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.

This gentle robot captures delicate sea creatures and collects data without harming them

National Geographic

27,978,975 subscribers

227,897 views • 3 years ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 Comments

Engelbert Bruna3 years ago

Una abducción 😨🛸

✨️Stephanie Halbrook✨️3 years ago

🥰

Ballz3 years ago

Lol.Thats cool but I wonder if it scares the shit out of the creatures or confuses them.

Ali Van Zee3 years ago

This is great. We’ve killed way too many creatures in the name of science.

HARRY POTTER❤️👋👑3 years ago

How about the energy these gadgets dish out? Isn’t it harmful to the ocean in the longer term

VAHİD ADIGÜZEL 🇹🇷3 years ago

Bu harika

Joshua Ajowele3 years ago

@SarahMackAttack

Stardust3 years ago

Future looks very bright

YEASIR ARFAT3 years ago

that's cool

Aaron Sweatt3 years ago

Protect the wild life we have left! :)

Related Videos

Can we use wearable devices to collect robot data without actual robots? Yes! With a pair of gloves🧤! Introducing DexCap, a portable hand motion capture system that collects 3D data (point cloud + finger motion) for training robots with dexterous hands Everything open-sourced

Can we use wearable devices to collect robot data without actual robots? Yes! With a pair of gloves🧤! Introducing DexCap, a portable hand motion capture system that collects 3D data (point cloud + finger motion) for training robots with dexterous hands Everything open-sourced

Chen Wang

239,510 views • 2 years ago

the sea and its creatures

the sea and its creatures

rubngum

103,854 views • 3 years ago

X Square Robot has introduced TwinDEX: a co-designed pair of three-finger, 9-DoF dexterous hands, one wearable for data collection, one matched robot end effector for deployment. The wearable and the robot hand share the same kinematics, geometry, materials, look, and sensors, so human demos map straight to the robot without retargeting. Human data collection improves throughput 5.3x compared to teleoperation, and a policy can be trained with a few hundred episodes without any robot data.

X Square Robot has introduced TwinDEX: a co-designed pair of three-finger, 9-DoF dexterous hands, one wearable for data collection, one matched robot end effector for deployment. The wearable and the robot hand share the same kinematics, geometry, materials, look, and sensors, so human demos map straight to the robot without retargeting. Human data collection improves throughput 5.3x compared to teleoperation, and a policy can be trained with a few hundred episodes without any robot data.

The Humanoid Hub

277,022 views • 1 month ago

You are not ready. The largest robot data factory just dropped footage. 😯 And this could completely change the humanoid robot data collection game.

You are not ready. The largest robot data factory just dropped footage. 😯 And this could completely change the humanoid robot data collection game.

Techniahqrobot | humanoid robots

12,690 views • 1 month ago

"Extremely dangerous sea creatures and fish." 🌊🐟

"Extremely dangerous sea creatures and fish." 🌊🐟

Animal Arts 😻🇺🇸🇬🇧🇬🇧🇺🇸

763,693 views • 3 months ago

Midjourney: Bioluminescent sea creature with expressive eyes and delicate appendages.

Midjourney: Bioluminescent sea creature with expressive eyes and delicate appendages.

Science Girl

40,603 views • 3 months ago

Can we collect robot data without any robots? Introducing Universal Manipulation Interface (UMI) An open-source $400 system from Stanford University designed to democratize robot data collection 0 teleop -> autonomously wash dishes (precise), toss (dynamic), and fold clothes (bimanual)

Can we collect robot data without any robots? Introducing Universal Manipulation Interface (UMI) An open-source $400 system from Stanford University designed to democratize robot data collection 0 teleop -> autonomously wash dishes (precise), toss (dynamic), and fold clothes (bimanual)

Cheng Chi

439,927 views • 2 years ago

THIS is how dolphins and sea creatures should be shown.. not glass tanks! so beautiful 🌊🐬

THIS is how dolphins and sea creatures should be shown.. not glass tanks! so beautiful 🌊🐬

Nature is Amazing ☘️

2,386,358 views • 1 year ago

🚨Is it possible to devise an intuitive approach for crowdsourcing trainable data for robots without requiring a physical robot🤖? Can we democratize robot learning for all?🧑‍🤝‍🧑 Check out our latest #CoRL2023 paper-> AR2-D2: Training a Robot Without a Robot

🚨Is it possible to devise an intuitive approach for crowdsourcing trainable data for robots without requiring a physical robot🤖? Can we democratize robot learning for all?🧑‍🤝‍🧑 Check out our latest #CoRL2023 paper-> AR2-D2: Training a Robot Without a Robot

Jiafei Duan

38,926 views • 3 years ago

This indie developer is making an adventure have where you can walk on water and have to herd sea creatures and protect them from danger. It's called The Edge of Water, are you interested?

This indie developer is making an adventure have where you can walk on water and have to herd sea creatures and protect them from danger. It's called The Edge of Water, are you interested?

