Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Berry pickup from Kyber Labs Robot hands that can pick up fragile objects quickly will be important to solving long-tail of robotics problems not currently automated

chris_j_paxton's profile picture

Chris Paxton

33,848 subscribers

33,336 Aufrufe • vor 1 Monat •via X (Twitter)

Wissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

In Super Mario Sunshine, Shadow Mario can pick up and carry Peach. In fact, Peach can always be picked up; the difference between Mario and Shadow Mario is that Mario is not allowed to do it. Below is footage of Mario's ability to pick up Peach being enabled.
0:10

In Super Mario Sunshine, Shadow Mario can pick up and carry Peach. In fact, Peach can always be picked up; the difference between Mario and Shadow Mario is that Mario is not allowed to do it. Below is footage of Mario's ability to pick up Peach being enabled.

Supper Mario Broth

508,451 Aufrufe • vor 2 Jahren

We’re solving problems that aren’t problems in America This is the new automated ketchup dispenser from Server Products at Raising Canes I think there is a bigger plan with these new dispensers, and they’re being rolled out at multiple chains. These dispensers are IoT-enabled in newer models, meaning they can monitoring usage and inventory This kind of tracking and quickly turn into new features like restricting the amount of condiments one user can get, similar to what’s being done with soda machines and QR codes It starts as convenience, and ends with restrictions and control
0:10

We’re solving problems that aren’t problems in America This is the new automated ketchup dispenser from Server Products at Raising Canes I think there is a bigger plan with these new dispensers, and they’re being rolled out at multiple chains. These dispensers are IoT-enabled in newer models, meaning they can monitoring usage and inventory This kind of tracking and quickly turn into new features like restricting the amount of condiments one user can get, similar to what’s being done with soda machines and QR codes It starts as convenience, and ends with restrictions and control

Wall Street Apes

944,054 Aufrufe • vor 2 Monaten

Our team is currently building a monitoring tool to monitor the up-time of the #nodes. This will help us ensure that our platform is running smoothly and efficiently, and we'll be able to quickly identify and resolve any issues that may arise. #buidl #evm #validators
0:13

Our team is currently building a monitoring tool to monitor the up-time of the #nodes. This will help us ensure that our platform is running smoothly and efficiently, and we'll be able to quickly identify and resolve any issues that may arise. #buidl #evm #validators

5ireChain (What's cooking?)

87,556 Aufrufe • vor 3 Jahren

You can't 3D reconstruct glass from images... ...WRONG! Thanks for video diffusion, now just about anything is possible! Introducing...Diffusion Knows Transparency (DKT) Transparent and reflective objects usually break robot vision and photogrammetry pipelines because they don't follow the "solid object" rules standard cameras expect. DKT is a new AI model that repurposes the "internal physics engine" found in video generation models to solve this problem. Researchers took a massive video diffusion model (WAN) and fine-tuned it using a custom-built synthetic dataset to turn it into a high-precision depth sensor. To train the AI, they built the first massive synthetic video library of transparent objects, 1.32 million frames of perfectly labeled glass and metal objects in motion. Without ever seeing a "real" labeled video of glass during training, the model (DKT) outperformed all previous specialized systems on real-world benchmarks (ClearPose, DREDS). They created a "lightweight" 1.3B parameter version that runs fast enough (0.17s per frame) to be used on actual robot hardware. Two reasons I find this project important: 1. It further proves that synthetic data will be essential for training the next generation vision models. 2. In real-world robotic tests, using DKT's depth maps nearly doubled the success rate of robot arms trying to pick up objects on tricky reflective or translucent surfaces. At home robots will need to interact with these types of objects on a daily basis. Check out the project page here: Code is LIVE! #Computervision #Robotics #AI
0:14

