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。

Controlled via a Bluetooth finger patch, BeetleBot, a beetle-inspired soft robot, can perform various locomotive tasks and provide visual and sensory feedback for potential applications from biomedical assistance to environment exploration. Learn more in Science Advances:

Science Magazine

4,784,574 subscribers

111,604 次观看 • 2 个月前 •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

This bioinspired robot can autorotate after aerial deployment to make a soft landing on water and convert to a sailboat—using only three actuators and three primary sensors. SUTD Singapore Learn more in Science #Robotics:

This bioinspired robot can autorotate after aerial deployment to make a soft landing on water and convert to a sailboat—using only three actuators and three primary sensors. SUTD Singapore Learn more in Science #Robotics:

Science Robotics

11,220 次观看 • 23 天前

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

58,763 次观看 • 10 个月前

📣 Introducing R3PEATS, a new NIH Common Fund program to invest in the people and practices behind rigorous science — helping researchers build and share the tools, training, and collaborations that strengthen biomedical research and translate more reliably into benefits for patients. Learn more ➡️

📣 Introducing R3PEATS, a new NIH Common Fund program to invest in the people and practices behind rigorous science — helping researchers build and share the tools, training, and collaborations that strengthen biomedical research and translate more reliably into benefits for patients. Learn more ➡️

NIH

17,936 次观看 • 9 天前

Population dynamics can provide insights into domains ranging from health to environmental science. Here we introduce a geospatial foundation model (plus embeddings and code recipes) that could be employed for a variety of downstream tasks. →

Population dynamics can provide insights into domains ranging from health to environmental science. Here we introduce a geospatial foundation model (plus embeddings and code recipes) that could be employed for a variety of downstream tasks. →

Google AI

41,934 次观看 • 1 年前

Memo is a robot that uses AI to perform household tasks effectively. Today Sunday announced its Series B, and we’re proud to be investors. Training robots for the home is hard — the environment is messy, dynamic, and full of edge cases. So Sunday is training robots directly on real households. Founders Tony Zhao and Cheng Chi built a glove-based system that lets hundreds of contributors record everyday tasks in their own homes, creating high-fidelity demonstrations that feed directly into robot learning. Home robotics will be defined by the companies that learn fastest from real homes. Sunday is building that loop. More here: Aaref Hilaly Amanda Huang

Memo is a robot that uses AI to perform household tasks effectively. Today Sunday announced its Series B, and we’re proud to be investors. Training robots for the home is hard — the environment is messy, dynamic, and full of edge cases. So Sunday is training robots directly on real households. Founders Tony Zhao and Cheng Chi built a glove-based system that lets hundreds of contributors record everyday tasks in their own homes, creating high-fidelity demonstrations that feed directly into robot learning. Home robotics will be defined by the companies that learn fastest from real homes. Sunday is building that loop. More here: Aaref Hilaly Amanda Huang

Bain Capital Ventures

22,050 次观看 • 7 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

Each weaver ant can pull on a leaf much harder when in a group than when it works alone. The ants’ sticky feet and coordinated legwork, researchers believe, improve the ants’ collective efficiency—a finding that may provide insights into how to build and coordinate swarms of robots that work together. Learn more: News from Science

Each weaver ant can pull on a leaf much harder when in a group than when it works alone. The ants’ sticky feet and coordinated legwork, researchers believe, improve the ants’ collective efficiency—a finding that may provide insights into how to build and coordinate swarms of robots that work together. Learn more: News from Science

Science Magazine

50,692 次观看 • 1 年前

System ID for legged robots is hard: (1) Discontinuous dynamics and (2) many parameters to identify and hard to "excite" them. SPI-Active is a general tool for legged robot system ID. Key ideas: (1) massively parallel sampling-based optimization, (2) structured parameter space, and (3) active exploration based on Fisher Information to collect the most informative data in real. SPI-Active provides an accurate robot model and effectively reduces the sim2real gap. In sim2real policy learning setting, it outperforms baselines by 42-63% in various quadruped & humanoid tasks. Led by Nikhil Sobanbabu Guanqi He

System ID for legged robots is hard: (1) Discontinuous dynamics and (2) many parameters to identify and hard to "excite" them. SPI-Active is a general tool for legged robot system ID. Key ideas: (1) massively parallel sampling-based optimization, (2) structured parameter space, and (3) active exploration based on Fisher Information to collect the most informative data in real. SPI-Active provides an accurate robot model and effectively reduces the sim2real gap. In sim2real policy learning setting, it outperforms baselines by 42-63% in various quadruped & humanoid tasks. Led by Nikhil Sobanbabu Guanqi He

Guanya Shi

21,442 次观看 • 1 年前

Super excited about Hydra-0 from Hongyu Li and team! The key idea is to use flow as a shared visual interface across embodiments/objects for controllable video generation, allowing a single generalist world model to learn from human, handheld-gripper, and robot interaction data. My favorite result is the video below: start from a real video of a human doing the task (left), extract the desired object flow, and condition the model on that flow (right). The model then hallucinates a plausible robot motion that could produce the same object motion. Very cool glimpse of how a generalist world model can bridge human demonstrations and robot control.

Super excited about Hydra-0 from Hongyu Li and team! The key idea is to use flow as a shared visual interface across embodiments/objects for controllable video generation, allowing a single generalist world model to learn from human, handheld-gripper, and robot interaction data. My favorite result is the video below: start from a real video of a human doing the task (left), extract the desired object flow, and condition the model on that flow (right). The model then hallucinates a plausible robot motion that could produce the same object motion. Very cool glimpse of how a generalist world model can bridge human demonstrations and robot control.

