正在加载视频...

视频加载失败

返回首页

Robots that act like slime! 🫟 Cornell University engineers developed a robotic collective that behaves less like a machine and more like a material that flows, reshapes, and adapts without centralized control. It consists of dozens of small robots with limited individual mobility that exhibit coordinated motion when entangled....

lukas_m_ziegler's profile picture

Lukas Ziegler

55,410 subscribers

13,026 次观看 • 1 个月前 •via X (Twitter)

LIVE

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

Each weaver ant can pull on a leaf much harder when in a group than when it works alone. The ants’ sticky feet and coordinated legwork, researchers believe, improve the ants’ collective efficiency—a finding that may provide insights into how to build and coordinate swarms of robots that work together. Learn more: News from Science
0:18

Each weaver ant can pull on a leaf much harder when in a group than when it works alone. The ants’ sticky feet and coordinated legwork, researchers believe, improve the ants’ collective efficiency—a finding that may provide insights into how to build and coordinate swarms of robots that work together. Learn more: News from Science

Science Magazine

50,663 次观看 • 10 个月前

😅 Expo Modules got faster again this SDK. You can see how performance compares to Turbo Modules in the benchmarks below. Then check out our docs to learn more about when/why to choose Expo Modules and/or Turbo Modules.
0:10

😅 Expo Modules got faster again this SDK. You can see how performance compares to Turbo Modules in the benchmarks below. Then check out our docs to learn more about when/why to choose Expo Modules and/or Turbo Modules.

Expo

13,785 次观看 • 1 个月前

The concept of a transformable drone - robotic dog that can switch between a machine dog, a machine wolf, and a drone, covering all terrains and airspaces, is truly mind-blowing. It combines the mobility of a robotic quadruped on the ground with the flight capabilities of a drone. In the realm of #Sci-Fi, #AI, it's like a futuristic hybrid that could revolutionize various fields, from exploration to surveillance. With its shape-shifting ability, it offers endless possibilities and a peek into a high-tech, future-forward world.
0:13

The concept of a transformable drone - robotic dog that can switch between a machine dog, a machine wolf, and a drone, covering all terrains and airspaces, is truly mind-blowing. It combines the mobility of a robotic quadruped on the ground with the flight capabilities of a drone. In the realm of #Sci-Fi, #AI, it's like a futuristic hybrid that could revolutionize various fields, from exploration to surveillance. With its shape-shifting ability, it offers endless possibilities and a peek into a high-tech, future-forward world.

Zhang Heqing

37,086 次观看 • 1 年前

Polymorphic moulding: a manufacturing method that forms parts using a grid of computer-controlled pins: Each pin can move up or down independently, so together they shape a surface that acts like a custom mould. Instead of building a fixed mould for every product, the machine quickly repositions the pins to match a new digital model. This means a mould can be created in minutes, used, and then reshaped again for the next design. Because the hardware stays the same and only its configuration changes: > no permanent tooling is needed > very little material is wasted > setup time between products is minimal The system essentially turns mould making into a programmable process. Engineers send a design file, the pins form the mould geometry, and the material is cast or formed inside it. Especially useful for rapid prototyping and customised manufacturing, where many different shapes must be produced in small quantities without rebuilding tools each time. Credit: ---- Weekly robotics and AI insights. Subscribe free:
0:14

Polymorphic moulding: a manufacturing method that forms parts using a grid of computer-controlled pins: Each pin can move up or down independently, so together they shape a surface that acts like a custom mould. Instead of building a fixed mould for every product, the machine quickly repositions the pins to match a new digital model. This means a mould can be created in minutes, used, and then reshaped again for the next design. Because the hardware stays the same and only its configuration changes: > no permanent tooling is needed > very little material is wasted > setup time between products is minimal The system essentially turns mould making into a programmable process. Engineers send a design file, the pins form the mould geometry, and the material is cast or formed inside it. Especially useful for rapid prototyping and customised manufacturing, where many different shapes must be produced in small quantities without rebuilding tools each time. Credit: ---- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

38,234 次观看 • 4 个月前

High-speed labeling is harder than it looks! 🍼 I remember when I was programming robots myself and the struggle of making an application really repeatable. It was hard. Super hard. That's why seeing a machine working as smooth as here, it's incredible! 🤯 Applying shrink sleeves without wrinkles or misalignment becomes a real bottleneck at scale. Krones machine solves that by combining fast application with precise servo-controlled cutting. It can handle up to 50,000 containers per hour, keep labels perfectly aligned, and switch between bottle shapes with minimal downtime. For manufacturers, that reliability matters. Magic!!! ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:17

