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 Doing Stuff #61 | Bimanual Nut Pick and Threading This is a real customer task: one step in a longer multi-part sequence we’re training in our labs. Threading requires precise alignment, force control, and fine manipulation. These are foundational capabilities for industrial dexterity applications that are currently inaccessible... show more

Sanctuary AI

10,161 subscribers

38,402 次观看 • 3 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

1 条评论

MendysRobotics 的头像

MendysRobotics3 个月前

Threading is a brutal task to learn from demos - it punishes force-control errors that pick-and-place forgives. Curious whether the teleop rig captures force/tactile data or just vision; that gap usually decides how well the autonomous policy transfers.

相关视频

Robots Doing Stuff is back. Ready? Robots Doing Stuff #60 | Welding Policy Repetitive, quick, and precise. Automating this manufacturing welding task with Physical AI required the successful execution of all of the above in order to achieve a consistent weld quality at production-level speed. Visit to learn more about our Physical AI-enabled automation solutions. #PhysicalAI #Robotics #Automation #AI #Manufacturing #Welding

Robots Doing Stuff is back. Ready? Robots Doing Stuff #60 | Welding Policy Repetitive, quick, and precise. Automating this manufacturing welding task with Physical AI required the successful execution of all of the above in order to achieve a consistent weld quality at production-level speed. Visit to learn more about our Physical AI-enabled automation solutions. #PhysicalAI #Robotics #Automation #AI #Manufacturing #Welding

Sanctuary AI

32,886 次观看 • 4 个月前

One brain. For any robot. 🤖 We’re launching Gemini Robotics 2: our next-generation physical AI bringing full body intelligence to humanoids, advanced dexterity, multi-robot teamwork and more.

One brain. For any robot. 🤖 We’re launching Gemini Robotics 2: our next-generation physical AI bringing full body intelligence to humanoids, advanced dexterity, multi-robot teamwork and more.

Google DeepMind

2,626,270 次观看 • 2 个月前

This is what Production-Ready Physical AI looks like. Yesterday, we announced our expanded Physical AI strategy, backed by a demonstration of a complex industrial wire plugging task completed with a 99.5%+ success rate and a 2.54-second cycle time. Why is this significant? "Manipulating a flexible wire into a moving target on a live conveyor is exactly the kind of contact-rich dexterity problem that has kept tasks like this out of reach for traditional automation ... Solving it required models built around performance from day one with reliability, cycle time, and safety measured against real production benchmarks. That's the bar Physical AI has to clear to matter in enterprise environments, and it's the bar we've now cleared." — Olivia Norton, CTO at Sanctuary AI. Read more:

This is what Production-Ready Physical AI looks like. Yesterday, we announced our expanded Physical AI strategy, backed by a demonstration of a complex industrial wire plugging task completed with a 99.5%+ success rate and a 2.54-second cycle time. Why is this significant? "Manipulating a flexible wire into a moving target on a live conveyor is exactly the kind of contact-rich dexterity problem that has kept tasks like this out of reach for traditional automation ... Solving it required models built around performance from day one with reliability, cycle time, and safety measured against real production benchmarks. That's the bar Physical AI has to clear to matter in enterprise environments, and it's the bar we've now cleared." — Olivia Norton, CTO at Sanctuary AI. Read more:

Sanctuary AI

32,816 次观看 • 4 个月前

Introducing FLUX-mimic, a next-generation Video-Action Model for general purpose dexterity, developed in partnership with Black Forest Labs. Late last year we published mimic-video and introduced Video-Action Models (VAM): a new family of robotics foundation models built on top of video generation models. We showed that robot control reduces to visual prediction, and that robot capability is downstream of improvements in video modeling accuracy. The obvious implication was that advances in the video modeling frontier would directly translate to increased capabilities in end-to-end robot learning. FLUX-mimic is that thesis at frontier scale: We've applied our VAM architecture to the strongest video backbone available today, FLUX 3 from Black Forest Labs, and trained it on data from our own robots and wearables. General-purpose dexterity, running on a single GPU on premises. Because the model already understands world dynamics, it needs far fewer demonstrations to learn a new task. This is game-changing for our mission to deploy robots to factory floors, where industrial robot data is scarce and expensive to collect. We're now testing and deploying FLUX-mimic with manufacturing leaders like Audi USA, on complex, multi-step manipulation long considered impossible for conventional automation.

