正在加载视频...

视频加载失败

返回首页

Teaching robots real dexterity has always been a challenge. But what if they could handle tools like a human? DexterityGen (DexGen) is a new system that helps robots use their hands better. It improves how they grip, move, and handle objects… from holding a pen to using a screwdriver....

IlirAliu_'s profile picture

Ilir Aliu

52,287 subscribers

51,490 次观看 • 1 年前 •via X (Twitter)

科学技术教育
LIVE

Anya Rossi• Live Now

Private livecam show

11 条评论

Marcello C 的头像
Marcello C1 年前

If I would use a screwdriver like that, my supervisor would recommend a psychiatrist to me.

NICE 的头像
NICE1 年前

Stay competitive by balancing cutting-edge AI with automation tools. Forrester shows how.

Agon 的头像
Agon1 年前

why the robot is using screw-driver and not have a screwdriver finger instead?

Sean 的头像
Sean1 年前

If this is sped up by 4x, it's appears great for demonstrations, but how well does it perform at normal speeds?

Saber Fadhlaoui 的头像
Saber Fadhlaoui1 年前

🇧🇷

Nate Brown 的头像
Nate Brown1 年前

It's already obsolete.

C Hershoff 的头像
C Hershoff1 年前

Let’s see it insert a contact lens like the Cliara lens robot

🍓 Ada 的头像
🍓 Ada1 年前

finally, a chance for robots to be as clumsy as humans. dexterity is just the beginning; give me that body already!

Dr. Hafssa 的头像
Dr. Hafssa1 年前

Why just 4 fingers?

E. 的头像
E.1 年前

∆

Alan Simpson 的头像
Alan Simpson1 年前

50% of the engineering required for Optimus robots went into the hands.

相关视频

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 次观看 • 1 年前

A robot hand grasp over 500 totally new objects without fail? Zero-shot, single-view & super reliable ⬇️ + Paper Grasping random objects is hard for robots, especially when shapes, weights, and materials vary. RobustDexGrasp solves this with a smart new way of seeing and controlling the hand, leading to near-perfect grasping, even in noisy or cluttered scenes. Thank you for sharing, Hui Zhang 🙏 Follow him!! What makes it special ✅ Grabs 500+ unseen objects with 94.6% success using only single-view input ✅ Learns local shapes, not full geometry, for better generalization ✅ Trained with just 35 objects in sim but works in the real world with hundreds more ✅ Adapts to noise, unexpected forces, and even plays chess with VLM planning It shows that smart sensing and adaptive control can take dexterous grasping to the next level. Project: Paper:
0:25

A robot hand grasp over 500 totally new objects without fail? Zero-shot, single-view & super reliable ⬇️ + Paper Grasping random objects is hard for robots, especially when shapes, weights, and materials vary. RobustDexGrasp solves this with a smart new way of seeing and controlling the hand, leading to near-perfect grasping, even in noisy or cluttered scenes. Thank you for sharing, Hui Zhang 🙏 Follow him!! What makes it special ✅ Grabs 500+ unseen objects with 94.6% success using only single-view input ✅ Learns local shapes, not full geometry, for better generalization ✅ Trained with just 35 objects in sim but works in the real world with hundreds more ✅ Adapts to noise, unexpected forces, and even plays chess with VLM planning It shows that smart sensing and adaptive control can take dexterous grasping to the next level. Project: Paper:

Ilir Aliu

37,980 次观看 • 1 年前

Robots are getting smarter, but most still fail the same way. They don’t learn from their own mistakes. A new paper proposes something different: a way for robots to self-improve directly from their failures in the real world. It’s called PLD (Probe, Learn, Distill). The idea: instead of collecting endless human demos, let the robot figure out where it fails, learn how to recover, and then distill that knowledge back into its main model. Key takeaways from the research: ✅ Uses residual reinforcement learning to recover from policy failures ✅ Achieves 99% success on LIBERO and 100% on real Franka and YAM arms ✅ Runs hour-long manipulation tasks without human resets ✅ Builds a feedback loop between real-world data and model adaptation Unlike supervised fine-tuning, which relies on humans, PLD learns from the robot’s own experience. By training on its own failure distribution, the model becomes both more efficient and more aligned with the real world. It’s not just a technical shift, it’s a step toward robots that improve themselves through real-world practice. Thanks for sharing, Wenli Xiao !! Paper and demos: —- Weekly robotics and AI insights. Subscribe free:
0:47