High-speed labeling is harder than it looks! 🍼 I remember when I was programming robots myself and the struggle of making an application really repeatable. It was hard. Super hard. That's why seeing a machine working as smooth as here, it's incredible! 🤯 Applying shrink sleeves without wrinkles or misalignment becomes a real bottleneck at scale. Krones machine solves that by combining fast application with precise servo-controlled cutting. It can handle up to 50,000 containers per hour, keep labels perfectly aligned, and switch between bottle shapes with minimal downtime. For manufacturers, that reliability matters. Magic!!! ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

121,821 次观看 • 6 个月前

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 次观看 • 4 个月前

Oh my! The cute baby and the adorable pet cat are just so lovely! Look at the baby with those chubby cheeks and bright, innocent eyes that seem to hold the whole universe of curiosity. Every little movement of the baby, like the way they wave their tiny hands or kick their little feet, is filled with an irresistible charm. And the cat! With its soft fur that shimmers in the light, and those big, round eyes that are like two glistening jewels. When it moves, it's like a fluffy ball of cuteness gliding gracefully. When the baby and the cat are together, it's a scene straight out of a heart - melting fairytale. The baby's giggles as they try to touch the cat's tail, and the cat's gentle purrs as it rubs against the baby's side create a symphony of cuteness that can make anyone's heart melt in an instant.
0:10

Oh my! The cute baby and the adorable pet cat are just so lovely! Look at the baby with those chubby cheeks and bright, innocent eyes that seem to hold the whole universe of curiosity. Every little movement of the baby, like the way they wave their tiny hands or kick their little feet, is filled with an irresistible charm. And the cat! With its soft fur that shimmers in the light, and those big, round eyes that are like two glistening jewels. When it moves, it's like a fluffy ball of cuteness gliding gracefully. When the baby and the cat are together, it's a scene straight out of a heart - melting fairytale. The baby's giggles as they try to touch the cat's tail, and the cat's gentle purrs as it rubs against the baby's side create a symphony of cuteness that can make anyone's heart melt in an instant.

Zhang Heqing

52,897 次观看 • 1 年前

It’s actually amusing how every time I post about Blake Lively and Ryan Reynolds, a community note suddenly appears like clockwork. At this point it feels less like fact checking and more like an organised reflex. Community Notes were meant to add context where it genuinely matters, not to be hijacked by fan groups who mass upvote notes simply because they dislike the post. The feature has become almost useless when outcomes are driven by follower counts instead of factual necessity. If one side has more coordinated supporters, they can force a note through whether the post needs correction or not. That turns what should be a transparency tool into a popularity contest. When “consensus” is determined by numbers rather than accuracy, it stops being about truth and starts being about control. And with that, you can stack the notes as high as you want. It won’t rewrite my opinion of Ryan Reynolds and Blake Lively.
0:12

It’s actually amusing how every time I post about Blake Lively and Ryan Reynolds, a community note suddenly appears like clockwork. At this point it feels less like fact checking and more like an organised reflex. Community Notes were meant to add context where it genuinely matters, not to be hijacked by fan groups who mass upvote notes simply because they dislike the post. The feature has become almost useless when outcomes are driven by follower counts instead of factual necessity. If one side has more coordinated supporters, they can force a note through whether the post needs correction or not. That turns what should be a transparency tool into a popularity contest. When “consensus” is determined by numbers rather than accuracy, it stops being about truth and starts being about control. And with that, you can stack the notes as high as you want. It won’t rewrite my opinion of Ryan Reynolds and Blake Lively.

Queen Esther

41,096 次观看 • 4 个月前

Harriet Harman, "More and more when I see Trump, it reminds me that it's a system with no checks and balances in it" "It is the most awful political spectacle of political hegemony" "And it affects everybody in the world"
0:13

Harriet Harman, "More and more when I see Trump, it reminds me that it's a system with no checks and balances in it" "It is the most awful political spectacle of political hegemony" "And it affects everybody in the world"

Farrukh

28,114 次观看 • 1 年前

Inspired by elephant trunks, scientists have developed a soft, flexible robotic arm that can twist to stiffen, enabling it to manipulate and install a lightbulb. Learn more in Science Robotics:
0:15