Introducing FLUX-mimic, a next-generation Video-Action Model for general purpose dexterity, developed in partnership with Black Forest Labs. Late last year we published mimic-video and introduced Video-Action Models (VAM): a new family of robotics foundation models built on top of video generation models. We showed that robot control reduces to visual prediction, and that robot capability is downstream of improvements in video modeling accuracy. The obvious implication was that advances in the video modeling frontier would directly translate to increased capabilities in end-to-end robot learning. FLUX-mimic is that thesis at frontier scale: We've applied our VAM architecture to the strongest video backbone available today, FLUX 3 from Black Forest Labs, and trained it on data from our own robots and wearables. General-purpose dexterity, running on a single GPU on premises. Because the model already understands world dynamics, it needs far fewer demonstrations to learn a new task. This is game-changing for our mission to deploy robots to factory floors, where industrial robot data is scarce and expensive to collect. We're now testing and deploying FLUX-mimic with manufacturing leaders like Audi USA, on complex, multi-step manipulation long considered impossible for conventional automation.

mimic

119,468 次观看 • 3 个月前

🤖 Physical AI is evolving weekly, but many models are trained on robots with limited payload capacity--restricting their real-world utility. 💪 To truly deploy AI in physical spaces, we need stronger hardware to unlock these models' full potential. Vega is capable of lifting 15+ lbs! 🚀 What applications will emerge when cutting-edge AI models meet Vega's physical capabilities? #PhysicalAI #EmbodiedAI #Robots #Automation #RealworldAI

🤖 Physical AI is evolving weekly, but many models are trained on robots with limited payload capacity--restricting their real-world utility. 💪 To truly deploy AI in physical spaces, we need stronger hardware to unlock these models' full potential. Vega is capable of lifting 15+ lbs! 🚀 What applications will emerge when cutting-edge AI models meet Vega's physical capabilities? #PhysicalAI #EmbodiedAI #Robots #Automation #RealworldAI

Dexmate

21,510 次观看 • 1 年前

Modern AI is confined to the digital world. At Skild AI, we are building towards AGI for the real world, unconstrained by robot type or task — a single, omni-bodied brain. Today, we are sharing our journey, starting with early milestones, with more to come in the weeks ahead. Our Mission: Artificial General Intelligence grounded in the physical world. We believe AGI that can truly understand and reason in the real world can only be built through grounding in the physical world. Our Vision: Any robot, Any task, One brain. We tackle robotics in its full generality – building a continually improving, omni-bodied brain that can control any hardware for any task. Who are we? A passionate group of scientists & engineers driven by our shared vision. We have been researching AI and robotics for more than a decade. Our team includes pioneers of self-supervised learning, curiosity-driven exploration, end-to-end sim2real for visual locomotion, dexterous manipulation, learning from human videos, robot parkour, and many more. Many of these works have won awards at top-tier AI and Robotics conferences. Our team has also built production-ready systems at Anduril, Tesla, Nvidia, Meta, Kitty Hawk, Google, Everyday Robotics, and Amazon. Join us in our mission to build the robot brains of tomorrow.

Modern AI is confined to the digital world. At Skild AI, we are building towards AGI for the real world, unconstrained by robot type or task — a single, omni-bodied brain. Today, we are sharing our journey, starting with early milestones, with more to come in the weeks ahead. Our Mission: Artificial General Intelligence grounded in the physical world. We believe AGI that can truly understand and reason in the real world can only be built through grounding in the physical world. Our Vision: Any robot, Any task, One brain. We tackle robotics in its full generality – building a continually improving, omni-bodied brain that can control any hardware for any task. Who are we? A passionate group of scientists & engineers driven by our shared vision. We have been researching AI and robotics for more than a decade. Our team includes pioneers of self-supervised learning, curiosity-driven exploration, end-to-end sim2real for visual locomotion, dexterous manipulation, learning from human videos, robot parkour, and many more. Many of these works have won awards at top-tier AI and Robotics conferences. Our team has also built production-ready systems at Anduril, Tesla, Nvidia, Meta, Kitty Hawk, Google, Everyday Robotics, and Amazon. Join us in our mission to build the robot brains of tomorrow.

