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。

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... show more

Ruihan Yang

2,493 subscribers

58,712 次观看 • 11 个月前 •via X (Twitter)

科学技术教育

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

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 • 6 个月前

How can we more effectively leverage robot data from different embodiments for skill transfer? Excited to share that our new work, RoVi-Aug, has been accepted to Conference on Robot Learning as an oral paper！ WIth RoVi-Aug, you can augment an existing robot dataset into a different robot and different viewpoints. A policy trained on the augmented dataset can zero-shot deploy on the unseen target robot with significantly different camera angles! 🧵👇 🔗 Check out our paper:

How can we more effectively leverage robot data from different embodiments for skill transfer? Excited to share that our new work, RoVi-Aug, has been accepted to Conference on Robot Learning as an oral paper！ WIth RoVi-Aug, you can augment an existing robot dataset into a different robot and different viewpoints. A policy trained on the augmented dataset can zero-shot deploy on the unseen target robot with significantly different camera angles! 🧵👇 🔗 Check out our paper:

Chenfeng_X

28,288 次观看 • 1 年前

Controlling a CM6 robot with a LEAP motion controller. J2 of the robot is a bit underpowered but we mainly tested our algorithm here that we will implement on our other robots. Data is shared at 125Hz between robot and Leap over local network.

Controlling a CM6 robot with a LEAP motion controller. J2 of the robot is a bit underpowered but we mainly tested our algorithm here that we will implement on our other robots. Data is shared at 125Hz between robot and Leap over local network.

SourceRobotics

14,433 次观看 • 1 年前

How can a visuomotor policy learn from internet videos? We introduce Dreamitate, where a robot uses a fine-tuned video diffusion model to dream the future (top) and imitate the dream to accomplish a task (bottom). website: paper:

How can a visuomotor policy learn from internet videos? We introduce Dreamitate, where a robot uses a fine-tuned video diffusion model to dream the future (top) and imitate the dream to accomplish a task (bottom). website: paper:

Ruoshi Liu

50,797 次观看 • 2 年前

𝗥𝗼𝗯𝗼𝘁𝘀 𝗱𝗼𝗻’𝘁 𝗻𝗲𝗲𝗱 𝗺𝗼𝗿𝗲 𝗱𝗲𝗺𝗼𝗻𝘀𝘁𝗿𝗮𝘁𝗶𝗼𝗻𝘀. 𝗧𝗵𝗲𝘆 𝗻𝗲𝗲𝗱 𝘁𝗼 𝗹𝗲𝗮𝗿𝗻 𝗳𝗿𝗼𝗺 𝗳𝗮𝗶𝗹𝘂𝗿𝗲 — 𝗮𝗳𝘁𝗲𝗿 𝘄𝗮𝘁𝗰𝗵𝗶𝗻𝗴 𝗵𝘂𝗺𝗮𝗻𝘀. Most robot learning systems assume failure is the end of learning. In our new work, we study whether robots can improve after deployment by learning from their own failures, without any human intervention, teleoperation, or corrective labels. The key idea is simple: human videos contain structure about how the world works. We use them to learn cross-embodiment representations of action, dynamics, and value, enabling a shared predictive space between human behavior and robot experience. This allows a new learning loop: 👉 pretrain on human videos 👉 deploy robot policy 👉 observe failures 👉 reinterpret failures using human priors 👉 improve autonomously We evaluate this across 7 real-world manipulation tasks, showing: 📈 40% → 81% success rate 🏆 Strong improvements over π0.6 RECAP and RISE ✔️ Zero human intervention during post-deployment improvement 🧬 Generalizes across robot embodiments and policy backbones A key finding is that explicit failure repair significantly outperforms failure reweighting, yielding substantially larger gains under identical data conditions (+25 pts vs +5 pts on the same π0.5 base policy). Overall, the results suggest a shift in how we think about robot learning: Human videos are not only for pretraining policies. They can provide the structure needed for continual self-improvement after deployment. 📄 Paper: 🌐 Project: I am grateful for working with the fantastic leads Hanzhi Chen and Anran Zhang, and our collaborators Simon Schaefer, Kejia Chen, Shi Chen, Daniel Cremers. Special thanks to Stefan Leutenegger for co-advising this project with me. ETH Zürich TU München Microsoft Check out Hanzhi's 🧵 for more details