Inspired by elephant trunks, scientists have developed a soft, flexible robotic arm that can twist to stiffen, enabling it to manipulate and install a lightbulb. Learn more in Science Robotics:

Science Magazine

27,890 次观看 • 1 年前

Inspired by elephant trunks, scientists have developed a soft, flexible robotic arm that can twist to stiffen, enabling it to manipulate and install a lightbulb. Learn more in Science Robotics:
0:15

Inspired by elephant trunks, scientists have developed a soft, flexible robotic arm that can twist to stiffen, enabling it to manipulate and install a lightbulb. Learn more in Science Robotics:

Science Magazine

23,608 次观看 • 1 年前

Spiders as robotic grippers? 🕷️ Researchers made a stunning discovery at Rice University. Dead spiders are being used as mechanical grippers. Yes, they use dead spiders as grippers... But how? 👀 It turns out that spiders use hydraulics to move their legs. They extend their legs by contracting their prosoma chamber, which sends fluid into their bodies. Scientists selected wolf spiders that can lift 130% of their weight. Using such a solution could be useful for pick-and-place processes in electronics assembly, for instance. Their discovery might start the field of necrobotics. Given my arachnophobia, I'm not sure how I'd react to such a grip. 🕸️ ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:13

Spiders as robotic grippers? 🕷️ Researchers made a stunning discovery at Rice University. Dead spiders are being used as mechanical grippers. Yes, they use dead spiders as grippers... But how? 👀 It turns out that spiders use hydraulics to move their legs. They extend their legs by contracting their prosoma chamber, which sends fluid into their bodies. Scientists selected wolf spiders that can lift 130% of their weight. Using such a solution could be useful for pick-and-place processes in electronics assembly, for instance. Their discovery might start the field of necrobotics. Given my arachnophobia, I'm not sure how I'd react to such a grip. 🕸️ ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

301,136 次观看 • 6 个月前

Scientists at Cornell University have developed a “biohybrid” robot that moves in response to signals from the nervous system of fungi. These robots incorporate mycelium, the root system of fungi, which senses and communicates through electrical signals. Researchers grew mycelium directly into the robot's electronics, allowing it to drive the machine by processing these natural signals. The team built two versions: one with wheels and another spider-shaped with soft legs. Both versions respond to light and other stimuli, with the mycelium sending signals to the robot's actuators to initiate movement. Experiments demonstrated the robots' ability to move based on natural mycelium signals, react to ultraviolet light, and even allow manual override. Future developments may include multiple inputs like chemical signatures, enhancing the robot's ability to autonomously interact with its environment. Credit: Cornell University #engineering
0:12

Scientists at Cornell University have developed a “biohybrid” robot that moves in response to signals from the nervous system of fungi. These robots incorporate mycelium, the root system of fungi, which senses and communicates through electrical signals. Researchers grew mycelium directly into the robot's electronics, allowing it to drive the machine by processing these natural signals. The team built two versions: one with wheels and another spider-shaped with soft legs. Both versions respond to light and other stimuli, with the mycelium sending signals to the robot's actuators to initiate movement. Experiments demonstrated the robots' ability to move based on natural mycelium signals, react to ultraviolet light, and even allow manual override. Future developments may include multiple inputs like chemical signatures, enhancing the robot's ability to autonomously interact with its environment. Credit: Cornell University #engineering

Wevolver

22,008 次观看 • 1 年前

hello ❤️ I managed to fix the texture so that they match some more with vanilla, made them rtgi+mxao+dof compatible, and posed the braid to test how well or poorly it behaved when pushed to the front! I also really like how it moves ❤️ I hope you like it too!
0:18

hello ❤️ I managed to fix the texture so that they match some more with vanilla, made them rtgi+mxao+dof compatible, and posed the braid to test how well or poorly it behaved when pushed to the front! I also really like how it moves ❤️ I hope you like it too!

