Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Where can linearized dynamics be trusted w/contact? MIT's "Contact Trust Region" answers this using manipulation theory, differentiable simulation & control. It enables manipulation w/less compute than RL, powering robots to be more energy-efficient:

MIT CSAIL

343,222 subscribers

20,180 просмотров • 5 месяцев назад •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Robots Using Their Feet to Manipulate Objects ETH Zurich researchers have advanced "pedipulation," where legged robots use their feet for manipulation instead of robotic arms. Their new approach trains robots to navigate and manipulate objects while avoiding static and dynamic obstacles. Tested on the ANYmal quadruped, the method enables precise foot control in complex, unseen environments after minimal training in simulation. Will this research open up new possibilities for efficient, obstacle-aware robot manipulation?

Robots Using Their Feet to Manipulate Objects ETH Zurich researchers have advanced "pedipulation," where legged robots use their feet for manipulation instead of robotic arms. Their new approach trains robots to navigate and manipulate objects while avoiding static and dynamic obstacles. Tested on the ANYmal quadruped, the method enables precise foot control in complex, unseen environments after minimal training in simulation. Will this research open up new possibilities for efficient, obstacle-aware robot manipulation?

Circuit

11,802 просмотров • 1 год назад

The RWA tokenization market has hit $24B+ this year. To scale even more, it needs infrastructure that’s secure, scalable & trusted. That’s where Hedera comes in. The trust layer powering transparent, efficient tokenization.

The RWA tokenization market has hit $24B+ this year. To scale even more, it needs infrastructure that’s secure, scalable & trusted. That’s where Hedera comes in. The trust layer powering transparent, efficient tokenization.

Hedera

44,177 просмотров • 10 месяцев назад

📢📢📢 Excited to release ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning (CVPR25). 🤏🤙✌️With ManipTrans, we can transfer dexterous manipulation skills into robotic hands in simulation and deploy them on a real robot, using a residual policy learned for dex manipulation. 🤖🤖🤖The video below illustrates how the MoCap data can be transferred to Inspire, Shadow, Xhand, Allegro, and Mano. With ManipTrans, we can scale up dex manip data greatly with minimal effort. For more details, please check our -webpage: -code: -huggingface:

📢📢📢 Excited to release ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning (CVPR25). 🤏🤙✌️With ManipTrans, we can transfer dexterous manipulation skills into robotic hands in simulation and deploy them on a real robot, using a residual policy learned for dex manipulation. 🤖🤖🤖The video below illustrates how the MoCap data can be transferred to Inspire, Shadow, Xhand, Allegro, and Mano. With ManipTrans, we can scale up dex manip data greatly with minimal effort. For more details, please check our -webpage: -code: -huggingface:

Siyuan Huang

20,983 просмотров • 1 год назад

Unmanned mining truck from XCMG using HW tech operating in Northern China. Entirely automated & can change battery packs to continue to operate. Hard to be more efficient than this in mining.

Unmanned mining truck from XCMG using HW tech operating in Northern China. Entirely automated & can change battery packs to continue to operate. Hard to be more efficient than this in mining.

tphuang

15,059 просмотров • 11 месяцев назад

Robots need to be able to apply pressure and make contact with objects as needed in order to accomplish their tasks. From compliance to working safely around humans to whole-body manipulation of heavy objects, combining force and position control can dramatically expand the capabilities of robots. This is especially true for legged robots, which have so much ability to exert forces on the world around them. But how do we train robots which can do this? Baoxiong Jia tells us more in our discussion of his team’s recent, Best Paper Award winning work on learning a unified policy for position and force control, called UniFP. To learn more, watch Episode #49 of RoboPapers, hosted by Michael Cho - Rbt/Acc and Chris Paxton.

Robots need to be able to apply pressure and make contact with objects as needed in order to accomplish their tasks. From compliance to working safely around humans to whole-body manipulation of heavy objects, combining force and position control can dramatically expand the capabilities of robots. This is especially true for legged robots, which have so much ability to exert forces on the world around them. But how do we train robots which can do this? Baoxiong Jia tells us more in our discussion of his team’s recent, Best Paper Award winning work on learning a unified policy for position and force control, called UniFP. To learn more, watch Episode #49 of RoboPapers, hosted by Michael Cho - Rbt/Acc and Chris Paxton.