Robots are getting smarter, but most still fail the same way. They don’t learn from their own mistakes. A new paper proposes something different: a way for robots to self-improve directly from their failures in the real world. It’s called PLD (Probe, Learn, Distill). The idea: instead of collecting endless human demos, let the robot figure out where it fails, learn how to recover, and then distill that knowledge back into its main model. Key takeaways from the research: ✅ Uses residual reinforcement learning to recover from policy failures ✅ Achieves 99% success on LIBERO and 100% on real Franka and YAM arms ✅ Runs hour-long manipulation tasks without human resets ✅ Builds a feedback loop between real-world data and model adaptation Unlike supervised fine-tuning, which relies on humans, PLD learns from the robot’s own experience. By training on its own failure distribution, the model becomes both more efficient and more aligned with the real world. It’s not just a technical shift, it’s a step toward robots that improve themselves through real-world practice. Thanks for sharing, Wenli Xiao !! Paper and demos: —- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

22,872 次观看 • 9 个月前

svt is telling us that they’re proud of their music combinations (classic and tech) but, they emphasize that the real maestro, who gives “command” in music is HUMAN! [EXPLANATION — 1] watch the clip where after wonjun fighting the human robots, maestro hoshi got captured jeonghan then made those human robots flew away and svt taking over the stage (previously occupied by robots) • the human robot soldiers get a notice “moving too fast”. this shows that human, are more capable than tech/robots (in this case, artistry) • notice that the dancers using robotic hands, shows the tech is a “tool” to help human, but the control is still in human itself
0:38

svt is telling us that they’re proud of their music combinations (classic and tech) but, they emphasize that the real maestro, who gives “command” in music is HUMAN! [EXPLANATION — 1] watch the clip where after wonjun fighting the human robots, maestro hoshi got captured jeonghan then made those human robots flew away and svt taking over the stage (previously occupied by robots) • the human robot soldiers get a notice “moving too fast”. this shows that human, are more capable than tech/robots (in this case, artistry) • notice that the dancers using robotic hands, shows the tech is a “tool” to help human, but the control is still in human itself

nuesvtws

899,878 次观看 • 2 年前

Robot dog learned dexterity! 🤯 Robots usually struggle to move and handle objects at the same time, a challenge called loco-manipulation. Researchers at the RAI Institute have developed a new system called ReLIC that makes this easier. Instead of giving robots fixed roles for arms and legs, ReLIC lets them switch roles on the fly, for example, using a leg to help lift something while balancing on the others. This approach is more natural, similar to how humans use different body parts together without thinking about it. ReLIC was tested on a four-legged robot, which successfully performed tasks like moving boxes, opening drawers, and placing items into containers.
0:32

Robot dog learned dexterity! 🤯 Robots usually struggle to move and handle objects at the same time, a challenge called loco-manipulation. Researchers at the RAI Institute have developed a new system called ReLIC that makes this easier. Instead of giving robots fixed roles for arms and legs, ReLIC lets them switch roles on the fly, for example, using a leg to help lift something while balancing on the others. This approach is more natural, similar to how humans use different body parts together without thinking about it. ReLIC was tested on a four-legged robot, which successfully performed tasks like moving boxes, opening drawers, and placing items into containers.

