正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

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.

AI Breakfast

238,726 subscribers

70,379 次观看 • 3 年前 •via X (Twitter)

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

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

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 次观看 • 1 年前

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.

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 次观看 • 8 个月前

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:

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 次观看 • 3 个月前

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 ->

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

56,845 次观看 • 8 个月前

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.

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

58,800 次观看 • 1 年前

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

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 次观看 • 1 年前

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 ✈️ CVPR 🙏

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 ✈️ CVPR 🙏

Ilir Aliu

71,502 次观看 • 1 年前

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.

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

33,816 次观看 • 2 个月前

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.

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

3,692,245 次观看 • 2 个月前

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:

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

32,716 次观看 • 1 年前

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.

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

27,765 次观看 • 2 个月前

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.

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🤖

15,243 次观看 • 10 个月前

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.

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

21,269 次观看 • 1 个月前

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

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 次观看 • 1 年前

Follow us KABClub to learn more about young entrepreneurs. At a power substation in southern China’s Guangzhou, humanoid robots are taking over inspection duties. The robot was developed by a local robot maker, but the tech subsidiary of China Southern Power Grid has made modifications by itself, adding more sensors, enhanced hands, and greater AI computing power. While these humanoid robots and robot dogs are still in trial, automated and AI-powered inspection tools have already been widely deployed.

Follow us KABClub to learn more about young entrepreneurs. At a power substation in southern China’s Guangzhou, humanoid robots are taking over inspection duties. The robot was developed by a local robot maker, but the tech subsidiary of China Southern Power Grid has made modifications by itself, adding more sensors, enhanced hands, and greater AI computing power. While these humanoid robots and robot dogs are still in trial, automated and AI-powered inspection tools have already been widely deployed.

KABClub

21,494 次观看 • 10 个月前

Teaching robots how to paint! 💅🏼 This painting robot, for example, mimics human movements with precision to handle repetitive, and tiring tasks. A special device memorizes points in 3D space, which are then sent to the robot's control. The result? A robot that, after a single demonstration, can perform a given action. Keep in mind that it's taught as 'fixed'. 👨🏻‍🔧 That is, it will not be able to react to an anomaly or changing environment. But ultimately, with fewer workers available and many avoiding tough, dirty jobs, robots are helping industries stay efficient and safe. ♻️ RT to help 1 robot find a new workplace!

Teaching robots how to paint! 💅🏼 This painting robot, for example, mimics human movements with precision to handle repetitive, and tiring tasks. A special device memorizes points in 3D space, which are then sent to the robot's control. The result? A robot that, after a single demonstration, can perform a given action. Keep in mind that it's taught as 'fixed'. 👨🏻‍🔧 That is, it will not be able to react to an anomaly or changing environment. But ultimately, with fewer workers available and many avoiding tough, dirty jobs, robots are helping industries stay efficient and safe. ♻️ RT to help 1 robot find a new workplace!

Lukas Ziegler

38,319 次观看 • 1 年前