正在加载视频...

视频加载失败

Do AI robots see the world like we do? I dove head first into latent space to uncover the attention maps that show how my robot sees and understands the world.

44,266 次观看 • 1 年前 •via X (Twitter)

11 条评论

Ville 🤖 的头像
Ville 🤖1 年前

Initially, the robot struggles to locate the capsule to pick, but gradually becomes more certain of the exact pick location. As the task succeeds for capsule 1, attention rapidly shifts to capsule 2 in the background

Ville 🤖 的头像
Ville 🤖1 年前

To me these attention maps prove that AI robot models like ACT make efficient use of the visual information they have access to. I also believe improvements in model performance should be directly visible as more focused attention maps

Ville 🤖 的头像
Ville 🤖1 年前

The algorithm behind this will be open-sourced and compatible with ACT policy in @LeRobotHF (probably this weekend) so stay tuned!

VistaShares 的头像
VistaShares1 年前

The global AI sector is evolving rapidly, supported by advancements in technology and infrastructure. AIS offers targeted exposure to key players driving these developments.

C Zhang 的头像
C Zhang1 年前

So such visual policies are like a neural state estimator plus a burnt-in tracker? 🤔

Dominique Paul 的头像
Dominique Paul1 年前

Man this is super cool!

Josh Ohara 的头像
Josh Ohara1 年前

That's super cool, is this just a reconstruction of the attention scores per pixel?

Ville 🤖 的头像
Ville 🤖1 年前

Yes though it’s not quite as simple as that, the transformer model compresses the image a lot, there’s some computer vision magic to upscale that compressed view into the full image you see here that I don’t fully understand 😅

Josh Ohara 的头像
Josh Ohara1 年前

Also, is your web app for lerobot open source? Looks really cool.

Ville 🤖 的头像
Ville 🤖1 年前

The app itself is not but the Python libraries that power it will be though it will take time for us to organise everything into a proper library

Tech Ren 的头像
Tech Ren1 年前

dinov2?

相关视频