Загрузка видео...

Не удалось загрузить видео

На главную

Optimus can now sort objects autonomously 🤖 Its neural network is trained fully end-to-end: video in, controls out. Come join to help develop Optimus (& improve its yoga routine 🧘) →

Tesla_Optimus's profile picture

Tesla Optimus

653,044 subscribers

14,209,054 просмотров • 2 лет назад •via X (Twitter)

ОбразованиеНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 10

Фото профиля Elon Musk
Elon Musk2 лет назад

Progress

Фото профиля Sawyer Merritt
Sawyer Merritt2 лет назад

BUT WALL ST SAYS UR JUST A CAR COMPANY!

Фото профиля Lex Fridman
Lex Fridman2 лет назад

This speed of progress is super exciting to see!

Фото профиля Emmet Peppers
Emmet Peppers2 лет назад

This is incredible progress

Фото профиля Gail Alfar
Gail Alfar2 лет назад

this is got to be one of the coolest places to work in the USA! 😎

Фото профиля Warren Redlich - Chasing Dreams 🇺🇸
Warren Redlich - Chasing Dreams 🇺🇸2 лет назад

Sweet! Next up ... cooking demos - Optimus makes an omelet.

Фото профиля The Tesla Hoe
The Tesla Hoe2 лет назад

One step closer to folding my clothes! 🧺 Can’t wait to have my own Optimus!

Фото профиля serious gemini
serious gemini2 лет назад

man i could almost feel it got annoyed right there

Фото профиля Elon's My Hero — e/acc 🤖FALSC
Elon's My Hero — e/acc 🤖FALSC2 лет назад

Awesome, but a couple questions. 1, why is it using its right hand to sort and not the left? Just copying what most people do? 2, why is it sorting with just one hand? Why doesn't it sort the blue with its right hand and green with its left hand at the same time?

Фото профиля Scott Wainner
Scott Wainner2 лет назад

Oh man, I thought that music sounded familiar. 🤣

Похожие видео

This is a vertically integrated end to end deep neural network performing forward pass inference real-time, controlling individual actuator's torque output for bidpedal gait generation in adverse, GPS denied, envs. ok its standard PPO rl trained in mjlab, strapped to a tractor.
1:29

This is a vertically integrated end to end deep neural network performing forward pass inference real-time, controlling individual actuator's torque output for bidpedal gait generation in adverse, GPS denied, envs. ok its standard PPO rl trained in mjlab, strapped to a tractor.

Harrison Kinsley

34,118 просмотров • 5 месяцев назад

ELON: NEXT OPTIMUS WILL BE ‘SOMETHING SPECIAL’ “The new Optimus design, which will be complete later this year, is something special.” In December 2023, Tesla unveiled its fully custom-built Gen 2 Optimus with improved speed, weight and number of degrees of freedom. In 2024, Tesla started to deploy the robot to do useful work in its factories. Source: 𝕏
1:43

ELON: NEXT OPTIMUS WILL BE ‘SOMETHING SPECIAL’ “The new Optimus design, which will be complete later this year, is something special.” In December 2023, Tesla unveiled its fully custom-built Gen 2 Optimus with improved speed, weight and number of degrees of freedom. In 2024, Tesla started to deploy the robot to do useful work in its factories. Source: 𝕏

Mario Nawfal

61,114 просмотров • 1 год назад

Brett Adcock says the latest autonomous demo of Figure 02 is fully end-to-end and uses a single neural network – camera frames in, actions out. “You cannot code your way out of this problem.”
2:30

Brett Adcock says the latest autonomous demo of Figure 02 is fully end-to-end and uses a single neural network – camera frames in, actions out. “You cannot code your way out of this problem.”

The Humanoid Hub

56,268 просмотров • 1 год назад

In time of war its important to keep mind and body fresh Do Yoga 🧘🧘
0:36

In time of war its important to keep mind and body fresh Do Yoga 🧘🧘

Lucky Singh

324,354 просмотров • 1 год назад

Optimus dancing autonomously
0:28

Optimus dancing autonomously

Whole Mars Catalog

940,417 просмотров • 1 год назад

Optimus can walk like us. Optimus can dance like us. Optimus can work like us. Now… Optimus can do Kung Fu like us.
0:22

Optimus can walk like us. Optimus can dance like us. Optimus can work like us. Now… Optimus can do Kung Fu like us.

