Aperdata_ai's profile picture. Physical AI nutrition = 3D spatial data = http://Aperdata.AI

Aperdata

@Aperdata_ai

Physical AI nutrition = 3D spatial data = http://Aperdata.AI

Aperdata さんがリポスト

My goal throughout my PhD has been to take robots out of the lab and into the real world. It was so special to be a part of this effort and see this dream become reality! Excited to keep pushing model capabilities—and, of course, keep playing with robots 🤖

We got a robot to clean up homes that were never seen in its training data! Our new model, π-0.5, aims to tackle open-world generalization. We took our robot into homes that were not in the training data and asked it to clean kitchens and bedrooms. More below⤵️



🤖!

Me, Robot

Tesla_Optimus's tweet image. Me, Robot


If Martínez had stood there would it have scored?

Booster Robotics @boosterobotics just dropped a new humanoid soccer demo—and it’s next level. From curved free kicks to smooth step-overs, their T1 units now pull off moves like Ronaldo and block like Buffon.



I thought it was doing a new dance😂

Trying to teach my new model to run using reinforcement learning (Hyfydy + depRL)



I think Phoenix is ​​the robot that is closest to embodied AI. What do you think?

Aperdata_ai's tweet image. I think Phoenix is ​​the robot that is closest to embodied AI. What do you think?

This is the same open source mission as we do,thanks to @NVIDIAAI that lead this feat!👏 huggingface.co/collections/nv…


Very intuitive demonstration

How do you teach a robot to handle complex, multi-step tasks, without training it for each one? [Github ⬇️] The team behind ReKep shows that robots can perform bimanual, in-the-wild tasks by reasoning over keypoint constraints: Generated on the fly using vision and language…



Aperdata さんがリポスト

FigureAI Robots - New demo just dropped today. We have NOT seen demos like this from Optimus (or anyone else). These are fully AI-driven humanoids, not 'puppeted' by humans in a dotsuit. Only Figure's proprietary robot AI is used to reason how to put the groceries away --…


Aperdata さんがリポスト

Teleoperating humanoids with friends in Hong Kong


Aperdata さんがリポスト

ORCA: An open-source, reliable, cost-effective, anthropomorphic dexterous hand for uninterrupted dexterous task learning. 17 degrees of freedom (16 in fingers, 1 in wrist), tendon actuated. orcahand.com

CyberRobooo's tweet image. ORCA: An open-source, reliable, cost-effective, anthropomorphic dexterous hand for uninterrupted dexterous task learning. 17 degrees of freedom (16 in fingers, 1 in wrist), tendon actuated.

orcahand.com

Aperdata さんがリポスト

Super happy to announce that we are acquiring @pollenrobotics to bring open-source robots to the world! 🤖 Since @RemiCadene joined us from Tesla, we’ve become the most widely used software platform for open robotics thanks to @LeRobotHF and the Hugging Face Hub. Now, we’re…

huggingface's tweet image. Super happy to announce that we are acquiring @pollenrobotics to bring open-source robots to the world! 🤖

Since @RemiCadene joined us from Tesla, we’ve become the most widely used software platform for open robotics thanks to @LeRobotHF and the Hugging Face Hub. Now, we’re…

United States トレンド

Loading...

Something went wrong.


Something went wrong.