Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Robots have developed the skill to learn by watching videos: The Visual-Robotics Bridge (VRB) model can teach a robot a new task in roughly 25 minutes using only reference video - without needing human interaction or a simulated environment.

AiBreakfast's profile picture

AI Breakfast

240,431 subscribers

70,389 Aufrufe • vor 3 Jahren •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Super excited about Hydra-0 from Hongyu Li and team! The key idea is to use flow as a shared visual interface across embodiments/objects for controllable video generation, allowing a single generalist world model to learn from human, handheld-gripper, and robot interaction data. My favorite result is the video below: start from a real video of a human doing the task (left), extract the desired object flow, and condition the model on that flow (right). The model then hallucinates a plausible robot motion that could produce the same object motion. Very cool glimpse of how a generalist world model can bridge human demonstrations and robot control.
0:13

Super excited about Hydra-0 from Hongyu Li and team! The key idea is to use flow as a shared visual interface across embodiments/objects for controllable video generation, allowing a single generalist world model to learn from human, handheld-gripper, and robot interaction data. My favorite result is the video below: start from a real video of a human doing the task (left), extract the desired object flow, and condition the model on that flow (right). The model then hallucinates a plausible robot motion that could produce the same object motion. Very cool glimpse of how a generalist world model can bridge human demonstrations and robot control.

Yunzhu Li

10,850 Aufrufe • vor 1 Monat

Scientists have developed a springtail-inspired, centimeter-scale robot that can jump up to 1.4 meters. Learn more in Science Robotics:
0:14

Scientists have developed a springtail-inspired, centimeter-scale robot that can jump up to 1.4 meters. Learn more in Science Robotics:

Science Magazine

31,470 Aufrufe • vor 1 Jahr

This also shows up in the representations learned by the model. We plot the model’s representations of human and robot images. As pre-training is scaled up, the representation of humans and robots become more aligned: to a scaled-up model, human videos "look" like robot demos.
0:10

This also shows up in the representations learned by the model. We plot the model’s representations of human and robot images. As pre-training is scaled up, the representation of humans and robots become more aligned: to a scaled-up model, human videos "look" like robot demos.

Physical Intelligence

120,595 Aufrufe • vor 10 Monaten

30 minutes of video. Robot learns the task. Open-source, end-to-end. An open-source framework for training robot policies from only 30 minutes of human egocentric videos captured via Meta Aria glasses: Achieving zero-shot transfer to robots without any robot data collection. The method relies on Interaction-Centric Tokens that encode hand-object spatial relationships invariant to embodiment and viewpoint, supplemented by auxiliary objectives like object motion prediction and latent consistency to extract richer supervision signals from the same data. HumanEgo demonstrates strong cross-embodiment, cross-environment performance on bimanual tasks, outperforming baselines like ACT and teleop data while being trainable on a single RTX 4090 GPU. Thanks for sharing, Zhi (Leo) Wang. 📌 Website: Paper: Code: Video: ——- Weekly robotics and AI insights. Subscribe free:
0:17

30 minutes of video. Robot learns the task. Open-source, end-to-end. An open-source framework for training robot policies from only 30 minutes of human egocentric videos captured via Meta Aria glasses: Achieving zero-shot transfer to robots without any robot data collection. The method relies on Interaction-Centric Tokens that encode hand-object spatial relationships invariant to embodiment and viewpoint, supplemented by auxiliary objectives like object motion prediction and latent consistency to extract richer supervision signals from the same data. HumanEgo demonstrates strong cross-embodiment, cross-environment performance on bimanual tasks, outperforming baselines like ACT and teleop data while being trainable on a single RTX 4090 GPU. Thanks for sharing, Zhi (Leo) Wang. 📌 Website: Paper: Code: Video: ——- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

17,077 Aufrufe • vor 4 Monaten

Predicting how the environment changes over time is a key task in robotics, enabling all kinds of downstream tasks. Trace Anything is a very interesting look at how you can train models which predict the trajectory each point will take in the future -- you can use this for robot manipulation, video prediction, and more. Learn more ->
0:16

Predicting how the environment changes over time is a key task in robotics, enabling all kinds of downstream tasks. Trace Anything is a very interesting look at how you can train models which predict the trajectory each point will take in the future -- you can use this for robot manipulation, video prediction, and more. Learn more ->

Chris Paxton

58,763 Aufrufe • vor 9 Monaten

How can we leverage diverse human videos to improve robot manipulation? Excited to introduce EgoVLA — a Vision-Language-Action model trained on egocentric human videos by explicitly modeling wrist & hand motion. We build a shared action space between humans and robots, enabling seamless transfer. With some robot demos, EgoVLA becomes a powerful, generalizable robot policy.
0:14

How can we leverage diverse human videos to improve robot manipulation? Excited to introduce EgoVLA — a Vision-Language-Action model trained on egocentric human videos by explicitly modeling wrist & hand motion. We build a shared action space between humans and robots, enabling seamless transfer. With some robot demos, EgoVLA becomes a powerful, generalizable robot policy.