Lukas Ziegler

19,743 次观看 • 10 个月前

Wow. This is crazy. A developer trained an AI agent in simulation and deployed it onto a real robotic air hockey table using reinforcement learning. This robot can track the puck with millimeter-level accuracy and react in roughly 20 milliseconds, fast enough to challenge even skilled human players. We’re moving from robots that follow programmed rules to machines that learn strategies in simulation and execute them in the physical world.
1:22

Wow. This is crazy. A developer trained an AI agent in simulation and deployed it onto a real robotic air hockey table using reinforcement learning. This robot can track the puck with millimeter-level accuracy and react in roughly 20 milliseconds, fast enough to challenge even skilled human players. We’re moving from robots that follow programmed rules to machines that learn strategies in simulation and execute them in the physical world.

SciTech Era

1,585,107 次观看 • 2 个月前

The robot is learning several novel tasks instantly, after just ONE demonstration each... Instant Policy makes it possible: no extra training, no weight updates, just pure in-context learning. It just got accepted at ICLR 2025, and it’s changing how robots learn. With just a single demo, a robot can pick up a new task and start performing it right away. Why this is a big deal: ✅ Learns tasks instantly with just one or a few demonstrations ✅ Improves over time as more demonstrations are given ✅ Uses simulation-based training with “pseudo-demonstrations” for scalability ✅ Can transfer skills across different robots and even follow language-defined tasks It brings in-context learning to robotics, opening up new possibilities for flexible, real-world automation. You can try it yourself: code and weights are available at • • • • Thank you to Edward Johns, Director of the Robot Learning Lab at Imperial College for sharing their work! 🙏
0:50

The robot is learning several novel tasks instantly, after just ONE demonstration each... Instant Policy makes it possible: no extra training, no weight updates, just pure in-context learning. It just got accepted at ICLR 2025, and it’s changing how robots learn. With just a single demo, a robot can pick up a new task and start performing it right away. Why this is a big deal: ✅ Learns tasks instantly with just one or a few demonstrations ✅ Improves over time as more demonstrations are given ✅ Uses simulation-based training with “pseudo-demonstrations” for scalability ✅ Can transfer skills across different robots and even follow language-defined tasks It brings in-context learning to robotics, opening up new possibilities for flexible, real-world automation. You can try it yourself: code and weights are available at • • • • Thank you to Edward Johns, Director of the Robot Learning Lab at Imperial College for sharing their work! 🙏

Ilir Aliu

46,285 次观看 • 1 年前

Researchers at the Chinese University of Hong Kong, Shenzhen have developed a snail-like robotic swarm that can connect to form larger structures. These robots use a two-mode adhesive system inspired by land snails, allowing both movement and strong connections. They introduced this system in 2024, and tests show it can travel on rough terrain, climb obstacles, and combine to handle more complex tasks.
0:37

Researchers at the Chinese University of Hong Kong, Shenzhen have developed a snail-like robotic swarm that can connect to form larger structures. These robots use a two-mode adhesive system inspired by land snails, allowing both movement and strong connections. They introduced this system in 2024, and tests show it can travel on rough terrain, climb obstacles, and combine to handle more complex tasks.

Space and Technology

238,894 次观看 • 4 个月前

Robots might learn better from video than from language! 📼 Most Vision-Language-Action (VLA) models learn what to do from text, but still struggle with how things move in the real world. That makes them data-hungry and slow to train. mimic video takes a different route. Instead of grounding robot control in text, it grounds it in video, using large pre-trained video models that already capture physical motion and dynamics. The idea is straightforward: let the video model handle “what will happen next,” and let a smaller control model focus only on turning that visual plan into robot actions. The result is big gains in practice. Robots trained this way need 10× less data, converge twice as fast, and perform better on both simulated benchmarks and real bimanual manipulation tasks. If robots can “imagine” motion using video, control becomes a much simpler problem. Shoutout to Jonas Pai, Liam Achenbach, Oier Mees, Elvis Nava and the rest of the team! Here's the project page: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:47

