Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

How do we make dexterous hands handle both power and precision tasks with ease? 🫳👌🫰 We introduce Power to Precision (💪➡️🎯), our new paper that optimizes both control and fingertip geometry to unlock robust manipulation from power grasp to fine-grained manipulations. With simplified finger motions and augmented fingertips, the... show more

Jianglong Ye

1,017 subscribers

110,220 views • 9 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

How to learn dexterous manipulation for any robot hand from a single human demonstration? Check out DexMachina, our new RL algorithm that learns long-horizon, bimanual dexterous policies for a variety of dexterous hands, articulated objects, and complex motions.

How to learn dexterous manipulation for any robot hand from a single human demonstration? Check out DexMachina, our new RL algorithm that learns long-horizon, bimanual dexterous policies for a variety of dexterous hands, articulated objects, and complex motions.

Mandi Zhao

121,265 views • 1 year ago

Researchers from RAI Institute present Diffuse-CLoC, a new control policy that fuses kinematic motion diffusion models with physics-based control to produce motions that are both physically realistic and precisely controllable. This breakthrough moves us closer to developing generalist policies that enable humanoid robots to perform diverse tasks, including dynamic locomotion and contact-rich manipulation, in a natural-looking and robust way. Learn more at

Researchers from RAI Institute present Diffuse-CLoC, a new control policy that fuses kinematic motion diffusion models with physics-based control to produce motions that are both physically realistic and precisely controllable. This breakthrough moves us closer to developing generalist policies that enable humanoid robots to perform diverse tasks, including dynamic locomotion and contact-rich manipulation, in a natural-looking and robust way. Learn more at

RAI Institute

13,536 views • 1 year ago

Synchronize Dual Hands for Physics-Based Dexterous Guitar Playing discuss: We present a novel approach to synthesize dexterous motions for physically simulated hands in tasks that require coordination between the control of two hands with high temporal precision. Instead of directly learning a joint policy to control two hands, our approach performs bimanual control through cooperative learning where each hand is treated as an individual agent. The individual policies for each hand are first trained separately, and then synchronized through latent space manipulation in a centralized environment to serve as a joint policy for two-hand control. By doing so, we avoid directly performing policy learning in the joint state-action space of two hands with higher dimensions, greatly improving the overall training efficiency. We demonstrate the effectiveness of our proposed approach in the challenging guitar-playing task. The virtual guitarist trained by our approach can synthesize motions from unstructured reference data of general guitar-playing practice motions, and accurately play diverse rhythms with complex chord pressing and string picking patterns based on the input guitar tabs that do not exist in the references. Along with this paper, we provide the motion capture data that we collected as the reference for policy training.

Synchronize Dual Hands for Physics-Based Dexterous Guitar Playing discuss: We present a novel approach to synthesize dexterous motions for physically simulated hands in tasks that require coordination between the control of two hands with high temporal precision. Instead of directly learning a joint policy to control two hands, our approach performs bimanual control through cooperative learning where each hand is treated as an individual agent. The individual policies for each hand are first trained separately, and then synchronized through latent space manipulation in a centralized environment to serve as a joint policy for two-hand control. By doing so, we avoid directly performing policy learning in the joint state-action space of two hands with higher dimensions, greatly improving the overall training efficiency. We demonstrate the effectiveness of our proposed approach in the challenging guitar-playing task. The virtual guitarist trained by our approach can synthesize motions from unstructured reference data of general guitar-playing practice motions, and accurately play diverse rhythms with complex chord pressing and string picking patterns based on the input guitar tabs that do not exist in the references. Along with this paper, we provide the motion capture data that we collected as the reference for policy training.

AK

26,855 views • 1 year ago

A dexterous hand capable of operating an iPhone Impressive, with nimble fingertip control. INSPIRE ROBOTS from Beijing has released a new dexterous hand featuring tactile and force sensing, and equipped with a motion library, making it ready to use right out of the box. Especially noteworthy is the modular finger design, allowing users to easily replace a damaged finger. With 13 degrees of freedom and a single-hand load capacity of 30kg, it can be used in general applications such as factory component handling, precision assembly, and warehouse logistics sorting. Notably, this company has already sold over 10,000 of these dexterous hands.

