movies the studio’s releasing at the same time—I think Disney had nine or ten in release at the same time—how much energy is put into it. Who knows. It’s always been a mystery to me. 'Jacob’s Ladder' (1990) came out at a time when it was just not right for that movie to be seen. We were about to go into the Gulf War, and the country did not want to see a movie about a Vietnam veteran involved in drug experiments when, as the movie’s playing in theaters, we are inoculating Gulf War soldiers with anthrax. I got a letter from one guy that resisted—he got put in a brig because he would not take the drugs. He said, “Thank you, because I saw Jacob’s Ladder before I left, and it gave me the strength to resist.” And now they’ve found out that a lot of these soldiers got sick from these vaccines, with this Gulf War Syndrome. That movie found its audience in video and cable, and it was huge. And then you see movies that somehow hit the zeitgeist, make tons of money, are huge hits, and then you see them a few years later and you go, “What? What did I see in this? Why is this not working?” Certainly you can’t judge the success of a film based on its initial box office. You have to wait ten years, see it again. If it still works, it’s a great film. There’s a lot of great films that didn’t do well in their initial release. 'It’s a Wonderful Life' (1946) was a bomb. 'Citizen Kane' (1941) didn’t do well. 'Shawshank Redemption' (1994)." ('Projection 11: New York Filmmakers on Filmmaking, edited by Tod Lippy, 2000 )
1:14

"'Jacob’s Ladder' (1990) came out at a time when it was just not right for that movie to be seen. We were about to go into the Gulf War, and the country did not want to see a movie about a Vietnam veteran involved in drug experiments" --- Tim Robbins Full Excerpt: "There are many different factors determining whether or not a film reaches a mass audience. How much the studio’s behind it, which other movies the studio’s releasing at the same time—I think Disney had nine or ten in release at the same time—how much energy is put into it. Who knows. It’s always been a mystery to me. 'Jacob’s Ladder' (1990) came out at a time when it was just not right for that movie to be seen. We were about to go into the Gulf War, and the country did not want to see a movie about a Vietnam veteran involved in drug experiments when, as the movie’s playing in theaters, we are inoculating Gulf War soldiers with anthrax. I got a letter from one guy that resisted—he got put in a brig because he would not take the drugs. He said, “Thank you, because I saw Jacob’s Ladder before I left, and it gave me the strength to resist.” And now they’ve found out that a lot of these soldiers got sick from these vaccines, with this Gulf War Syndrome. That movie found its audience in video and cable, and it was huge. And then you see movies that somehow hit the zeitgeist, make tons of money, are huge hits, and then you see them a few years later and you go, “What? What did I see in this? Why is this not working?” Certainly you can’t judge the success of a film based on its initial box office. You have to wait ten years, see it again. If it still works, it’s a great film. There’s a lot of great films that didn’t do well in their initial release. 'It’s a Wonderful Life' (1946) was a bomb. 'Citizen Kane' (1941) didn’t do well. 'Shawshank Redemption' (1994)." ('Projection 11: New York Filmmakers on Filmmaking, edited by Tod Lippy, 2000 )

DepressedBergman

69,461 görüntüleme • 6 ay önce