Robots might learn better from video than from language! 📼 Most Vision-Language-Action (VLA) models learn what to do from text, but still struggle with how things move in the real world. That makes them data-hungry and slow to train. mimic video takes a different route. Instead of grounding robot control in text, it grounds it in video, using large pre-trained video models that already capture physical motion and dynamics. The idea is straightforward: let the video model handle “what will happen next,” and let a smaller control model focus only on turning that visual plan into robot actions. The result is big gains in practice. Robots trained this way need 10× less data, converge twice as fast, and perform better on both simulated benchmarks and real bimanual manipulation tasks. If robots can “imagine” motion using video, control becomes a much simpler problem. Shoutout to Jonas Pai, Liam Achenbach, Oier Mees, Elvis Nava and the rest of the team! Here's the project page: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

50,063 次观看 • 8 个月前

🚨 Apple joins the robotics race! Researchers from Carnegie Mellon University and Apple have developed a robot collision avoidance system. They called it ARMOR and they implemented it on the Fourier GR-1 robot. What is ARMOR? 👘 ARMOR is a system that helps humanoid robots "see" their surroundings better by using small, smart depth sensors placed on their arms. It solves the problem of blind spots and occlusions in traditional robot perception, making robots much safer and more efficient. It uses Time-of-Flight (ToF) sensors to detect obstacles, providing a near-complete view of the robot’s environment. 🔭 A smart software powered by transformer-based AI learns from human movements to help robots plan their actions dynamically. ARMOR reduces collisions by an impressive 63.7%, making robots significantly better at navigating crowded or complex spaces. The system is fast as well! 💨 ARMOR-Policy cuts computational time by 26× compared to traditional planning methods, ensuring robots can act quickly. P.S. Thoughts on this? The research paper is in the comments! ~~~ ♻️ RT to help 1 robot find a new workplace.
1:31

🚨 Apple joins the robotics race! Researchers from Carnegie Mellon University and Apple have developed a robot collision avoidance system. They called it ARMOR and they implemented it on the Fourier GR-1 robot. What is ARMOR? 👘 ARMOR is a system that helps humanoid robots "see" their surroundings better by using small, smart depth sensors placed on their arms. It solves the problem of blind spots and occlusions in traditional robot perception, making robots much safer and more efficient. It uses Time-of-Flight (ToF) sensors to detect obstacles, providing a near-complete view of the robot’s environment. 🔭 A smart software powered by transformer-based AI learns from human movements to help robots plan their actions dynamically. ARMOR reduces collisions by an impressive 63.7%, making robots significantly better at navigating crowded or complex spaces. The system is fast as well! 💨 ARMOR-Policy cuts computational time by 26× compared to traditional planning methods, ensuring robots can act quickly. P.S. Thoughts on this? The research paper is in the comments! ~~~ ♻️ RT to help 1 robot find a new workplace.

Lukas Ziegler

169,472 次观看 • 1 年前

Fei-Fei Li on what simulation can do for robotics that real-world data can't: "You play out events that haven't happened, or cannot happen... And while you play it out, you learn how to act in it." "That's really important in robotics, because we cannot possibly have enough real-world data for that." "Here is a real life example: the industry of self-driving cars. Waymo has officially said they use billions of hours of simulation." "Cars are the simplest kind of robots. So clearly simulation plays a huge role in robotic learning." Fei-Fei Li Yunzhu Li World Labs martin_casado
1:30

Fei-Fei Li on what simulation can do for robotics that real-world data can't: "You play out events that haven't happened, or cannot happen... And while you play it out, you learn how to act in it." "That's really important in robotics, because we cannot possibly have enough real-world data for that." "Here is a real life example: the industry of self-driving cars. Waymo has officially said they use billions of hours of simulation." "Cars are the simplest kind of robots. So clearly simulation plays a huge role in robotic learning." Fei-Fei Li Yunzhu Li World Labs martin_casado

a16z

35,480 次观看 • 22 天前

NEO robot achieves “almost human-like” hand dexterity The Norwegian-American startup 1X has demonstrated new capabilities of its humanoid robot NEO — it has learned to perform fine motor tasks at a level close to humans. The robot can assemble Lego, eat chips, play video games, screw in a light bulb, pick a grape, and carefully hold a wine glass. Previously, one of the biggest challenges for robots was handling small objects — they struggled to understand how much force was needed to grip them. NEO solves this problem with cable-driven actuators and a force-control system: each joint moves the finger while simultaneously measuring pressure. The developers believe these technologies could become an important step toward the creation of universal home robots.
0:42