A dexterous hand capable of operating an iPhone Impressive, with nimble fingertip control. INSPIRE ROBOTS from Beijing has released a new dexterous hand featuring tactile and force sensing, and equipped with a motion library, making it ready to use right out of the box. Especially noteworthy is the modular finger design, allowing users to easily replace a damaged finger. With 13 degrees of freedom and a single-hand load capacity of 30kg, it can be used in general applications such as factory component handling, precision assembly, and warehouse logistics sorting. Notably, this company has already sold over 10,000 of these dexterous hands.

CyberRobo

14,196 views • 7 months ago

Hands are as important as the brain. From Shenzhen, Stella Robot has unveiled the PANTHEON HAND 22:a new generation of bionic dexterous hand that combines 22 degrees of freedom with remarkable strength and finesse. It’s a hand that truly understands precision. It can lift 30 kilograms, yet is delicate enough to thread a needle.Each finger can bear 1.5 kilograms, and the entire hand can gently hold a piece of tofu or sense the subtle expansion of a balloon. Powered by a tendon-driven mechanism with integrated actuators inside the forearm, it achieves compact design and natural, human-like movement. From precision assembly and component handling to material transport and human-robot collaboration,the PANTHEON HAND 22 shows what it means for humanoid robots to truly work with their hands.

Hands are as important as the brain. From Shenzhen, Stella Robot has unveiled the PANTHEON HAND 22:a new generation of bionic dexterous hand that combines 22 degrees of freedom with remarkable strength and finesse. It’s a hand that truly understands precision. It can lift 30 kilograms, yet is delicate enough to thread a needle.Each finger can bear 1.5 kilograms, and the entire hand can gently hold a piece of tofu or sense the subtle expansion of a balloon. Powered by a tendon-driven mechanism with integrated actuators inside the forearm, it achieves compact design and natural, human-like movement. From precision assembly and component handling to material transport and human-robot collaboration,the PANTHEON HAND 22 shows what it means for humanoid robots to truly work with their hands.

CyberRobo

26,867 views • 10 months ago

🤖 What if a humanoid robot could make a hamburger from raw ingredients—all the way to your plate? 🔥 Excited to announce ViTacFormer: our new pipeline for next-level dexterous manipulation with active vision + high-resolution touch. 🎯 For the first time ever, we demonstrate ~2.5 minutes of continuous, autonomous control—combining active vision, high-res touch, and high-DoF robot hands SharpaWave — to complete complex, real-world tasks. Code is fully released; check out our: Homepage: Paper link: Github:

🤖 What if a humanoid robot could make a hamburger from raw ingredients—all the way to your plate? 🔥 Excited to announce ViTacFormer: our new pipeline for next-level dexterous manipulation with active vision + high-resolution touch. 🎯 For the first time ever, we demonstrate ~2.5 minutes of continuous, autonomous control—combining active vision, high-res touch, and high-DoF robot hands SharpaWave — to complete complex, real-world tasks. Code is fully released; check out our: Homepage: Paper link: Github:

Haoran Geng

95,651 views • 1 year ago

If the end goal of robot hands is to perform human motion, then we should optimize the hardware design with human motion - and on a large scale! We can generate both a high-dof generalist hand, and also low-dof specialized hands from human demonstration.

If the end goal of robot hands is to perform human motion, then we should optimize the hardware design with human motion - and on a large scale! We can generate both a high-dof generalist hand, and also low-dof specialized hands from human demonstration.

yisha

36,984 views • 2 months ago

Unlock the power of your mind and take control of your life with the Freedom of Mind podcast. Join me, Dr. Steven Hassan, and my guests as we explore the world of cults, undue influence, and how to protect yourself from manipulation. Tune in now!