RoboPapers

44,813 просмотров • 8 месяцев назад

2nd Tea App breach?! 1 million messages w/ sensitive cheating stories, details of ending pregnancies, contact details, real names — it could not be more serious. Here are actions to protect yourself and what to do next. I’ll be on NBC News Now at 7 pm ET tomorrow discussing this.

2nd Tea App breach?! 1 million messages w/ sensitive cheating stories, details of ending pregnancies, contact details, real names — it could not be more serious. Here are actions to protect yourself and what to do next. I’ll be on NBC News Now at 7 pm ET tomorrow discussing this.

Rachel Tobac

41,174 просмотров • 1 год назад

Teaching robots to perform dexterous manipulation tasks currently requires teleoperation, which limits demonstration quality, speed, and scalability. Instead, why not use human videos? The problem is that a human hand isn’t a robot hand, so data must be retargeted using simulation to resolve issues like collisions and interpenetration when controlling the hand. In VideoManip, Hongyi Chen and co-authors built a system to solve this problem, taking in RGB videos of humans performing manipulation tasks and using them to create accurate simulations with which to learn robot policies. Watch episode #73 of RoboPapers, hosted by Michael Cho - Rbt/Acc and Chris Paxton, now to learn more!

Teaching robots to perform dexterous manipulation tasks currently requires teleoperation, which limits demonstration quality, speed, and scalability. Instead, why not use human videos? The problem is that a human hand isn’t a robot hand, so data must be retargeted using simulation to resolve issues like collisions and interpenetration when controlling the hand. In VideoManip, Hongyi Chen and co-authors built a system to solve this problem, taking in RGB videos of humans performing manipulation tasks and using them to create accurate simulations with which to learn robot policies. Watch episode #73 of RoboPapers, hosted by Michael Cho - Rbt/Acc and Chris Paxton, now to learn more!

RoboPapers

27,360 просмотров • 4 месяцев назад

Parasma Founder & CEO Sean Cole, who previously went viral for training human brain cells to play Doom, says that using them for compute could be far more energy-efficient than today's silicon chips. "Regardless of how efficient we make silicon, we still haven't solved the efficiency aspect of it, in terms of power efficiency." "I think human brains are extremely power efficient in comparison to silicon." "There are things that we can harness [with human brain cells] on top of other stuff like sample efficiency and continual learning."

Parasma Founder & CEO Sean Cole, who previously went viral for training human brain cells to play Doom, says that using them for compute could be far more energy-efficient than today's silicon chips. "Regardless of how efficient we make silicon, we still haven't solved the efficiency aspect of it, in terms of power efficiency." "I think human brains are extremely power efficient in comparison to silicon." "There are things that we can harness [with human brain cells] on top of other stuff like sample efficiency and continual learning."

TBPN

42,692 просмотров • 15 дней назад

Policies trained on real robot data via imitation can be surprisingly capable. But for domains like dexterous manipulation, they are often not quite good enough: they move slowly, miss grasps, make unreliable contact, and fail under small perturbations. Can we improve them without any additional data collection on the real robot? In SCORE, we show that we can improve real-world diffusion/flow policies cheaply by using simulation to simply learn how to steer them on deployment. This leads to large gains in real-world success and speed across a variety of tasks, without requiring additional real-world experience: 🧵 (1/10)

Policies trained on real robot data via imitation can be surprisingly capable. But for domains like dexterous manipulation, they are often not quite good enough: they move slowly, miss grasps, make unreliable contact, and fail under small perturbations. Can we improve them without any additional data collection on the real robot? In SCORE, we show that we can improve real-world diffusion/flow policies cheaply by using simulation to simply learn how to steer them on deployment. This leads to large gains in real-world success and speed across a variety of tasks, without requiring additional real-world experience: 🧵 (1/10)

Abhishek Gupta

34,775 просмотров • 1 месяц назад

How can clean energy be delivered directly to factories without going through the power grid?🔋 The answer: green power direct supply. This technology connects renewable energy sources like wind and solar power to industrial facilities through dedicated lines — generating power nearby and using it where it’s needed. From energy production to final consumption, every kilowatt-hour can be clearly tracked.📍 For energy-intensive industries, it means more than lower emissions. It brings cleaner electricity, less transmission loss, and a verifiable green pathway for sustainable operations.💡 CEEC is developing tailored green power direct supply solutions for businesses worldwide. Simple, transparent, and traceable — this is how we are powering a greener future. Watch the video to see how green power goes “straight to the factory” and drives real change for industry.♻️ #EnergyTransition #CleanEnergy #Innovation

