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。

We’ve submitted our hackathon project! To grasp small tools, we made an adapter using a 3D printer and repeatedly trained our ACT-based policy with imitation learning — resulting in our robotic TeaMaster :wink: #LeRobotWorldwideHackathon #lerobot

taguromaru / JK1RZI

4,320 subscribers

38,838 次观看 • 1 年前 •via X (Twitter)

科学技术教育 #LeRobotWorldwideHackathon #lerobot

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

Using our brain simulator, we’ve trained a reinforcement learning agent to maximize bits per second. Here is the RL policy converting brain data to cursor control in simulation:

Using our brain simulator, we’ve trained a reinforcement learning agent to maximize bits per second. Here is the RL policy converting brain data to cursor control in simulation:

Neuralink

18,410 次观看 • 1 年前

About a robot that became a 3D printer! 🖨️ A team of designers in Shanghai developed a groundbreaking 6-axis robotic 3D printer inspired by spiderwebs during a three-week summer workshop at Tongji University. The project sought to merge design and fabrication processes, drawing from spider threads' biomimetic strength and structure. 🕸️ The printer utilizes a unique spindle-knot extrusion technique, enabling self-supporting structures and greater spatial flexibility than traditional layer-based 3D printing. The device features a robot from KUKA and a robotic end-effector with movable printheads, controlled by an Arduino-based system with precise temperature and extrusion controls. Despite being a work in progress, the project exemplifies the potential of combining robotics and 3D printing for advanced manufacturing applications.

About a robot that became a 3D printer! 🖨️ A team of designers in Shanghai developed a groundbreaking 6-axis robotic 3D printer inspired by spiderwebs during a three-week summer workshop at Tongji University. The project sought to merge design and fabrication processes, drawing from spider threads' biomimetic strength and structure. 🕸️ The printer utilizes a unique spindle-knot extrusion technique, enabling self-supporting structures and greater spatial flexibility than traditional layer-based 3D printing. The device features a robot from KUKA and a robotic end-effector with movable printheads, controlled by an Arduino-based system with precise temperature and extrusion controls. Despite being a work in progress, the project exemplifies the potential of combining robotics and 3D printing for advanced manufacturing applications.

Lukas Ziegler

276,496 次观看 • 11 个月前

We used machine learning to quickly recreate key moments from the World Cup in 3D using just a single photograph. Read about our process:

We used machine learning to quickly recreate key moments from the World Cup in 3D using just a single photograph. Read about our process:

NYTimes R&D

100,678 次观看 • 3 年前

🎉Excited to share a fun little hardware project we’ve been working on. GELLO is an intuitive and low cost teleoperation device for robot arms that costs less than $300. We've seen the importance of data quality in imitation learning. Our goal is to make this more accessible 1/n

🎉Excited to share a fun little hardware project we’ve been working on. GELLO is an intuitive and low cost teleoperation device for robot arms that costs less than $300. We've seen the importance of data quality in imitation learning. Our goal is to make this more accessible 1/n

Philipp Wu

162,934 次观看 • 2 年前

🤖 How can robot policies zero-shot generalize to any new environment and any new object? Introducing our new project: 🚀Data Scaling Laws in Imitation Learning for Robotic Manipulation🚀—bringing us closer to the dream of having robots work as waiters in hot pot restaurants! 🍲

🤖 How can robot policies zero-shot generalize to any new environment and any new object? Introducing our new project: 🚀Data Scaling Laws in Imitation Learning for Robotic Manipulation🚀—bringing us closer to the dream of having robots work as waiters in hot pot restaurants! 🍲

Yang Gao

125,057 次观看 • 1 年前

AI agents are becoming increasingly capable of taking actions beyond the chat window and interacting with tools in the real world, such as web browsers. We explored this capability by having an AI agent present one of our interactive web-based demos. In this video, it's presenting our election interference demo. This agent is a Cursor coding agent and is equipped with tools to read and interact with the browser (using Playwright) and perform text-to-speech (with ElevenLabs), in addition to the standard Cursor tools.

AI agents are becoming increasingly capable of taking actions beyond the chat window and interacting with tools in the real world, such as web browsers. We explored this capability by having an AI agent present one of our interactive web-based demos. In this video, it's presenting our election interference demo. This agent is a Cursor coding agent and is equipped with tools to read and interact with the browser (using Playwright) and perform text-to-speech (with ElevenLabs), in addition to the standard Cursor tools.