Yunzhu Li

10,850 次观看 • 2 个月前

ANTHROPIC 🔥: A new Managed Projects feature has been spotted in testing on Claude. > Claude takes on tasks and keeps the project organized. > A project is a home for one stream of work. Sessions share memory and instructions so context carries forward, and Claude runs more autonomously. Projects only create and manage cloud sessions. This feature may be built on top of Claude Managed Agents, where each project gets a dedicated cloud environment so Claude can execute periodic tasks and refine project context via "Dreams". It could also be a successor to Conway, which is set to be removed this Friday internally.

ANTHROPIC 🔥: A new Managed Projects feature has been spotted in testing on Claude. > Claude takes on tasks and keeps the project organized. > A project is a home for one stream of work. Sessions share memory and instructions so context carries forward, and Claude runs more autonomously. Projects only create and manage cloud sessions. This feature may be built on top of Claude Managed Agents, where each project gets a dedicated cloud environment so Claude can execute periodic tasks and refine project context via "Dreams". It could also be a successor to Conway, which is set to be removed this Friday internally.

🚨 AI News | TestingCatalog

61,827 次观看 • 3 个月前

See the world, build your skills and bring new perspectives home. Through International Experience Canada, Canadian citizens aged 18 to 35 can travel and work and thrive in a new environment abroad for up to 2 years —gaining international experience they can draw on when they return to Canada and continue building their careers. Learn more:

See the world, build your skills and bring new perspectives home. Through International Experience Canada, Canadian citizens aged 18 to 35 can travel and work and thrive in a new environment abroad for up to 2 years —gaining international experience they can draw on when they return to Canada and continue building their careers. Learn more:

IRCC

48,473 次观看 • 3 个月前

E pluribus unum – “out of many, one” – is not only a motto for the United States. It’s a good credo for microrobots. A research collaboration between Cornell and the Max Planck Institute for Intelligent Systems has shown how a swarm of microrobots spinning on a water surface can together generate the fluidic torque needed to manipulate passive structures without any physical contact. This collective behavior was demonstrated to operate gears and move objects, with the aim of eventually performing microscale tasks and biomedical procedures. “At small scales, contact-based manipulation can be limiting, and flow-based manipulation offers a great alternative,” said Kirstin Petersen, associate professor and an Aref and Manon Lahham Faculty Fellow in the Department of Electrical and Computer Engineering in Cornell Duffield College of Engineering and the paper’s co-senior author. “We’re showing that in spite of their size, adding more microrobots creates stronger flows and greater torque transfer.” The research published Feb. 25 in Science Advances. The lead author is Steven Ceron, Ph.D. ’22, now an assistant professor at the University of Michigan. More:

E pluribus unum – “out of many, one” – is not only a motto for the United States. It’s a good credo for microrobots. A research collaboration between Cornell and the Max Planck Institute for Intelligent Systems has shown how a swarm of microrobots spinning on a water surface can together generate the fluidic torque needed to manipulate passive structures without any physical contact. This collective behavior was demonstrated to operate gears and move objects, with the aim of eventually performing microscale tasks and biomedical procedures. “At small scales, contact-based manipulation can be limiting, and flow-based manipulation offers a great alternative,” said Kirstin Petersen, associate professor and an Aref and Manon Lahham Faculty Fellow in the Department of Electrical and Computer Engineering in Cornell Duffield College of Engineering and the paper’s co-senior author. “We’re showing that in spite of their size, adding more microrobots creates stronger flows and greater torque transfer.” The research published Feb. 25 in Science Advances. The lead author is Steven Ceron, Ph.D. ’22, now an assistant professor at the University of Michigan. More:

Cornell University

52,358 次观看 • 7 个月前

High fidelity visuomotor data from handheld grippers or data capture gloves provide the most valuable robot learning data. This data collection modality achieves the best balance of trade-offs compared to teleop, master–slave devices (e.g., ALOHA), and egocentric cameras. They’re portable, intuitive, low-cost/scalable, and directly transferable to robots. They don’t require expensive robot hardware (like teleop or master–slave devices), and they avoid morphology mismatch and occlusion issues (egocentric cameras). This new handheld gripper improves on the original UMI gripper with a few advantages: •A “Robotiq”-style finger linkage enables parallel-jaw grasps without the bulky linear rail •Quick-disconnect swappable fingertips for diverse tasks •A touchscreen enables real-time data auditing/labeling •Stereo cameras provide depth information •A microphone which can capture haptic contact information and natural language annotations •An “action” button under the trigger finger to easily start/stop recording demonstrations

High fidelity visuomotor data from handheld grippers or data capture gloves provide the most valuable robot learning data. This data collection modality achieves the best balance of trade-offs compared to teleop, master–slave devices (e.g., ALOHA), and egocentric cameras. They’re portable, intuitive, low-cost/scalable, and directly transferable to robots. They don’t require expensive robot hardware (like teleop or master–slave devices), and they avoid morphology mismatch and occlusion issues (egocentric cameras). This new handheld gripper improves on the original UMI gripper with a few advantages: •A “Robotiq”-style finger linkage enables parallel-jaw grasps without the bulky linear rail •Quick-disconnect swappable fingertips for diverse tasks •A touchscreen enables real-time data auditing/labeling •Stereo cameras provide depth information •A microphone which can capture haptic contact information and natural language annotations •An “action” button under the trigger finger to easily start/stop recording demonstrations

Simon Kalouche

39,082 次观看 • 9 个月前