How can clean energy be delivered directly to factories without going through the power grid?🔋 The answer: green power direct supply. This technology connects renewable energy sources like wind and solar power to industrial facilities through dedicated lines — generating power nearby and using it where it’s needed. From energy production to final consumption, every kilowatt-hour can be clearly tracked.📍 For energy-intensive industries, it means more than lower emissions. It brings cleaner electricity, less transmission loss, and a verifiable green pathway for sustainable operations.💡 CEEC is developing tailored green power direct supply solutions for businesses worldwide. Simple, transparent, and traceable — this is how we are powering a greener future. Watch the video to see how green power goes “straight to the factory” and drives real change for industry.♻️ #EnergyTransition #CleanEnergy #Innovation

Energy China

31,941 просмотров • 2 месяцев назад

I’m entering a new season, and I need to be crystal clear. There is no need to contact me asking for connections, introductions, or access to RFK. The answer is no, respectfully, but firmly. I’m staying in my own lane and pouring all of my energy into the mission God placed on my heart: Auntie Angie’s House, maternal health, and protecting our mothers and babies. This season is about alignment, not attachment. Purpose, not politics. Mission, not manipulation. I’m avoiding grifts, frauds, distractions, and anything that pulls me away from what truly matters. My trust is in God and in the work He called me to do nothing more, nothing less. If you support me, support this mission. That’s where my focus is. That’s where my heart is. And that’s where I’m staying.

I’m entering a new season, and I need to be crystal clear. There is no need to contact me asking for connections, introductions, or access to RFK. The answer is no, respectfully, but firmly. I’m staying in my own lane and pouring all of my energy into the mission God placed on my heart: Auntie Angie’s House, maternal health, and protecting our mothers and babies. This season is about alignment, not attachment. Purpose, not politics. Mission, not manipulation. I’m avoiding grifts, frauds, distractions, and anything that pulls me away from what truly matters. My trust is in God and in the work He called me to do nothing more, nothing less. If you support me, support this mission. That’s where my focus is. That’s where my heart is. And that’s where I’m staying.

Angela Stanton King

38,440 просмотров • 8 месяцев назад

This powerful device is more or less the size of a smartphone. It can power a house, and do much more than that. This has been available for decades. They've been hiding this, and other Free Energy inventions, because they want you to be dependent on their parasitic system.

This powerful device is more or less the size of a smartphone. It can power a house, and do much more than that. This has been available for decades. They've been hiding this, and other Free Energy inventions, because they want you to be dependent on their parasitic system.

Antonello Bacchetti

16,586 просмотров • 3 месяцев назад

We are excited to share our latest work, "Learning on the Fly: Rapid Policy Adaptation via Differentiable Simulation", where a policy learns to adapt in the real world to unknown disturbances within 5 seconds, both with and without explicit state estimation, directly from visual features. Code released! PDF: Project Page: Starting from a simple analytical dynamics model, the system continuously learns residual dynamics from real-world data and embeds the refined model into a differentiable simulator. This enables fast, gradient-based policy updates that are far more sample-efficient than classical #ReinforcementLearning. We demonstrate rapid adaptation in <5 seconds in agile quadrotor control under challenging conditions, including added payloads, wind disturbances, and large sim-to-real gaps. In real-world experiments, our method reduces hovering error by up to 81% compared to L1-MPC and 55% compared to PPO-based adaptive methods. It also operates directly from visual features without explicit state estimation. Reference: “Learning on the Fly: Rapid Policy Adaptation via Differentiable Simulation” IEEE Robotics and Automation Letters, 2026 PDF: Video: Code: Website: Kudos to Michael Pan, Jiaxu Xing, Rudolf Reiter, Yifan Zhai, Elie Aljalbout! UZH Space Hub UZH IfI European Research Council (ERC) AUTOASSESS UZH Science University of Zurich