Ruihan Yang

58,941 Aufrufe • vor 1 Jahr

Struggling to manage your reference images in the Sub View palette? Use the new pop-up list to view all your reference images and select the one you want, without needing to tap through each image one by one. You can also rearrange the display order of images or remove them from the popup. Learn more here ↓ #clipstudio
0:14

Struggling to manage your reference images in the Sub View palette? Use the new pop-up list to view all your reference images and select the one you want, without needing to tap through each image one by one. You can also rearrange the display order of images or remove them from the popup. Learn more here ↓ #clipstudio

CLIP STUDIO PAINT

62,236 Aufrufe • vor 1 Jahr

JUST IN: Reimagine Robotics has just emerged from stealth! 🥷🏻 Its approach to robot training is one of the most human-centric I've seen. The founder is Jonathan Scholz, the person who built and led Google DeepMind's Applied Robotics team in London for seven years. This is not a first-time founder taking a swing at robotics. He has spent a decade at the frontier of the field. The philosophy is powerful. He calls it "monkey-see, monkey-do." 🐒 A worker shows the robot what to do. Watches it attempt the task. Corrects it on the spot. The robot learns. No specialist programmers. No months of integration. And it's already working in the real world: → A made-to-order plastics business trained robots to tend 3D printers overnight, removing print beds, operating latches, pressing controls → A hard drive disassembly facility built a three-robot cell combining robots and people to recover critical materials → Time to prototype and test a new robot behaviour reduced from one day to 10 MINUTES That last number is the one that changes everything. When testing a new behaviour takes 10 minutes instead of a day, the entire pace of deployment transforms. Scholz's framing of the human-robot relationship is worth reading carefully: "A robot that learns on the job depends on people. The worker identifies the bottleneck, shows the robot how to help, and corrects it until it is useful." It's August, and we keep getting robotics bangers week in week. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:14

JUST IN: Reimagine Robotics has just emerged from stealth! 🥷🏻 Its approach to robot training is one of the most human-centric I've seen. The founder is Jonathan Scholz, the person who built and led Google DeepMind's Applied Robotics team in London for seven years. This is not a first-time founder taking a swing at robotics. He has spent a decade at the frontier of the field. The philosophy is powerful. He calls it "monkey-see, monkey-do." 🐒 A worker shows the robot what to do. Watches it attempt the task. Corrects it on the spot. The robot learns. No specialist programmers. No months of integration. And it's already working in the real world: → A made-to-order plastics business trained robots to tend 3D printers overnight, removing print beds, operating latches, pressing controls → A hard drive disassembly facility built a three-robot cell combining robots and people to recover critical materials → Time to prototype and test a new robot behaviour reduced from one day to 10 MINUTES That last number is the one that changes everything. When testing a new behaviour takes 10 minutes instead of a day, the entire pace of deployment transforms. Scholz's framing of the human-robot relationship is worth reading carefully: "A robot that learns on the job depends on people. The worker identifies the bottleneck, shows the robot how to help, and corrects it until it is useful." It's August, and we keep getting robotics bangers week in week. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

23,404 Aufrufe • vor 2 Monaten

Can robots learn without training❓ [𝗜𝘁'𝘀 𝗼𝗽𝗲𝗻 𝘀𝗼𝘂𝗿𝗰𝗲𝗱 ⬇ ] Teaching robots to do complex tasks WITHOUT spending hours training them. Sounds cool, right? That's exactly what DIAL-MPC does! The first training-free method for whole-body torque control using full-order dynamics: ✅ Instantly checks if a robot's moves are right or wrong ✅ Adapts quickly to new tasks without needing extra training ✅ Could work hand-in-hand with other robot learning methods Robots are getting smarter AND faster without the need for long training sessions. Website: Paper: Code: Saw this first Haoru Xue 🙏
0:10

Can robots learn without training❓ [𝗜𝘁'𝘀 𝗼𝗽𝗲𝗻 𝘀𝗼𝘂𝗿𝗰𝗲𝗱 ⬇ ] Teaching robots to do complex tasks WITHOUT spending hours training them. Sounds cool, right? That's exactly what DIAL-MPC does! The first training-free method for whole-body torque control using full-order dynamics: ✅ Instantly checks if a robot's moves are right or wrong ✅ Adapts quickly to new tasks without needing extra training ✅ Could work hand-in-hand with other robot learning methods Robots are getting smarter AND faster without the need for long training sessions. Website: Paper: Code: Saw this first Haoru Xue 🙏

Ilir Aliu

71,540 Aufrufe • vor 1 Jahr

Turns out you can train humanoid hands without any robot data. The idea in HUG is quite simple: (a) collect human data with smart glasses, (b) train a human manipulation model, (c) retarget to multi-fingered robot hands.
0:18

Turns out you can train humanoid hands without any robot data. The idea in HUG is quite simple: (a) collect human data with smart glasses, (b) train a human manipulation model, (c) retarget to multi-fingered robot hands.