You can't 3D reconstruct glass from images... ...WRONG! Thanks for video diffusion, now just about anything is possible! Introducing...Diffusion Knows Transparency (DKT) Transparent and reflective objects usually break robot vision and photogrammetry pipelines because they don't follow the "solid object" rules standard cameras expect. DKT is a new AI model that repurposes the "internal physics engine" found in video generation models to solve this problem. Researchers took a massive video diffusion model (WAN) and fine-tuned it using a custom-built synthetic dataset to turn it into a high-precision depth sensor. To train the AI, they built the first massive synthetic video library of transparent objects, 1.32 million frames of perfectly labeled glass and metal objects in motion. Without ever seeing a "real" labeled video of glass during training, the model (DKT) outperformed all previous specialized systems on real-world benchmarks (ClearPose, DREDS). They created a "lightweight" 1.3B parameter version that runs fast enough (0.17s per frame) to be used on actual robot hardware. Two reasons I find this project important: 1. It further proves that synthetic data will be essential for training the next generation vision models. 2. In real-world robotic tests, using DKT's depth maps nearly doubled the success rate of robot arms trying to pick up objects on tricky reflective or translucent surfaces. At home robots will need to interact with these types of objects on a daily basis. Check out the project page here: Code is LIVE! #Computervision #Robotics #AI

Jonathan Stephens

17,712 Aufrufe • vor 7 Monaten

SOOO many problems. I don’t understand how this can possibly be the play you design in that huddle. • Donovan Mitchell inbounding???? • Not a single pick • DEAN WADE in the game • A contested Evan Mobley deep mid range to tie the game Just awful from Kenny.
0:14

SOOO many problems. I don’t understand how this can possibly be the play you design in that huddle. • Donovan Mitchell inbounding???? • Not a single pick • DEAN WADE in the game • A contested Evan Mobley deep mid range to tie the game Just awful from Kenny.

𝕱𝖊𝖗𝖗𝖊𝖙 𝖆𝖑𝖑𝖊𝖓

56,982 Aufrufe • vor 8 Monaten

It's the little things that make me excited about the future. Many people are (rightfully) worried that AI and robotics will take their jobs. Yes, it's about money they need to live on, and solutions are needed. At the same time, it's often work that's strenuous and tedious. So we can be glad when robots take these tasks off our hands. Furthermore, robots don't need breaks, vacations, or sleep. They can be scaled quickly and are efficient. Globalization, and humanity as a whole, can therefore benefit massively from this increase in efficiency.
0:15

It's the little things that make me excited about the future. Many people are (rightfully) worried that AI and robotics will take their jobs. Yes, it's about money they need to live on, and solutions are needed. At the same time, it's often work that's strenuous and tedious. So we can be glad when robots take these tasks off our hands. Furthermore, robots don't need breaks, vacations, or sleep. They can be scaled quickly and are efficient. Globalization, and humanity as a whole, can therefore benefit massively from this increase in efficiency.

Chubby♨️

25,528 Aufrufe • vor 5 Monaten

Didn't take long for BOS to get into their first Spain rep. We also get a coverage clue from OKC -- Hartenstein creeps up to the level of the screen. Hidden beauty of Chet having the Hauser assignment (!) is that he winds up low by default, can pick up the Brown drive.
0:10

Didn't take long for BOS to get into their first Spain rep. We also get a coverage clue from OKC -- Hartenstein creeps up to the level of the screen. Hidden beauty of Chet having the Hauser assignment (!) is that he winds up low by default, can pick up the Brown drive.

Nekias (Nuh-KY-us) Duncan

58,402 Aufrufe • vor 5 Monaten

The future of robotics isn't coming - it's already here. Experience it in person at CES 2025. We're thrilled to announce that Richtech Robotics will exhibit at #CES2025 from January 7-10, 2025! Visit booth #8549 to experience the cutting-edge of robotic technology and witness our innovative solutions firsthand. Connect with us at CES to explore partnership opportunities and discover how Richtech Robotics can transform your operations. Our team will be on hand to answer your questions and demonstrate the incredible capabilities of our robotic lineup. $RR #RichtechRobotics #Medbot #ADAM #Matradee #Scorpion
0:14

The future of robotics isn't coming - it's already here. Experience it in person at CES 2025. We're thrilled to announce that Richtech Robotics will exhibit at #CES2025 from January 7-10, 2025! Visit booth #8549 to experience the cutting-edge of robotic technology and witness our innovative solutions firsthand. Connect with us at CES to explore partnership opportunities and discover how Richtech Robotics can transform your operations. Our team will be on hand to answer your questions and demonstrate the incredible capabilities of our robotic lineup. $RR #RichtechRobotics #Medbot #ADAM #Matradee #Scorpion