june

189,804 次观看 • 5 个月前

Normally I wouldn’t be this interested in chip tech, even considering this is impressive. Huawei has found a creative workaround to catch up with the likes of TSMC. But what makes it even more compelling to me is the bigger story and resilience behind it. Starting in 2019, Huawei faced intense sanctions that significantly restricted their access to advanced chip technology and global supply chains. For a while, it looked like this would seriously damage or even sideline them in major way. A lot of people thought the company was done or would be stuck far behind for years. Yet Huawei refused to die. Pushed hard by those challenges, they didn’t fold or give up. Instead, they dug in, poured everything into self-reliance, research, and fresh thinking. They reinvented how they approach problems and entered a whole new era of innovation and creativity that probably wouldn’t have happened this quickly, or maybe even at all, without being forced into that corner. That’s the part I find truly inspiring. When the pressure was at its heaviest, they turned obstacles into fuel. They focused on what they could control, built up their own capabilities, and came back stronger with real breakthroughs. It’s rare to see that kind of determination pay off in such a visible way. So many observers probably believed the sanctions would destroy them or at least slow them down permanently. Instead, they lit a fire under the whole company and sparked a level of ingenuity that feels genuinely exciting to watch unfold. Sanctions were supposed to end them. Instead, they pushed Huawei into this impressive new chapter of self-reliance and forward momentum. That kind of comeback story is exactly why I’m such a big fan and why moments like this announcement feel so satisfying.
0:11

Normally I wouldn’t be this interested in chip tech, even considering this is impressive. Huawei has found a creative workaround to catch up with the likes of TSMC. But what makes it even more compelling to me is the bigger story and resilience behind it. Starting in 2019, Huawei faced intense sanctions that significantly restricted their access to advanced chip technology and global supply chains. For a while, it looked like this would seriously damage or even sideline them in major way. A lot of people thought the company was done or would be stuck far behind for years. Yet Huawei refused to die. Pushed hard by those challenges, they didn’t fold or give up. Instead, they dug in, poured everything into self-reliance, research, and fresh thinking. They reinvented how they approach problems and entered a whole new era of innovation and creativity that probably wouldn’t have happened this quickly, or maybe even at all, without being forced into that corner. That’s the part I find truly inspiring. When the pressure was at its heaviest, they turned obstacles into fuel. They focused on what they could control, built up their own capabilities, and came back stronger with real breakthroughs. It’s rare to see that kind of determination pay off in such a visible way. So many observers probably believed the sanctions would destroy them or at least slow them down permanently. Instead, they lit a fire under the whole company and sparked a level of ingenuity that feels genuinely exciting to watch unfold. Sanctions were supposed to end them. Instead, they pushed Huawei into this impressive new chapter of self-reliance and forward momentum. That kind of comeback story is exactly why I’m such a big fan and why moments like this announcement feel so satisfying.

Daniel Dumbrill

56,350 次观看 • 1 个月前

A metal origami! 🪭 This method is called Hyperbolic Metal Forming and is hypnotizing to watch. Instead of shaping metal with slow mechanical force, HMF uses controlled shockwaves to form complex geometries at extreme speed, often without the need for heavy dies or post-processing. The result is stronger, lighter parts with shapes that are almost impossible using traditional stamping. That’s why you see it popping up in aerospace, automotive structures, and defense components. Think of it like metal origami, but driven by high-energy pulses instead of presses. A small reminder that some things in manufacturing come from physics, not just automation. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:18

A metal origami! 🪭 This method is called Hyperbolic Metal Forming and is hypnotizing to watch. Instead of shaping metal with slow mechanical force, HMF uses controlled shockwaves to form complex geometries at extreme speed, often without the need for heavy dies or post-processing. The result is stronger, lighter parts with shapes that are almost impossible using traditional stamping. That’s why you see it popping up in aerospace, automotive structures, and defense components. Think of it like metal origami, but driven by high-energy pulses instead of presses. A small reminder that some things in manufacturing come from physics, not just automation. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

567,473 次观看 • 7 个月前

I hope more people are starting to see what's happening. Whenever people find a candidate to take on the corrupt system, the system protects itself by either co-opting the candidate or pouring in millions of dollars from AIPAC and/or billionaires to crush their campaign. It happened with Bernie and Massie, and it will happen to the next candidate the people put their time, energy, and hope into too. The only thing that can save us is each other. We the people must cast aside the divide-and-conquer politics of our corporate rulers and rise up together to fight for a better system that puts people over profits.
0:18

I hope more people are starting to see what's happening. Whenever people find a candidate to take on the corrupt system, the system protects itself by either co-opting the candidate or pouring in millions of dollars from AIPAC and/or billionaires to crush their campaign. It happened with Bernie and Massie, and it will happen to the next candidate the people put their time, energy, and hope into too. The only thing that can save us is each other. We the people must cast aside the divide-and-conquer politics of our corporate rulers and rise up together to fight for a better system that puts people over profits.

Power to the People ☭🕊

11,854 次观看 • 1 个月前