𝗥𝗼𝗯𝗼𝘁𝘀 𝗱𝗼𝗻’𝘁 𝗻𝗲𝗲𝗱 𝗺𝗼𝗿𝗲 𝗱𝗲𝗺𝗼𝗻𝘀𝘁𝗿𝗮𝘁𝗶𝗼𝗻𝘀. 𝗧𝗵𝗲𝘆 𝗻𝗲𝗲𝗱 𝘁𝗼 𝗹𝗲𝗮𝗿𝗻 𝗳𝗿𝗼𝗺 𝗳𝗮𝗶𝗹𝘂𝗿𝗲 — 𝗮𝗳𝘁𝗲𝗿 𝘄𝗮𝘁𝗰𝗵𝗶𝗻𝗴 𝗵𝘂𝗺𝗮𝗻𝘀. Most robot learning systems assume failure is the end of learning. In our new work, we study whether robots can improve after deployment by learning from their own failures, without any human intervention, teleoperation, or corrective labels. The key idea is simple: human videos contain structure about how the world works. We use them to learn cross-embodiment representations of action, dynamics, and value, enabling a shared predictive space between human behavior and robot experience. This allows a new learning loop: 👉 pretrain on human videos 👉 deploy robot policy 👉 observe failures 👉 reinterpret failures using human priors 👉 improve autonomously We evaluate this across 7 real-world manipulation tasks, showing: 📈 40% → 81% success rate 🏆 Strong improvements over π0.6 RECAP and RISE ✔️ Zero human intervention during post-deployment improvement 🧬 Generalizes across robot embodiments and policy backbones A key finding is that explicit failure repair significantly outperforms failure reweighting, yielding substantially larger gains under identical data conditions (+25 pts vs +5 pts on the same π0.5 base policy). Overall, the results suggest a shift in how we think about robot learning: Human videos are not only for pretraining policies. They can provide the structure needed for continual self-improvement after deployment. 📄 Paper: 🌐 Project: I am grateful for working with the fantastic leads Hanzhi Chen and Anran Zhang, and our collaborators Simon Schaefer, Kejia Chen, Shi Chen, Daniel Cremers. Special thanks to Stefan Leutenegger for co-advising this project with me. ETH Zürich TU München Microsoft Check out Hanzhi's 🧵 for more details

Oier Mees

11,985 次观看 • 16 天前

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

31,873 次观看 • 25 天前

Evaluating policies on a real robot can be painful. Can we use a world model to get a rough estimate of how good a policy is? Checkout "Evaluating Robot Policies in a World Model". Paper: Demo: Code:

Evaluating policies on a real robot can be painful. Can we use a world model to get a rough estimate of how good a policy is? Checkout "Evaluating Robot Policies in a World Model". Paper: Demo: Code:

Sherry Yang

36,568 次观看 • 1 年前

RGB Human Videos -> Dexterous Manipulation Policies No teleoperation. No wearables. No robot interaction. The 🔑: Reliable 3D hand-object trajectory reconstruction and efficient action augmentation Fun collaboration led by Hongyi Chen

RGB Human Videos -> Dexterous Manipulation Policies No teleoperation. No wearables. No robot interaction. The 🔑: Reliable 3D hand-object trajectory reconstruction and efficient action augmentation Fun collaboration led by Hongyi Chen

Homanga Bharadhwaj

10,797 次观看 • 4 个月前

Learning bimanual, contact-rich robot manipulation policies that generalize over diverse objects has long been a challenge. Excited to share our work: Planning-Guided Diffusion Policy Learning for Generalizable Contact-Rich Bimanual Manipulation! 🧵1/n

Learning bimanual, contact-rich robot manipulation policies that generalize over diverse objects has long been a challenge. Excited to share our work: Planning-Guided Diffusion Policy Learning for Generalizable Contact-Rich Bimanual Manipulation! 🧵1/n

Xuanlin Li (Simon)

20,911 次观看 • 1 年前

we open sourced the code to transform human videos into robot trajectories, so you can train robots with your hands 👐🏻 we used it in our recent paper R+X: Retrieval and Execution from Everyday Human Videos (ICRA 2025 🇺🇸) link and details in thread 🧵

we open sourced the code to transform human videos into robot trajectories, so you can train robots with your hands 👐🏻 we used it in our recent paper R+X: Retrieval and Execution from Everyday Human Videos (ICRA 2025 🇺🇸) link and details in thread 🧵

Norman Di Palo

10,578 次观看 • 1 年前

🇺🇸🇨🇳 China will host a human vs. robot marathon on April 19. How do these robots compare to Tesla Optimus 🤔 Who would win in a ROBOT race?

🇺🇸🇨🇳 China will host a human vs. robot marathon on April 19. How do these robots compare to Tesla Optimus 🤔 Who would win in a ROBOT race?