Unlock the power of your mind and take control of your life with the Freedom of Mind podcast. Join me, Dr. Steven Hassan, and my guests as we explore the world of cults, undue influence, and how to protect yourself from manipulation. Tune in now!

Steven Hassan, PhD

115,486 views • 3 years ago

Who actually runs our government? In this clip we have a heated debate over power, influence and decision making. Is it elected officials working for the people or do corporations and hidden interests have the real control? From policies and funding to behind the scenes influence, both sides bring arguments that challenge how we see leadership and authority

Who actually runs our government? In this clip we have a heated debate over power, influence and decision making. Is it elected officials working for the people or do corporations and hidden interests have the real control? From policies and funding to behind the scenes influence, both sides bring arguments that challenge how we see leadership and authority

Charlie Kirk Forever

16,994 views • 3 months ago

Can robotic hands really outperform human dexterity? Meet the Linker Hand L30 from LinkerBot. This tendon-driven dexterous hand packs high precision and compact size, making it a serious contender for complex manipulation tasks: ► 22 Degrees of Freedom utilizing a sophisticated tendon drive system. ► Ultra-fine positioning control with ±0.20mm repeatable accuracy. ► Rapid response speed, achieving up to 450°/S for core movements. ► Adaptive grasping enabled by high-sensitivity tactile sensors built into the fingertips. ► Compact dimensions (85mm average width, 179mm length) despite its complex architecture.

Can robotic hands really outperform human dexterity? Meet the Linker Hand L30 from LinkerBot. This tendon-driven dexterous hand packs high precision and compact size, making it a serious contender for complex manipulation tasks: ► 22 Degrees of Freedom utilizing a sophisticated tendon drive system. ► Ultra-fine positioning control with ±0.20mm repeatable accuracy. ► Rapid response speed, achieving up to 450°/S for core movements. ► Adaptive grasping enabled by high-sensitivity tactile sensors built into the fingertips. ► Compact dimensions (85mm average width, 179mm length) despite its complex architecture.

RoboHub🤖

22,556 views • 10 months ago

If you’re not doing this, you’re losing power and stability in your swing. After a controlled load into the back hip, we have to be ready to unleash that stored energy into the ball. The only way to do this with both force and stability is by hitting against a strong front side — more specifically, our front heel. When we drive the front heel properly into the ground, it allows us to maximize both force and stability, enabling our mechanics to function correctly and generate gap-to-gap power! #softball #hitting #lesson

If you’re not doing this, you’re losing power and stability in your swing. After a controlled load into the back hip, we have to be ready to unleash that stored energy into the ball. The only way to do this with both force and stability is by hitting against a strong front side — more specifically, our front heel. When we drive the front heel properly into the ground, it allows us to maximize both force and stability, enabling our mechanics to function correctly and generate gap-to-gap power! #softball #hitting #lesson

CamWood Bats

55,697 views • 1 year ago

Republicans snuck a provision into their budget bill that will make it harder for courts to hold the Trump administration — and any future administration — accountable. This is intentional. They want to continue to amass and abuse their power without checks and balances. It’s also a dangerous transfer of power from both branches to the executive. We must stop this in the Senate.

Republicans snuck a provision into their budget bill that will make it harder for courts to hold the Trump administration — and any future administration — accountable. This is intentional. They want to continue to amass and abuse their power without checks and balances. It’s also a dangerous transfer of power from both branches to the executive. We must stop this in the Senate.

Rep. Morgan McGarvey

10,458 views • 1 year ago

Finished a meeting with military leaders, the Government, and the Office, summarizing the visit to the United States. Our teams – both Ukrainian and American – are already working on everything we discussed in New York and Washington, and we are now preparing for the upcoming ‘Ramstein’ meeting. This time it will be a special meeting, and from our side, our partners will receive all the details and arguments on how to secure results in the coming months – both on the frontlines and through diplomatic efforts. The power of weapons and the power of diplomacy are always most effective when they work together, and that’s exactly how we plan to implement our Victory Plan. We also expect concrete steps from our partners to strengthen our strategy. This applies to all of them – our strength lies in the fact that the free world is defending itself.