Skild AI

386,992 次观看 • 1 年前

Today we’re launching Coco Robotics’ new Physical AI Lab led by Bolei Zhou, one of the world’s most cited AI researchers, and our new Chief AI Scientist. Our fleet faces unpredictable environments daily. That real world data is the key to advancing physical AI.

Today we’re launching Coco Robotics’ new Physical AI Lab led by Bolei Zhou, one of the world’s most cited AI researchers, and our new Chief AI Scientist. Our fleet faces unpredictable environments daily. That real world data is the key to advancing physical AI.

Zach Rash

142,768 次观看 • 1 年前

Robotics doesn't have a model problem. It has a data problem. And underneath that, a deployment problem. Physical AI progresses through real-world interaction. Robots act, fail, recover, and adapt. Without shared standards, every team relearns the same lessons in isolation. Deployment standards determine whether learning compounds or resets. PrismaX is the service layer for physical AI. We run the systems that define how robots get deployed, standardize how interaction data is generated, and integrate human judgment where models fall short, turning fragmented robotics capability into deployable infrastructure. Our Mission: Enable people and robots to work together by setting the standards that allow physical AI systems to learn and improve through real-world operation. Our Vision: A world where intelligent robots are deployed responsibly and at scale, supported by systems that embed human judgment into how intelligence advances. The next chapter for physical AI is about turning real-world operation into scalable intelligence. More soon.

Robotics doesn't have a model problem. It has a data problem. And underneath that, a deployment problem. Physical AI progresses through real-world interaction. Robots act, fail, recover, and adapt. Without shared standards, every team relearns the same lessons in isolation. Deployment standards determine whether learning compounds or resets. PrismaX is the service layer for physical AI. We run the systems that define how robots get deployed, standardize how interaction data is generated, and integrate human judgment where models fall short, turning fragmented robotics capability into deployable infrastructure. Our Mission: Enable people and robots to work together by setting the standards that allow physical AI systems to learn and improve through real-world operation. Our Vision: A world where intelligent robots are deployed responsibly and at scale, supported by systems that embed human judgment into how intelligence advances. The next chapter for physical AI is about turning real-world operation into scalable intelligence. More soon.

PrismaX

15,336 次观看 • 5 个月前

Physical AI is here—the next wave of AI and the foundation of the next industrial revolution. NVIDIA founder and CEO Jensen Huang outlines the full stack making it possible: Cosmos and Omniverse to develop physical AI in virtual worlds, Isaac and Newton where robots learn skills in physics-simulated gyms, and Jetson robotics computers where their intelligence runs. Together with Japan’s robotics and manufacturing leaders, NVIDIA is creating a new era of industrial automation.

Physical AI is here—the next wave of AI and the foundation of the next industrial revolution. NVIDIA founder and CEO Jensen Huang outlines the full stack making it possible: Cosmos and Omniverse to develop physical AI in virtual worlds, Isaac and Newton where robots learn skills in physics-simulated gyms, and Jetson robotics computers where their intelligence runs. Together with Japan’s robotics and manufacturing leaders, NVIDIA is creating a new era of industrial automation.

NVIDIA

135,264 次观看 • 2 个月前

Meet Gemini Robotics: our latest AI models designed for a new generation of helpful robots. 🤖 Based on Gemini 2.0, they bring capabilities such as better reasoning, interactivity, dexterity and generalization into the physical world. 🧵

Meet Gemini Robotics: our latest AI models designed for a new generation of helpful robots. 🤖 Based on Gemini 2.0, they bring capabilities such as better reasoning, interactivity, dexterity and generalization into the physical world. 🧵

Google DeepMind

644,037 次观看 • 1 年前

Touch: A Game-Changer in Dexterity for Robots You can’t be responsive to the world if you can’t feel it. That’s true for people—and it's just as true for robots. We’re zeroed in on a practical, yet innovative, approach to creating general purpose robots designed to perform physical work. And that means hands, powered not just by vision, but by touch. Vision alone falls short. There are many instances where our vision is obstructed while performing work tasks–like grabbing items out of a bin–you lose line of sight. You need tactile intelligence—texture, pressure, contact—with real-time feedback to move faster, smarter, and with confidence. Watch a full explainer video on Sanctuary AI’s latest touch sensors on our blog: #Robotics #AI #HumanoidRobots #Dexterity #TactileSensing #SanctuaryAI

