Tesla robots work in factories, Musk: The degree of freedom of hands will reach 22 this year!

Tesla RobotOptimusThe latest video is released, and it can already work in the factory.

At normal speed, it sorts batteries (Tesla’s 4680 battery) like this:

The official also released the video at 20x speed - picking and picking and picking at the small "work station":

The video released this time One of the highlights is that Optimus completes this work in the factory, completely autonomously, without human intervention throughout the process. And from the perspective of Optimus, it can also pick up and place the crooked battery, featuring an

automatic error correction

:

Regarding Optimus’s hand

, Nvidia scientist

Jim Fan gave a high evaluation:

Optimus’s hand is the most dexterous among the five-fingered robots in the world. one.

Not only does its hand have tactile sensing, but it also has 11 degrees of freedom

(DoF)

, while its peers basically only have 5-6 degrees of freedom. And is durable enough to withstand a lot of object interaction without constant maintenance.

And in Jim Fan’s comment area,

Musk

also appeared and revealed a more important news:

Later this year At that time, the

Optimus hand's degree of freedom will reach 22

!

However, the video showing Optimus sorting its own batteries is just an "appetizer".

This time, Tesla rarely announced the details of robot training.

Similar logic to Tesla cars

First of all, in terms of neural networks, we can know from the subtitles in the video that Tesla deployed a

end-to-end End-to-end neural network

is used to train the task of sorting batteries. Because of this, the data used by Optimus only comes from the 2D camera and the tactile and force sensors of the hand, and directly generates joint control sequences.

Tesla engineer

Milan Kovac

further revealed that this neural network runs entirely on the robot’s embedded FSD computer and is powered by an onboard battery. Powered by:

A single neural network can perform multiple tasks as we add more diverse data during training.

In terms of training data, we can see that humans wear VR glasses and gloves and collect it through remote operation:

Regarding this point, Jim Fan believes:

It is very important to set up the software for first-person video streaming input and precise control of the streaming output while maintaining extremely low latency.

This is because humans are very sensitive to even the smallest delay between their own movements and those of the robot.

And Optimus happens to have a fluid full-body controller that can perform human poses in real time.

And Tesla Robot has extended this model to other tasks:

Such a scale is also what shocked Jim Fan:

To collect data in parallel, one robot is not enough, and humans have to work in shifts every day.

An operation of this scale may be unimaginable in an academic laboratory.

Not only that, judging from the tasks Optimus are performing in the video, they are also diverse, including sorting batteries, folding clothes, and organizing items.

Milan Kovac said Tesla has deployed several robots in one of its factories, and they are being tested and continuously improved at real workstations every day.

# In short, Optimus trains based solely on vision and human demonstration, which is somewhat similar to the logic of Tesla cars.

At the end of the video, the official also revealed another improvement in Optimus' abilities - can go further:

One More Thing

Jim Fan's laboratory has also released a new development in the past two days-

Let the robot dog walk on the yoga ball!

Its training method is completely different from Tesla Optimus. It is completely conducted in a simulation environment, and then migrated to the real world with zero samples, without fine-tuning, and runs directly .

The specific technology behind it is the team’s newly launched DrEureka, which is based on Eureka, the technology behind the previous five-finger robot pen-turning machine.

DrEureka is an LLM agent that can write code to train robots’ skills in simulations and write more code to bridge the difficult gap between simulations and reality.

In short, it completely automates the process from new skill learning to real-world deployment.

## Compared with the training methods of Tesla Optimus and NVIDIA robot dogs, Jim Fan also made a soul summary:

Remote Operation is a necessary but not sufficient condition for solving humanoid robot problems. Fundamentally, it doesn't scale.

And some netizens agreed with this:

So what do you think?

The above is the detailed content of Tesla robots work in factories, Musk: The degree of freedom of hands will reach 22 this year!. For more information, please follow other related articles on the PHP Chinese website!