Richtech Robotics

52,113 Aufrufe • vor 1 Jahr

Today may be the ImageNet moment for robotics. RT-X: the largest open-source robot dataset ever compiled, across 33 institutes, 22 robot hardware, 527 skills, and 1M episodes. Why is robotics lagging so far behind NLP, vision, and other AI domains? Data scarcity is the main culprit to blame, among other difficulties. Unlike text, images, and videos, you cannot download mass amounts of onboard robot control data from the internet. They simply don't exist in the wild. 11 yrs ago, ImageNet kicked off the deep learning revolution. 3-4 yrs ago, internet-scale data fueled the first GPTs and Diffusions that define this era of foundation models. I think 2023 is finally the year for robotics to scale up. Robot foundation models like VIMA ( my team's work at NVIDIA) and RT-1/2 ( Google DeepMind's effort) are extremely data hungry. While massively parallel simulations like NVIDIA IsaacGym & Omniverse can alleviate the problem to some extent, it's still not quite enough to bridge the gap to the messy, physical world. This new dataset is not just a technical contribution. I also see it as a commendable effort to overcome institutional bureaucracies and unite researchers from around the world to tackle a grand challenge together. Robotics will be the final holy grail that we capture in AI. We are not there yet, but ascending in the right gradient direction. RT-X website: Launch blog:
0:11

Today may be the ImageNet moment for robotics. RT-X: the largest open-source robot dataset ever compiled, across 33 institutes, 22 robot hardware, 527 skills, and 1M episodes. Why is robotics lagging so far behind NLP, vision, and other AI domains? Data scarcity is the main culprit to blame, among other difficulties. Unlike text, images, and videos, you cannot download mass amounts of onboard robot control data from the internet. They simply don't exist in the wild. 11 yrs ago, ImageNet kicked off the deep learning revolution. 3-4 yrs ago, internet-scale data fueled the first GPTs and Diffusions that define this era of foundation models. I think 2023 is finally the year for robotics to scale up. Robot foundation models like VIMA ( my team's work at NVIDIA) and RT-1/2 ( Google DeepMind's effort) are extremely data hungry. While massively parallel simulations like NVIDIA IsaacGym & Omniverse can alleviate the problem to some extent, it's still not quite enough to bridge the gap to the messy, physical world. This new dataset is not just a technical contribution. I also see it as a commendable effort to overcome institutional bureaucracies and unite researchers from around the world to tackle a grand challenge together. Robotics will be the final holy grail that we capture in AI. We are not there yet, but ascending in the right gradient direction. RT-X website: Launch blog:

Jim Fan

265,061 Aufrufe • vor 2 Jahren

If you’ve been ignoring Axis Robotics because it looks like another random points farm, read this. In the last 48 hours, Unitree said robotics is approaching its "ChatGPT moment", while the chairman of ACE Robotics believes it could happen by the end of 2027. But for robots to reach that level, they need a crazy amount of training data. That’s exactly what Axis is building. You control simulated robots directly from your browser, complete simple tasks and earn points. Those movements also help create data that can be used to train real robots. And this isn’t some tiny experiment anymore: - $12M raised - 123K+ contributors - 3M+ robot trajectories - Community data already used to train a real robot So yeah, we’re basically farming a potential airdrop while teaching our future robot servants how to work 😂 If you haven’t started yet, it’s completely free. You only need a tiny amount of gas on Base to sign your completed tasks. ✅ Start farming Axis points: Important: Sign every completed task from the History page, otherwise you won’t receive the points.
0:12

If you’ve been ignoring Axis Robotics because it looks like another random points farm, read this. In the last 48 hours, Unitree said robotics is approaching its "ChatGPT moment", while the chairman of ACE Robotics believes it could happen by the end of 2027. But for robots to reach that level, they need a crazy amount of training data. That’s exactly what Axis is building. You control simulated robots directly from your browser, complete simple tasks and earn points. Those movements also help create data that can be used to train real robots. And this isn’t some tiny experiment anymore: - $12M raised - 123K+ contributors - 3M+ robot trajectories - Community data already used to train a real robot So yeah, we’re basically farming a potential airdrop while teaching our future robot servants how to work 😂 If you haven’t started yet, it’s completely free. You only need a tiny amount of gas on Base to sign your completed tasks. ✅ Start farming Axis points: Important: Sign every completed task from the History page, otherwise you won’t receive the points.