Touch: A Game-Changer in Dexterity for Robots You can’t be responsive to the world if you can’t feel it. That’s true for people—and it's just as true for robots. We’re zeroed in on a practical, yet innovative, approach to creating general purpose robots designed to perform physical work. And that means hands, powered not just by vision, but by touch. Vision alone falls short. There are many instances where our vision is obstructed while performing work tasks–like grabbing items out of a bin–you lose line of sight. You need tactile intelligence—texture, pressure, contact—with real-time feedback to move faster, smarter, and with confidence. Watch a full explainer video on Sanctuary AI’s latest touch sensors on our blog: #Robotics #AI #HumanoidRobots #Dexterity #TactileSensing #SanctuaryAI

Sanctuary AI

53,293 次观看 • 1 年前

Today we’re thrilled to announce #SharpaWave — our first dexterous robotic hand — now officially in mass production and delivery! Robotic dexterity just took a leap forward. #Sharpa #Robotics #AI #DexterousHand #Robot #Humanoid #TactileSensing

Today we’re thrilled to announce #SharpaWave — our first dexterous robotic hand — now officially in mass production and delivery! Robotic dexterity just took a leap forward. #Sharpa #Robotics #AI #DexterousHand #Robot #Humanoid #TactileSensing

Sharpa

135,238 次观看 • 1 年前

Announcing Axol: a dual-arm robot designed for teams working with physical AI. Made in America. Axol is for builders who believe robots should work, in the real world, not just staged environments, and that the future of physical AI should be open, not closed. #robotics #automation #ai #hardware

Announcing Axol: a dual-arm robot designed for teams working with physical AI. Made in America. Axol is for builders who believe robots should work, in the real world, not just staged environments, and that the future of physical AI should be open, not closed. #robotics #automation #ai #hardware

Almond Robotics

64,774 次观看 • 4 个月前

Introducing: Phoenix™ Gen 7 Major improvements, all delivered in less than a year. Our next generation of general-purpose technology marks an inflection point in task automation velocity. “With Generation 7, we can capture increasing quantities of higher quality, higher fidelity human behavioral data, which in turn will expedite the development of foundational AI models and customer deployments,” says @realgeordierose, CEO and Co-founder at Sanctuary AI. Learn more: #EmbodiedAI #AI #PhoenixGen7 #SanctuaryAI

Introducing: Phoenix™ Gen 7 Major improvements, all delivered in less than a year. Our next generation of general-purpose technology marks an inflection point in task automation velocity. “With Generation 7, we can capture increasing quantities of higher quality, higher fidelity human behavioral data, which in turn will expedite the development of foundational AI models and customer deployments,” says @realgeordierose, CEO and Co-founder at Sanctuary AI. Learn more: #EmbodiedAI #AI #PhoenixGen7 #SanctuaryAI

Sanctuary AI

187,384 次观看 • 2 年前

For decades, we’ve dreamed of robots that can seamlessly step into our world and lend a hand. Today, we take a major stride toward making that dream a reality: Introducing Gemini Robotics 2 from Google DeepMind, the intelligence layer powering the next generation of truly adaptable robots. This major advance unlocks intelligent whole-body control, advanced dexterity, and even multi-robot collaboration 🤯. Ok but... how does a robot actually "think"? Real-world tasks take time and planning. To manage that complexity, our new embodied reasoning model, Gemini Robotics ER 2, acts as the robot’s high-level brain, enhancing the robot’s capabilities to: — Observe the environment — Reason about the actions needed to complete the task — Coordinate with the vision-language-action model to carry out actions — Track progress until the job is done This setup allows robots to execute complex multi-step workflows, self-correct if a step fails, and adapt to completely novel situations. Learn more about Gemini Robotics ER 2 (and our two other brand new models) here:

Google AI

789,272 次观看 • 2 个月前