NEO robot achieves “almost human-like” hand dexterity The Norwegian-American startup 1X has demonstrated new capabilities of its humanoid robot NEO — it has learned to perform fine motor tasks at a level close to humans. The robot can assemble Lego, eat chips, play video games, screw in a light bulb, pick a grape, and carefully hold a wine glass. Previously, one of the biggest challenges for robots was handling small objects — they struggled to understand how much force was needed to grip them. NEO solves this problem with cable-driven actuators and a force-control system: each joint moves the finger while simultaneously measuring pressure. The developers believe these technologies could become an important step toward the creation of universal home robots.

NEXTA

47,071 次观看 • 1 个月前

What if we're approaching robotic manipulation all wrong? Ilya Sutskever makes a fascinating point here: Current approaches throw massive amounts of data at the problem — millions of simulation steps, huge compute. And still, robots can't match human dexterity. Real-world learning of new skills? "Very out of reach." Meanwhile, humans pick up manipulation tasks almost instantly. Our dexterity is unmatched. And we do it with remarkable robustness — no reward shaping, no curriculum design, no training instability. Why the gap? Evolution. 500M years of optimisation for locomotion, vision, and manipulation. For these ancient sensorimotor tasks, maybe brute-force data isn't the answer. Maybe we should be copying the biological algorithms that already solved it. CC: Dwarkesh Patel
1:40

What if we're approaching robotic manipulation all wrong? Ilya Sutskever makes a fascinating point here: Current approaches throw massive amounts of data at the problem — millions of simulation steps, huge compute. And still, robots can't match human dexterity. Real-world learning of new skills? "Very out of reach." Meanwhile, humans pick up manipulation tasks almost instantly. Our dexterity is unmatched. And we do it with remarkable robustness — no reward shaping, no curriculum design, no training instability. Why the gap? Evolution. 500M years of optimisation for locomotion, vision, and manipulation. For these ancient sensorimotor tasks, maybe brute-force data isn't the answer. Maybe we should be copying the biological algorithms that already solved it. CC: Dwarkesh Patel

Jack 🤖

31,262 次观看 • 8 个月前

A new member joins the European humanoid robot team. German company Agile Robotics has launched its first industrial humanoid robot, Agile One, featuring intuitive human-robot interaction, dexterous hands (for grasping small screws and touching the screen), and AI-driven operation trained in the real world. It performs tasks such as material collection, handling, picking and placing, loading and unloading machine tools, tool handling, and precision operations. The emergence of humanoid robots by industrial robot companies is a natural progression; they are designed for areas inaccessible to traditional robotic arms and industrial robots, extending operational systems and enhancing business collaboration capabilities. Agile One will be manufactured in Germany in early 2026 and deployed for on-site training at customers to enhance its AI model capabilities. Soon, Europe will enter its second wave of automation driven by intelligent technology.
1:32

A new member joins the European humanoid robot team. German company Agile Robotics has launched its first industrial humanoid robot, Agile One, featuring intuitive human-robot interaction, dexterous hands (for grasping small screws and touching the screen), and AI-driven operation trained in the real world. It performs tasks such as material collection, handling, picking and placing, loading and unloading machine tools, tool handling, and precision operations. The emergence of humanoid robots by industrial robot companies is a natural progression; they are designed for areas inaccessible to traditional robotic arms and industrial robots, extending operational systems and enhancing business collaboration capabilities. Agile One will be manufactured in Germany in early 2026 and deployed for on-site training at customers to enhance its AI model capabilities. Soon, Europe will enter its second wave of automation driven by intelligent technology.

CyberRobo

72,567 次观看 • 9 个月前