Lerrel Pinto

34,942 Aufrufe • vor 3 Monaten

Researchers at Columbia University have developed modular robots that can adapt, repair, and even rebuild themselves using a concept called robot metabolism. 🤖 Instead of remaining fixed, these robots can detach, reconnect, and reorganize their own structure based on the task or environment. If one part is damaged, the system can replace or rearrange itself rather than stopping completely. This could reshape the future of disaster response, industrial automation, and even space exploration. The idea of robots that evolve instead of wear out is becoming more than science fiction. What real-world application do you think will benefit most from this technology? 🎥 Media: Columbia University ⚠️ This content is shared for informational purposes only. CTO Robotics Media is a media platform and does not own or develop the technology shown. Credit belongs to the original creators.
0:10

Researchers at Columbia University have developed modular robots that can adapt, repair, and even rebuild themselves using a concept called robot metabolism. 🤖 Instead of remaining fixed, these robots can detach, reconnect, and reorganize their own structure based on the task or environment. If one part is damaged, the system can replace or rearrange itself rather than stopping completely. This could reshape the future of disaster response, industrial automation, and even space exploration. The idea of robots that evolve instead of wear out is becoming more than science fiction. What real-world application do you think will benefit most from this technology? 🎥 Media: Columbia University ⚠️ This content is shared for informational purposes only. CTO Robotics Media is a media platform and does not own or develop the technology shown. Credit belongs to the original creators.

CTO ROBOTICS Media

3,693,765 Aufrufe • vor 4 Monaten

We’re thrilled to announce the launch of Vidu’s Q1 Reference to Video (R2V) model on Civitai - your new go-to for creating crisp 1080p videos using up to 7 image references, along with a limited time Vidu signup bonus! Learn more:
0:16

We’re thrilled to announce the launch of Vidu’s Q1 Reference to Video (R2V) model on Civitai - your new go-to for creating crisp 1080p videos using up to 7 image references, along with a limited time Vidu signup bonus! Learn more:

Civitai

36,568 Aufrufe • vor 1 Jahr

Mondo is the most adorable companion robot. It’s safe around kids, can track and follow a person, and capture high-resolution action videos. Mondo is also doing frontier research in humanoid Video-Action models built on a world model backbone: I have no doubt we’ll be hearing this name a lot in consumer robotics. Thanks Mondo Robotics Shuo Yang for the tour.
0:34

Mondo is the most adorable companion robot. It’s safe around kids, can track and follow a person, and capture high-resolution action videos. Mondo is also doing frontier research in humanoid Video-Action models built on a world model backbone: I have no doubt we’ll be hearing this name a lot in consumer robotics. Thanks Mondo Robotics Shuo Yang for the tour.

The Humanoid Hub

27,957 Aufrufe • vor 3 Monaten

Check out the new interactive humanoid robot, Yogi, introduced by Cartwheel Robotics. Yogi is designed as a companion for everyday life, offering help and companionship in settings from hospitals to living rooms. It features soft silicone skin for safe touch, precision actuators for predictable movement, and simple, natural interaction. The robot continuously learns new abilities for greater utility. Cartwheel's founder, Scott LaValley, has a deep background, having developed over four humanoid systems. His expertise includes nearly a decade developing the Atlas robot at Boston Dynamics, followed by five years at Disney leading the team that created the Groot robot. This extensive, hands-on experience is key to Cartwheel Robotics' innovations.
0:15

Check out the new interactive humanoid robot, Yogi, introduced by Cartwheel Robotics. Yogi is designed as a companion for everyday life, offering help and companionship in settings from hospitals to living rooms. It features soft silicone skin for safe touch, precision actuators for predictable movement, and simple, natural interaction. The robot continuously learns new abilities for greater utility. Cartwheel's founder, Scott LaValley, has a deep background, having developed over four humanoid systems. His expertise includes nearly a decade developing the Atlas robot at Boston Dynamics, followed by five years at Disney leading the team that created the Groot robot. This extensive, hands-on experience is key to Cartwheel Robotics' innovations.

RoboHub🤖

15,307 Aufrufe • vor 1 Jahr

Robot money isn't a meme anymore. Agents already execute, but what they can't do is have real ownership. Every agent runs on a key some human holds. Only on Ritual can agents derive their own private keys without a human custodian or off-chain vault in the loop.
0:16

Robot money isn't a meme anymore. Agents already execute, but what they can't do is have real ownership. Every agent runs on a key some human holds. Only on Ritual can agents derive their own private keys without a human custodian or off-chain vault in the loop.

Ritual Foundation

21,518 Aufrufe • vor 3 Monaten

BaBot: The Ball-Balancing Robot - Real-time PID control on a 2-axis platform, powered by a microcontroller using the same chip as an Arduino. - Precision servos and IR sensors track the ball with speed and accuracy. - Perfect for learning control systems, teaching robotics, or showing off your engineering skills. - Fully open-source & ready to build at Video Credit: Johan Link #engineering #technology #robots #robotics
0:18

BaBot: The Ball-Balancing Robot - Real-time PID control on a 2-axis platform, powered by a microcontroller using the same chip as an Arduino. - Precision servos and IR sensors track the ball with speed and accuracy. - Perfect for learning control systems, teaching robotics, or showing off your engineering skills. - Fully open-source & ready to build at Video Credit: Johan Link #engineering #technology #robots #robotics

Wevolver

48,877 Aufrufe • vor 1 Jahr