DogeDesigner

1,523,702 просмотров • 8 месяцев назад

VIDEO - Tesla Optimus Robot Dancing to Kanye’s Heil Hitler. Okay this is just getting out of hand now… Come on Elon Musk 🤨
0:35

VIDEO - Tesla Optimus Robot Dancing to Kanye’s Heil Hitler. Okay this is just getting out of hand now… Come on Elon Musk 🤨

Matthew Sabia ⚡️

24,599 просмотров • 1 год назад

This is a comparison video between LI and Tesla's autonomous driving systems. LI once claimed in 2024 that it had developed an end-to-end neural network better than Tesla's, but what the truth is, we can see it in this video.
27:30

This is a comparison video between LI and Tesla's autonomous driving systems. LI once claimed in 2024 that it had developed an end-to-end neural network better than Tesla's, but what the truth is, we can see it in this video.

𝐶ℎ𝑎𝑟𝑙𝑒𝑠

35,248 просмотров • 1 год назад

RTFM can be seen as a learned renderer: it is an autoregressive diffusion transformer trained end-to-end on large-scale video data, and it learns to model 3D geometry, reflections, shadows and more just by observing them in its training set.
0:24

RTFM can be seen as a learned renderer: it is an autoregressive diffusion transformer trained end-to-end on large-scale video data, and it learns to model 3D geometry, reflections, shadows and more just by observing them in its training set.

World Labs

15,870 просмотров • 7 месяцев назад

2 Chainz talks to the new Tesla Robot “Optimus” 🤖
1:08

2 Chainz talks to the new Tesla Robot “Optimus” 🤖

DailyRapFacts

208,338 просмотров • 1 год назад

Elon Musk on Optimus: "Everything in the Optimus robot is designed from Physics First Principles. Its not taken from a catalog. These are custom designed. Everything, literally everything. Optimus is designed to have a lot of intelligence and to have the same electromechanical dexterity, if not higher than a human. It's quite a big robot because it has to carry heavy objects for long periods of time and not overheat or exceed the power of its actuators. It's 5 11, so it's pretty tall and it's got a lot of intelligence. So it's going to be more expensive than a small robot that is not. Over time as Optimus robots build Optimus robots, the cost will drop very quickly."
2:43

Elon Musk on Optimus: "Everything in the Optimus robot is designed from Physics First Principles. Its not taken from a catalog. These are custom designed. Everything, literally everything. Optimus is designed to have a lot of intelligence and to have the same electromechanical dexterity, if not higher than a human. It's quite a big robot because it has to carry heavy objects for long periods of time and not overheat or exceed the power of its actuators. It's 5 11, so it's pretty tall and it's got a lot of intelligence. So it's going to be more expensive than a small robot that is not. Over time as Optimus robots build Optimus robots, the cost will drop very quickly."

DogeDesigner

69,859 просмотров • 4 месяцев назад

🇩🇪 Tesla Optimus serving popcorn during its first appearance in Germany
0:51

🇩🇪 Tesla Optimus serving popcorn during its first appearance in Germany

The Tesla Newswire

45,026 просмотров • 5 месяцев назад

Can a single neural network policy generalize over poses, objects, obstacles, backgrounds, scene arrangements, in-hand objects, and start/goal states? Introducing Neural MP: A generalist policy for solving motion planning tasks in the real world 🤖 1/N
1:15

Can a single neural network policy generalize over poses, objects, obstacles, backgrounds, scene arrangements, in-hand objects, and start/goal states? Introducing Neural MP: A generalist policy for solving motion planning tasks in the real world 🤖 1/N

Murtaza Dalal

114,538 просмотров • 1 год назад

Optimus bots are already performing tasks autonomously in the Tesla factory.
0:41

Optimus bots are already performing tasks autonomously in the Tesla factory.

DogeDesigner

682,490 просмотров • 1 год назад

🇺🇸 TESLA’S OPTIMUS ROBOT JUST STOLE THE SHOW IN MIAMI It didn’t give a speech, but it didn’t need to. Just by waving and handing out water, Optimus got the kind of attention you'd expect a real, functioning humanoid robot to get. At Tesla’s “Future of Autonomy” event, Optimus wasn’t just for show. It moved on its own, interacted with people, and looked one step closer to something out of a sci-fi movie. Tesla says Optimus is trained using the same tech behind Autopilot, feeding on millions of real-world videos to learn how to operate in messy human environments. Source: Tesla, Erick Brito
0:41