Best Indie Games

27,065 views • 5 months ago

Tired of teleoperation? One human video → 1,000s of robot demos. (📍GitHub ) Scaling Robot Data Without Dynamics Simulation or Robot Hardware Real2Render2Real (R2R2R) is a new way to scale robot data without physics simulation or hardware. You take a phone scan + a single monocular human demo. It tracks the motion, renders photorealistic scenes, and generates diverse, robot-agnostic trajectories ready for training. > No teleop, no sim, no robot, just a phone and a video > Train VLA models and diffusion policies directly on the output > Supports multiple robot embodiments with kinematic consistency > 1000s of demos in 1/27 the time of real-world collection Thank you, Max Fu, for sharing!! Project: Paper: Code coming soon: It shows that with the right pipeline, you can scale robot learning data without touching a robot. One of the most interesting directions in scalable robotics today. —— Weekly robotics and AI insights. Subscribe free:

Tired of teleoperation? One human video → 1,000s of robot demos. (📍GitHub ) Scaling Robot Data Without Dynamics Simulation or Robot Hardware Real2Render2Real (R2R2R) is a new way to scale robot data without physics simulation or hardware. You take a phone scan + a single monocular human demo. It tracks the motion, renders photorealistic scenes, and generates diverse, robot-agnostic trajectories ready for training. > No teleop, no sim, no robot, just a phone and a video > Train VLA models and diffusion policies directly on the output > Supports multiple robot embodiments with kinematic consistency > 1000s of demos in 1/27 the time of real-world collection Thank you, Max Fu, for sharing!! Project: Paper: Code coming soon: It shows that with the right pipeline, you can scale robot learning data without touching a robot. One of the most interesting directions in scalable robotics today. —— Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

42,864 views • 8 months ago

TRENDING 🚨: A video captures the moment a spiritualist dumps sacrificed food items into the sea as onlookers and fishermen dive to retrieve them. Is this a norm in Nigeria? 🇳🇬

TRENDING 🚨: A video captures the moment a spiritualist dumps sacrificed food items into the sea as onlookers and fishermen dive to retrieve them. Is this a norm in Nigeria? 🇳🇬

WithAlvin 🇬🇭

294,716 views • 9 months ago

Policies trained on real robot data via imitation can be surprisingly capable. But for domains like dexterous manipulation, they are often not quite good enough: they move slowly, miss grasps, make unreliable contact, and fail under small perturbations. Can we improve them without any additional data collection on the real robot? In SCORE, we show that we can improve real-world diffusion/flow policies cheaply by using simulation to simply learn how to steer them on deployment. This leads to large gains in real-world success and speed across a variety of tasks, without requiring additional real-world experience: 🧵 (1/10)

Policies trained on real robot data via imitation can be surprisingly capable. But for domains like dexterous manipulation, they are often not quite good enough: they move slowly, miss grasps, make unreliable contact, and fail under small perturbations. Can we improve them without any additional data collection on the real robot? In SCORE, we show that we can improve real-world diffusion/flow policies cheaply by using simulation to simply learn how to steer them on deployment. This leads to large gains in real-world success and speed across a variety of tasks, without requiring additional real-world experience: 🧵 (1/10)

Abhishek Gupta

35,328 views • 3 months ago

i love how gentle leon can be. in moments with grace or ashley seeing them panic he becomes more delicate and soft to help them calm down, to guide them and reassure them they can do it. he always makes sure they know they aren't alone and he's there to support them

i love how gentle leon can be. in moments with grace or ashley seeing them panic he becomes more delicate and soft to help them calm down, to guide them and reassure them they can do it. he always makes sure they know they aren't alone and he's there to support them

charlotte.

127,799 views • 6 months ago

Introducing OM-1, our first robot foundation model, zero-shot generalizing to any robot: table-top arms, industrial arms and humanoids. - learned directly from human manipulation data - no teleop/robot data - close to human-level dexterity and efficiency - multi-robot collab

Introducing OM-1, our first robot foundation model, zero-shot generalizing to any robot: table-top arms, industrial arms and humanoids. - learned directly from human manipulation data - no teleop/robot data - close to human-level dexterity and efficiency - multi-robot collab

Reward AI

1,762,584 views • 23 days ago

Imagine robots learning new skills—without any robot data. Today, we're excited to release EgoZero: our first steps in training robot policies that operate in unseen environments, solely from data collected through humans wearing Aria smart glasses. 🧵👇

Imagine robots learning new skills—without any robot data. Today, we're excited to release EgoZero: our first steps in training robot policies that operate in unseen environments, solely from data collected through humans wearing Aria smart glasses. 🧵👇

Lerrel Pinto

42,673 views • 1 year ago

He was bullied, and so the sea creatures stand to defend him 🤯

He was bullied, and so the sea creatures stand to defend him 🤯

Ahmad

97,128 views • 6 months ago