CivAI

18,428 次观看 • 8 个月前

“We haven’t merely shot down India’s Rafale, we’ve shattered their morale. We’ve dismantled the pride they held in their supposed military superiority. By downing 25 of their advanced drones using both jammers and our defence systems, we’ve made our strength undeniable & that is called a huge victory in ‘conventional warfare’, we will keep these debris in our museums for our children to see that victory.” Federal minister Attaullah Tarar

“We haven’t merely shot down India’s Rafale, we’ve shattered their morale. We’ve dismantled the pride they held in their supposed military superiority. By downing 25 of their advanced drones using both jammers and our defence systems, we’ve made our strength undeniable & that is called a huge victory in ‘conventional warfare’, we will keep these debris in our museums for our children to see that victory.” Federal minister Attaullah Tarar

Dr Shama Junejo

20,203 次观看 • 1 年前

Experimenting with wrist controls on smart glasses Using our Wearables SDK, we can display a 3D wireframe A-Frame scene on compatible smartglasses (in this case the Brilliant Labs Frame running our custom firmware) We’re also using our SDK to control a virtual cursor with our Ukaton motion module strapped to our wrist, running an Edge Impulse model to detect pinches There’s a lot of third party hand control accessories we could use (TapWithUs, Doublepoint, and Mudra Band), but using our own hardware/software is great for creating custom gestures

Experimenting with wrist controls on smart glasses Using our Wearables SDK, we can display a 3D wireframe A-Frame scene on compatible smartglasses (in this case the Brilliant Labs Frame running our custom firmware) We’re also using our SDK to control a virtual cursor with our Ukaton motion module strapped to our wrist, running an Edge Impulse model to detect pinches There’s a lot of third party hand control accessories we could use (TapWithUs, Doublepoint, and Mudra Band), but using our own hardware/software is great for creating custom gestures

Brilliant Wear

29,397 次观看 • 10 个月前

We have entered the arena!🏛️ has been listed as an official project in the Solana Frontier Hackathon via Colosseum 🌍 Solana’s Largest Hackathon 💰 $2.5 million from Colosseum's venture fund We are building browser-native 3D AI agents onchain. Our platform allows anyone to create their own 3D agent, give it an LLM brain with memory + emotions + tool use with an on-chain identity that can be embedded anywhere as a web component.

We have entered the arena!🏛️ has been listed as an official project in the Solana Frontier Hackathon via Colosseum 🌍 Solana’s Largest Hackathon 💰 $2.5 million from Colosseum's venture fund We are building browser-native 3D AI agents onchain. Our platform allows anyone to create their own 3D agent, give it an LLM brain with memory + emotions + tool use with an on-chain identity that can be embedded anywhere as a web component.

three.ws

46,980 次观看 • 3 个月前

To make sure our customers have the best charging experience wherever they go, we made our own Ford Motor Company-specific adapter, co-developed with Lectron. Here's a behind-the-scenes look at the hard work, collaboration and extreme testing that brought this adapter to life...

To make sure our customers have the best charging experience wherever they go, we made our own Ford Motor Company-specific adapter, co-developed with Lectron. Here's a behind-the-scenes look at the hard work, collaboration and extreme testing that brought this adapter to life...

Jim Farley

188,261 次观看 • 1 年前

Every session is a learning curve. We’ve made huge strides, and we’re analyzing the data to compete in our first race tomorrow 🤜🤛

Every session is a learning curve. We’ve made huge strides, and we’re analyzing the data to compete in our first race tomorrow 🤜🤛

Cadillac Formula 1 Team

34,538 次观看 • 5 个月前

Our folding project showed what is possible with open-source. Reproducing it shouldn't take a PhD. LeRobot now ships with AGENT_GUIDE.md → so now your AI agent knows the insights, how to set up an SO-101, record good data, and pick a policy for your GPU. Just ask!

Our folding project showed what is possible with open-source. Reproducing it shouldn't take a PhD. LeRobot now ships with AGENT_GUIDE.md → so now your AI agent knows the insights, how to set up an SO-101, record good data, and pick a policy for your GPU. Just ask!