Finished a meeting with military leaders, the Government, and the Office, summarizing the visit to the United States. Our teams – both Ukrainian and American – are already working on everything we discussed in New York and Washington, and we are now preparing for the upcoming ‘Ramstein’ meeting. This time it will be a special meeting, and from our side, our partners will receive all the details and arguments on how to secure results in the coming months – both on the frontlines and through diplomatic efforts. The power of weapons and the power of diplomacy are always most effective when they work together, and that’s exactly how we plan to implement our Victory Plan. We also expect concrete steps from our partners to strengthen our strategy. This applies to all of them – our strength lies in the fact that the free world is defending itself.

Volodymyr Zelenskyy / Володимир Зеленський

343,261 views • 1 year ago

📢📢📢 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

20,975 views • 1 year ago

Can vision-language-action (VLA) models generalize to diverse OOD tasks and align with customized objectives? 🤔 🚀 We introduce GRAPE, a plug-and-play algorithm to generalize robot policies via preference alignment. GRAPE unfolds three benefits to boost the generalizability of VLAs: 👉1. GRAPE aligns VLAs on a trajectory level and endows the model with the ability for global decision-making, instead of merely cloning behavior; 👉2. GRAPE implicitly models reward from both successful and failed trials to boost generalizability to diverse tasks; 👉3. GRAPE adopts a scalable preference synthesis algorithm to rank trajectories with preferences that align with arbitrary objectives. Our experiments on a diverse array of real-world and simulated robotic tasks reveal: 1⃣GRAPE enhances the performance of state-of-the-art VLA models, increasing success rates on in-domain and unseen manipulation tasks by 51.79% and 60.36%; 2⃣GRAPE is versatile to be aligned with diverse objectives and reduce collision rates by 44.31% or rollout length by 11.15% when aligning towards safer or more efficient manipulation policy, respectively. Check out our full project for more details: 🔥 Paper: 🔥 Project: 🔥 Code:

Can vision-language-action (VLA) models generalize to diverse OOD tasks and align with customized objectives? 🤔 🚀 We introduce GRAPE, a plug-and-play algorithm to generalize robot policies via preference alignment. GRAPE unfolds three benefits to boost the generalizability of VLAs: 👉1. GRAPE aligns VLAs on a trajectory level and endows the model with the ability for global decision-making, instead of merely cloning behavior; 👉2. GRAPE implicitly models reward from both successful and failed trials to boost generalizability to diverse tasks; 👉3. GRAPE adopts a scalable preference synthesis algorithm to rank trajectories with preferences that align with arbitrary objectives. Our experiments on a diverse array of real-world and simulated robotic tasks reveal: 1⃣GRAPE enhances the performance of state-of-the-art VLA models, increasing success rates on in-domain and unseen manipulation tasks by 51.79% and 60.36%; 2⃣GRAPE is versatile to be aligned with diverse objectives and reduce collision rates by 44.31% or rollout length by 11.15% when aligning towards safer or more efficient manipulation policy, respectively. Check out our full project for more details: 🔥 Paper: 🔥 Project: 🔥 Code:

Huaxiu Yao

19,988 views • 1 year ago

Today, Adobe and NVIDIA announced a strategic partnership to reinvent creative and marketing workflows with the power of AI. Adobe’s creative and marketing technology, combined with NVIDIA’s research and accelerated computing, will come together to develop next-generation Firefly models and creative, marketing, and agentic workflows to deliver best-in-class creative precision and control. Check out the full announcement from #NVIDIAGTC to see what’s ahead:

Today, Adobe and NVIDIA announced a strategic partnership to reinvent creative and marketing workflows with the power of AI. Adobe’s creative and marketing technology, combined with NVIDIA’s research and accelerated computing, will come together to develop next-generation Firefly models and creative, marketing, and agentic workflows to deliver best-in-class creative precision and control. Check out the full announcement from #NVIDIAGTC to see what’s ahead:

Adobe

997,190 views • 5 months ago