🇺🇸 TESLA’S OPTIMUS ROBOT JUST STOLE THE SHOW IN MIAMI It didn’t give a speech, but it didn’t need to. Just by waving and handing out water, Optimus got the kind of attention you'd expect a real, functioning humanoid robot to get. At Tesla’s “Future of Autonomy” event, Optimus wasn’t just for show. It moved on its own, interacted with people, and looked one step closer to something out of a sci-fi movie. Tesla says Optimus is trained using the same tech behind Autopilot, feeding on millions of real-world videos to learn how to operate in messy human environments. Source: Tesla, Erick Brito

Mario Nawfal

145,210 просмотров • 6 месяцев назад

Rivian has been working since 2022 to re-architect its self-driving system around an end-to-end trained model. The ultimate capability of the vehicle will be level four self-driving - being able to operate autonomously without anyone in the driver's seat, says CEO RJ Scaringe.
2:17

Rivian has been working since 2022 to re-architect its self-driving system around an end-to-end trained model. The ultimate capability of the vehicle will be level four self-driving - being able to operate autonomously without anyone in the driver's seat, says CEO RJ Scaringe.

TBPN

31,966 просмотров • 5 месяцев назад

Figure-01 has learned to make coffee ☕️ Our AI learned this after watching humans make coffee This is end-to-end AI: our neural networks are taking video in, trajectories out Join us to train our robot fleet:
1:21

Figure-01 has learned to make coffee ☕️ Our AI learned this after watching humans make coffee This is end-to-end AI: our neural networks are taking video in, trajectories out Join us to train our robot fleet:

Brett Adcock

1,689,610 просмотров • 2 лет назад

India can use its channels with Russia to help end the Ukraine war, says Norway PM Gahr
1:07

India can use its channels with Russia to help end the Ukraine war, says Norway PM Gahr

Sidhant Sibal

28,552 просмотров • 23 дней назад

End-to-end neural networks racing drones in Abu Dhabi! 🚁 Check out the drone racing team from Delft University of Technology! A completely end-to-end neural network solution, from pixels to direct motor commands. No Kalman filters. No computer vision feature detectors. Just neurons flying the drone. The challenge is extreme. These drones fly at high speeds and need split-second decisions with minimal onboard resources: a single rolling-shutter camera and an IMU. Their approach is called SkyDreamer, based on the Dreamer-v3 reinforcement learning algorithm. First, a world model is trained in simulation. Then, the neural network learns how to fly in its dreams through reinforcement learning. The network's internal state can be read out to see where it thinks it is on the track or how fast it's going. Even better, the drone estimates some of its own body characteristics during flight, like the camera angle relative to the body, eliminating time-consuming manual calibration. The system uses only a single camera and the gyros from the IMU, ignoring the accelerometers, just like human FPV pilots do. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
1:01

End-to-end neural networks racing drones in Abu Dhabi! 🚁 Check out the drone racing team from Delft University of Technology! A completely end-to-end neural network solution, from pixels to direct motor commands. No Kalman filters. No computer vision feature detectors. Just neurons flying the drone. The challenge is extreme. These drones fly at high speeds and need split-second decisions with minimal onboard resources: a single rolling-shutter camera and an IMU. Their approach is called SkyDreamer, based on the Dreamer-v3 reinforcement learning algorithm. First, a world model is trained in simulation. Then, the neural network learns how to fly in its dreams through reinforcement learning. The network's internal state can be read out to see where it thinks it is on the track or how fast it's going. Even better, the drone estimates some of its own body characteristics during flight, like the camera angle relative to the body, eliminating time-consuming manual calibration. The system uses only a single camera and the gyros from the IMU, ignoring the accelerometers, just like human FPV pilots do. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

206,924 просмотров • 4 месяцев назад

Elon Musk on MACROHARD: "I'd be surprised if by end of this year, the digital human emulation has not been solved. That's what we mean by like, the sort of MACROHARD project is, can you do anything that a human with access to a computer could do? That's the best you can do before you have a physical Optimus, the best you can do is a digital Optimus."
1:54

Elon Musk on MACROHARD: "I'd be surprised if by end of this year, the digital human emulation has not been solved. That's what we mean by like, the sort of MACROHARD project is, can you do anything that a human with access to a computer could do? That's the best you can do before you have a physical Optimus, the best you can do is a digital Optimus."

DogeDesigner

90,940 просмотров • 4 месяцев назад