LeRobot

30,930 次观看 • 3 个月前

We’re proud to introduce our longtime Supporters, those who made this event possible and stood by us from our early days as a small streamer community in 2023 to everything we’ve built today. Our heartfelt thanks to 👇 #TEMPESTVORTEX

We’re proud to introduce our longtime Supporters, those who made this event possible and stood by us from our early days as a small streamer community in 2023 to everything we’ve built today. Our heartfelt thanks to 👇 #TEMPESTVORTEX

Tempest Gaming Guild

11,577 次观看 • 10 个月前

The robot climbs stairs🏯, steps over stones 🪨, and runs in the wild🏞️, all in one policy, without any remote control! Our #CVPR2023 Highlight paper achieves this by using RL + a 3D Neural Volumetric Memory (NVM) trained with view synthesis!

The robot climbs stairs🏯, steps over stones 🪨, and runs in the wild🏞️, all in one policy, without any remote control! Our #CVPR2023 Highlight paper achieves this by using RL + a 3D Neural Volumetric Memory (NVM) trained with view synthesis!

Xiaolong Wang

113,042 次观看 • 3 年前

Shri Abhishek Banerjee, our Parliamentary Party Leader in the Lok Sabha, chaired a meeting with our MPs today and submitted an official intimation to the Hon’ble Speaker. We want the House to function smoothly, but we also believe that an issue of immense importance like the Special Intensive Revision must be taken up for discussion. To that end, our MPs have repeatedly submitted adjournment motions. If BJP has nothing to hide, why are they dodging every question thrown at them?

Shri Abhishek Banerjee, our Parliamentary Party Leader in the Lok Sabha, chaired a meeting with our MPs today and submitted an official intimation to the Hon’ble Speaker. We want the House to function smoothly, but we also believe that an issue of immense importance like the Special Intensive Revision must be taken up for discussion. To that end, our MPs have repeatedly submitted adjournment motions. If BJP has nothing to hide, why are they dodging every question thrown at them?

All India Trinamool Congress

13,551 次观看 • 1 年前

🚀 Our NeurIPS '24 work, Large Spatial Model (LSM), is here! LSM performs semantic 3D reconstruction in just 0.1s, processing unposed data via feed-forward 3D reconstruction. 👉It leverages large-scale 3D datasets with minimal annotations, defining a 3D latent space. We are continuously exploring how this explicit 3D representation can further enhance reasoning and robotic learning. 🔗 Try our online Gradio demo with your own data at #NeurIPS2024 #3DReconstruction

🚀 Our NeurIPS '24 work, Large Spatial Model (LSM), is here! LSM performs semantic 3D reconstruction in just 0.1s, processing unposed data via feed-forward 3D reconstruction. 👉It leverages large-scale 3D datasets with minimal annotations, defining a 3D latent space. We are continuously exploring how this explicit 3D representation can further enhance reasoning and robotic learning. 🔗 Try our online Gradio demo with your own data at #NeurIPS2024 #3DReconstruction

Zhiwen(Aaron) Fan

43,986 次观看 • 1 年前

🏗️ Policy Adaptation from Foundation Model Feedback #CVPR2023 Instead of using foundation model as a pre-trained encoder (generator), we use it as a Teacher (discriminator) to tell where our policy did wrong and helps it adapts to new envs and tasks.

🏗️ Policy Adaptation from Foundation Model Feedback #CVPR2023 Instead of using foundation model as a pre-trained encoder (generator), we use it as a Teacher (discriminator) to tell where our policy did wrong and helps it adapts to new envs and tasks.

Xiaolong Wang

24,412 次观看 • 3 年前

Famine in #Gaza is a created catastrophe. Ending this human-made crisis demands that we act as if it were our mother, our father, our child, our family trying to survive in Gaza today. We would all do more. We must all do more. And quickly.

Famine in #Gaza is a created catastrophe. Ending this human-made crisis demands that we act as if it were our mother, our father, our child, our family trying to survive in Gaza today. We would all do more. We must all do more. And quickly.

Joyce Msuya

22,215 次观看 • 11 个月前

The magic of a DAO is that it’s a new type of community-owned company that wasn’t previously possible. Myosin isn't perfect, but we’ve done something right.... Despite the relentless bear market, we've scaled up our operations, boosted our cash flow, expanded our community, and extended our reach. We’ve built a community with over 150 marketing experts. We’ve worked with over 25 high-profile clients. And we’ve paid out OVER a million dollars to our members! But here's the thing—we make mistakes. We’re learning and building in real-time. And we want to bring you along for the ride. Welcome to Behind the DAO.

Myosin.xyz (〽️, 🌎)

40,960 次观看 • 2 年前