We are excited to share our latest work, "Learning on the Fly: Rapid Policy Adaptation via Differentiable Simulation", where a policy learns to adapt in the real world to unknown disturbances within 5 seconds, both with and without explicit state estimation, directly from visual features. Code released! PDF: Project Page: Starting from a simple analytical dynamics model, the system continuously learns residual dynamics from real-world data and embeds the refined model into a differentiable simulator. This enables fast, gradient-based policy updates that are far more sample-efficient than classical #ReinforcementLearning. We demonstrate rapid adaptation in <5 seconds in agile quadrotor control under challenging conditions, including added payloads, wind disturbances, and large sim-to-real gaps. In real-world experiments, our method reduces hovering error by up to 81% compared to L1-MPC and 55% compared to PPO-based adaptive methods. It also operates directly from visual features without explicit state estimation. Reference: “Learning on the Fly: Rapid Policy Adaptation via Differentiable Simulation” IEEE Robotics and Automation Letters, 2026 PDF: Video: Code: Website: Kudos to Michael Pan, Jiaxu Xing, Rudolf Reiter, Yifan Zhai, Elie Aljalbout! UZH Space Hub UZH IfI European Research Council (ERC) AUTOASSESS UZH Science University of Zurich

Davide Scaramuzza

19,184 просмотров • 7 месяцев назад

Robots might learn better from video than from language! 📼 Most Vision-Language-Action (VLA) models learn what to do from text, but still struggle with how things move in the real world. That makes them data-hungry and slow to train. mimic video takes a different route. Instead of grounding robot control in text, it grounds it in video, using large pre-trained video models that already capture physical motion and dynamics. The idea is straightforward: let the video model handle “what will happen next,” and let a smaller control model focus only on turning that visual plan into robot actions. The result is big gains in practice. Robots trained this way need 10× less data, converge twice as fast, and perform better on both simulated benchmarks and real bimanual manipulation tasks. If robots can “imagine” motion using video, control becomes a much simpler problem. Shoutout to Jonas Pai, Liam Achenbach, Oier Mees, Elvis Nava and the rest of the team! Here's the project page: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Robots might learn better from video than from language! 📼 Most Vision-Language-Action (VLA) models learn what to do from text, but still struggle with how things move in the real world. That makes them data-hungry and slow to train. mimic video takes a different route. Instead of grounding robot control in text, it grounds it in video, using large pre-trained video models that already capture physical motion and dynamics. The idea is straightforward: let the video model handle “what will happen next,” and let a smaller control model focus only on turning that visual plan into robot actions. The result is big gains in practice. Robots trained this way need 10× less data, converge twice as fast, and perform better on both simulated benchmarks and real bimanual manipulation tasks. If robots can “imagine” motion using video, control becomes a much simpler problem. Shoutout to Jonas Pai, Liam Achenbach, Oier Mees, Elvis Nava and the rest of the team! Here's the project page: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

50,090 просмотров • 8 месяцев назад

“not everyone can be special so dont be too obsessed w becoming someone great. just find whats valuable to u in your life,that's more than enough” got me in tears this is the kind of convo every sibling should've & this is the ted talk he needed fr #LoveNextDoor #LoveNextDoorEp13

“not everyone can be special so dont be too obsessed w becoming someone great. just find whats valuable to u in your life,that's more than enough” got me in tears this is the kind of convo every sibling should've & this is the ted talk he needed fr #LoveNextDoor #LoveNextDoorEp13

🎧

109,362 просмотров • 1 год назад

I think about this a lot. I think most people would look at this & mourn how things have changed but for me it's more of a challenge to see where this is already a reality & where it can be a vision for the future. there are so many stays who I love & trust. we're pretty amazing

I think about this a lot. I think most people would look at this & mourn how things have changed but for me it's more of a challenge to see where this is already a reality & where it can be a vision for the future. there are so many stays who I love & trust. we're pretty amazing

🌙 gigi bang

26,275 просмотров • 1 год назад

Cursor CEO Michael Truell: Programming in the future might not mean programming with an AI helper, but in a new language entirely. "There is a future version of the world where the way you interact with AI is a little bit less like it's a human helper that you're delegating work to... and instead, it's a little bit more of an advance in compiler or interpreter technology." "It can lead you to a world where programming languages actually change. They can start to be a little bit more about what you want and a little bit less about how you do it." "There is a world where direct manipulation of the UI starts to play a little bit more into it." Michael Truell with Patrick Collison

Cursor CEO Michael Truell: Programming in the future might not mean programming with an AI helper, but in a new language entirely. "There is a future version of the world where the way you interact with AI is a little bit less like it's a human helper that you're delegating work to... and instead, it's a little bit more of an advance in compiler or interpreter technology." "It can lead you to a world where programming languages actually change. They can start to be a little bit more about what you want and a little bit less about how you do it." "There is a world where direct manipulation of the UI starts to play a little bit more into it." Michael Truell with Patrick Collison

a16z

92,602 просмотров • 6 месяцев назад