Donald J Trump Posts TruthSocial

46,422 次观看 • 2 个月前

The world’s first street argument between a human and a robot reportedly ended with police stepping in and taking the robot away

The world’s first street argument between a human and a robot reportedly ended with police stepping in and taking the robot away

Massimo

17,798 次观看 • 4 个月前

MolmoAct2 is landing in LeRobot! Ai2's open Action Reasoning Model combines a Molmo2-ER vision-language backbone with a flow-matching continuous action expert to predict robot action chunks from images, language instructions, and proprioceptive state. An open robot foundation model built for real-world control, with strong out-of-the-box performance and easy fine-tuning in LeRobot. Pick-and-place inference running on NVIDIA DGX Spark! Blog: Paper: Thanks to Ai2 Jiafei Duan Haoquan Fang

MolmoAct2 is landing in LeRobot! Ai2's open Action Reasoning Model combines a Molmo2-ER vision-language backbone with a flow-matching continuous action expert to predict robot action chunks from images, language instructions, and proprioceptive state. An open robot foundation model built for real-world control, with strong out-of-the-box performance and easy fine-tuning in LeRobot. Pick-and-place inference running on NVIDIA DGX Spark! Blog: Paper: Thanks to Ai2 Jiafei Duan Haoquan Fang

LeRobot

24,727 次观看 • 1 个月前

Can we make Transformers better and more efficient for robot learning? Excited to introduce Body Transformer (BoT), an architecture that leverages robot embodiment in the attention mechanism, by treating it as a graph of sensors and actuators.

Can we make Transformers better and more efficient for robot learning? Excited to introduce Body Transformer (BoT), an architecture that leverages robot embodiment in the attention mechanism, by treating it as a graph of sensors and actuators.

Carlo Sferrazza

60,679 次观看 • 1 年前

Excited to share a few presentations, demos, and workshop talks from our group and collaborators at #ICRA2026! We will present recent work on real-to-sim-to-real robot policy evaluation, model-based planning with learned dynamics, and multi-modal manipulation. We will also have a joint live demo between SceniX AI and Analog Devices, Inc. on real-to-sim-to-real cable manipulation at the ICRA exhibition. This is a small teaser of what we have been building, with more to come soon! If you are at ICRA, please stop by the sessions or the demo booth. Happy to chat about robot learning, simulation, world models, and sim-to-real!

Excited to share a few presentations, demos, and workshop talks from our group and collaborators at #ICRA2026! We will present recent work on real-to-sim-to-real robot policy evaluation, model-based planning with learned dynamics, and multi-modal manipulation. We will also have a joint live demo between SceniX AI and Analog Devices, Inc. on real-to-sim-to-real cable manipulation at the ICRA exhibition. This is a small teaser of what we have been building, with more to come soon! If you are at ICRA, please stop by the sessions or the demo booth. Happy to chat about robot learning, simulation, world models, and sim-to-real!

Yunzhu Li

10,469 次观看 • 1 个月前

Long-horizon visual goals remain surprisingly hard for robot manipulation. We introduce Act2Goal, a goal-conditioned policy that uses a visual world model to reason about progress toward a goal, and practice it autonomously in the real world.

Long-horizon visual goals remain surprisingly hard for robot manipulation. We introduce Act2Goal, a goal-conditioned policy that uses a visual world model to reason about progress toward a goal, and practice it autonomously in the real world.

Jianlan Luo

95,100 次观看 • 6 个月前

NVIDIA DROPPED A MOTION DIFFUSION MODEL FOR HUMANOID ROBOTS trained on 700 hours of mocap data kimodo generates high-quality 3D human and robot motions from text prompts you control it with: → full-body pose keyframes → end-effector positions/rotations → 2D paths and waypoints works on human skeletons and unitree G1 robot plug the outputs directly into mujoco or retarget to other robots using GMR has a web-based interactive demo with a timeline editor. runs locally needs ~17GB VRAM to run inference open source under apache 2.0

NVIDIA DROPPED A MOTION DIFFUSION MODEL FOR HUMANOID ROBOTS trained on 700 hours of mocap data kimodo generates high-quality 3D human and robot motions from text prompts you control it with: → full-body pose keyframes → end-effector positions/rotations → 2D paths and waypoints works on human skeletons and unitree G1 robot plug the outputs directly into mujoco or retarget to other robots using GMR has a web-based interactive demo with a timeline editor. runs locally needs ~17GB VRAM to run inference open source under apache 2.0

Vaishnavi

17,572 次观看 • 2 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

Robot hands are already becoming more powerful than human hands. The next big AGI moment is when we can buy fancy robots for $100K to do all the housework!

Robot hands are already becoming more powerful than human hands. The next big AGI moment is when we can buy fancy robots for $100K to do all the housework!

Bindu Reddy

152,803 次观看 • 10 个月前