正在加载视频...

视频加载失败

Nvidia's Jim Fan: We're training robots in a simulation that accelerates physics by 10,000x. The robots undergo 1 year of intense training in a virtual “dojo”, but take only ~50 minutes of wall clock time. Those who still remember Dragonball Z will recognize the room where a few minutes...

1,187,685 次观看 • 1 年前 •via X (Twitter)

11 条评论

Prinz Eugen, der edle Ritter 的头像
Prinz Eugen, der edle Ritter1 年前

Nvidia is a robotics company now. Few have noticed.

Chubby♨️ 的头像
Chubby♨️1 年前

Yes, they know how much of an important sector this

Page to Pixel Publishing 的头像
Page to Pixel Publishing2 年前

The Art of Flight is a homage to 80s/90s arcade action shmups with a fresh twist on the genre. Pilot multiple ships at the same time to take on oncoming waves of enemies in this fast paced space shooter. Wishlist on Steam today!

Emir Karabeg 🇧🇦 的头像
Emir Karabeg 🇧🇦1 年前

This is also how Naruto trains with shadow clones - each clone’s experience feeds back into his training

build things that build things 的头像
build things that build things1 年前

What this will accomplish at scale is insane

Doug 的头像
Doug1 年前

That's fine, but they will break when something goes wrong. Let's say I have one make me an omlet and think of everything that can go wrong - an egg is already cracked in the case, a piece of eggshell falls on the bowl, the gas stove won't light, etc. Those things will stop them dead.

Chubby♨️ 的头像
Chubby♨️1 年前

you really think that?

Sam Controlman 的头像
Sam Controlman1 年前

I wonder if they become conscious how would they sense time? It would be virtually eternity for them

Selim Candar 的头像
Selim Candar1 年前

Do they also use a transformer model to train robots for everyday tasks?

Harshit 的头像
Harshit1 年前

Hyperbolic Time Chamber 😍

LMT ⚡️ 的头像
LMT ⚡️1 年前

The first time I saw Unitree one-shot a robot dog - from walking on a ball in simulation - to doing it in real life, I immediately reconsidered my Tesla Optimus investment thesis.

相关视频

Elon just dropped a MAJOR nugget on how Tesla is going to be training Optimus to do real world tasks. They are building an Optimus Academy, which is a large scale, dedicated real-world training facility to accelerate the development of Optimus. The Academy will deploy thousands of Optimus units, potentially 10,000 to 30,000 robots, in a controlled realistic environment where they perform self-play, experiment with tasks, iterate on behaviors, and continuously generate training data through trial and error. The Tesla bots will also run millions of simulations in Tesla’s high-fidelity physics-accurate engine, allowing Optimus to close the “sim-to-real gap” by using these real-world observations to refine and validate the simulations! “You’re actually highlighting an important limitation and difference from cars. We’ll soon have 10 million cars on the road. It’s hard to duplicate that massive training flywheel. For the robot, what we’re going to need to do is build a lot of robots and put them in kind of an Optimus Academy so they can do self-play in reality. We’re actually building that out. We can have at least 10,000 Optimus robots, maybe 20-30,000, that are doing self-play and testing different tasks. Tesla has quite a good reality generator, a physics-accurate reality generator, that we made for the cars. We’ll do the same thing for the robots. We actually have done that for the robots. So you have a few tens of thousands of humanoid robots doing different tasks. You can do millions of simulated robots in the simulated world. You use the tens of thousands of robots in the real world to close the simulation to reality gap. Close the sim-to-real gap.”

Teslaconomics

42,563 次观看 • 7 个月前