Pranjal Bora 🧭

29,321 Aufrufe • vor 4 Tagen

The likely next Chancellor of Germany Friedrich Merz speaking after tonight’s election victory: “For me, the absolute priority will be to strengthen Europe as quickly as possible so that, step by step, we can really achieve independence from the USA”
0:10

The likely next Chancellor of Germany Friedrich Merz speaking after tonight’s election victory: “For me, the absolute priority will be to strengthen Europe as quickly as possible so that, step by step, we can really achieve independence from the USA”

Visegrád 24

353,376 Aufrufe • vor 1 Jahr

even so, I trust that any new watcher will be able to pick up what's going on. The people who made the OVAs shown from time and time again that they have faith in their viewers that they'll be able to understand the world building that culminated to this point. You can start the other shows prior to this, either before or after this OVA and it will still feel like a proper climax leading up to this. The story beats in this show are pretty good in the sense that anyone can understand it, it's not universally profound but it does a good job in highlighting perspectives of every side and have a glimpse at what happened that lead up to it.
0:19

even so, I trust that any new watcher will be able to pick up what's going on. The people who made the OVAs shown from time and time again that they have faith in their viewers that they'll be able to understand the world building that culminated to this point. You can start the other shows prior to this, either before or after this OVA and it will still feel like a proper climax leading up to this. The story beats in this show are pretty good in the sense that anyone can understand it, it's not universally profound but it does a good job in highlighting perspectives of every side and have a glimpse at what happened that lead up to it.

delty

41,473 Aufrufe • vor 1 Jahr

Kitten update #25: We're starting to let the kittens explore more of the house. The soda cases are blocking the door gap to keep them from escaping, but it's also provided a convenient barrier that Buffy respects so that the door can be open and the kitties can decide whether to engage with her or not. So far, they have enthusiastically chosen YES. Fortunately, Buffy has realized that the face end tastes better than the tail end because it might have some cat food on it. Besides the dog time, they also got to have new experiences with wood floors (soooo slippery!), stairs (fun to leap on), and the robot vacuum (not really that scary but not really making friends either). I suspect the afternoon nap will be extra intense today.
0:18

Kitten update #25: We're starting to let the kittens explore more of the house. The soda cases are blocking the door gap to keep them from escaping, but it's also provided a convenient barrier that Buffy respects so that the door can be open and the kitties can decide whether to engage with her or not. So far, they have enthusiastically chosen YES. Fortunately, Buffy has realized that the face end tastes better than the tail end because it might have some cat food on it. Besides the dog time, they also got to have new experiences with wood floors (soooo slippery!), stairs (fun to leap on), and the robot vacuum (not really that scary but not really making friends either). I suspect the afternoon nap will be extra intense today.

Andrea Burkhart 🐟🐟🐟🐟🏴‍☠️

33,478 Aufrufe • vor 11 Monaten

AI-Powered weed control! 🌱 The LaserWeeder machine from Carbon Robotics has captured the imagination of American farmers. This technology uses AI system to identify weeds in crops and zap them with precision thermal bursts from lasers. Bit of facts about the cool robot: → The machine can remove weeds from over 40 crops and can also be used for thinning crops. → It can operate in virtually all weather conditions, with millimeter accuracy at all times, and can work through the night thanks to its built-in lighting system. → High-resolution cameras and computer machine learning enable it to distinguish weeds from crops in milliseconds. → The LaserWeeder can replace about 70 workers on farms where manual weeding is used, and can weed up to four acres per hour. What other applications can we expect to see in the future in farming applications? Btw. I believe farming robots are A HUGE THING in robotics! 🔥 ~~ ♻ Join the weekly robotics newsletter, and never miss any news →
0:10

AI-Powered weed control! 🌱 The LaserWeeder machine from Carbon Robotics has captured the imagination of American farmers. This technology uses AI system to identify weeds in crops and zap them with precision thermal bursts from lasers. Bit of facts about the cool robot: → The machine can remove weeds from over 40 crops and can also be used for thinning crops. → It can operate in virtually all weather conditions, with millimeter accuracy at all times, and can work through the night thanks to its built-in lighting system. → High-resolution cameras and computer machine learning enable it to distinguish weeds from crops in milliseconds. → The LaserWeeder can replace about 70 workers on farms where manual weeding is used, and can weed up to four acres per hour. What other applications can we expect to see in the future in farming applications? Btw. I believe farming robots are A HUGE THING in robotics! 🔥 ~~ ♻ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

54,776 Aufrufe • vor 8 Monaten