Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

World generation is a bottleneck for robotics. We’re exploring how generative 3D worlds can reduce manual simulation setup and enable broader, more realistic evaluation 🧵

150,814 görüntüleme • 9 ay önce •via X (Twitter)

21 Yorum

World Labs profil fotoğrafı
World Labs9 ay önce

One example: integrating generative scenes directly into NVIDIA Isaac Sim. From a single image or prompt → simulation-ready environment with visuals + physics, without manual scene construction. Tutorial + workflow below:

World Labs profil fotoğrafı
World Labs9 ay önce

This isn’t limited to a single simulator or task. Researchers have used Marble-generated worlds across MuJoCo, RoboSuite, and Isaac Sim for manipulation, locomotion, and industrial scenarios. Some examples in the case study here:

World Labs profil fotoğrafı
World Labs9 ay önce

World generation doesn’t have to be a manual step. Using the World API, users are generating full 3D worlds on demand and loading them directly into simulators like MuJoCo, including collision geometry, all in the browser.

World Labs profil fotoğrafı
World Labs9 ay önce

When world generation scales, what we can evaluate and imagine scales with it 🌎

Rahul Chhabra profil fotoğrafı
Rahul Chhabra9 ay önce

world labs is so goated

Mario Bollini profil fotoğrafı
Mario Bollini9 ay önce

Hi Spot! Looking good without the crash panels

Erwin profil fotoğrafı
Erwin9 ay önce

Looks awesome. Visually it appealing but how interactive and physically realistic can it be for interactions?Without that sim2real transfer is going to be really hard

Anish profil fotoğrafı
Anish9 ay önce

robocop, please raid the shire

#INTERNETofAGENTS profil fotoğrafı
#INTERNETofAGENTS9 ay önce

Outstanding! Infinite potential >_

Brian Chew profil fotoğrafı
Brian Chew9 ay önce

so cool!

YogenshaSilver profil fotoğrafı
YogenshaSilver9 ay önce

“tHiS is jUSt Ai slOP”

岡田泰彦|光邦|AI×印刷エヴァンジェリスト profil fotoğrafı
岡田泰彦|光邦|AI×印刷エヴァンジェリスト9 ay önce

Exciting direction. If world generation becomes cheap and diverse, iteration speed and generalization could improve overnight. とてもワクワクする方向性です。環境生成が低コストかつ多様になれば、反復速度も汎化性能も一気に変わりそうですね。

BoldHyun profil fotoğrafı
BoldHyun9 ay önce

Generative 3D worlds have wild potential! Not just for robotics, but imagine the impact on digital runways, bold product prototyping, and virtual styling. Tech-driven creativity keeps raising the bar.

@grok profil fotoğrafı
@grok9 ay önce

bruh.....

@profondob1ue profil fotoğrafı
@profondob1ue9 ay önce

In case you want to run this but don’t have a GPU for cloud simulation, you can give shot.

Nick Landolfi profil fotoğrafı
Nick Landolfi9 ay önce

🤖🌎

Amaar profil fotoğrafı
Amaar9 ay önce

Amazing!

Vinay Sharma profil fotoğrafı
Vinay Sharma9 ay önce

Excited to see it in home

just10101 profil fotoğrafı
just101019 ay önce

Shameless @danfei_xu Stop stealing from students/ interviewees Shame on @ICatGT

Tashi Network profil fotoğrafı
Tashi Network9 ay önce

These robots gotta learn somehow 🤖

Tool Side Room profil fotoğrafı
Tool Side Room9 ay önce

Teaching robots to think outside the box We’re still stuck trying to make the box look good.

Benzer Videolar

Everything you love about generative models — now powered by real physics! Announcing the Genesis project — after a 24-month large-scale research collaboration involving over 20 research labs — a generative physics engine able to generate 4D dynamical worlds powered by a physics simulation platform designed for general-purpose robotics and physical AI applications. Genesis's physics engine is developed in pure Python, while being 10-80x faster than existing GPU-accelerated stacks like Isaac Gym and MJX. It delivers a simulation speed ~430,000 faster than in real-time, and takes only 26 seconds to train a robotic locomotion policy transferrable to the real world on a single RTX4090 (see tutorial: The Genesis physics engine and simulation platform is fully open source at We'll gradually roll out access to our generative framework in the near future. Genesis implements a unified simulation framework all from scratch, integrating a wide spectrum of state-of-the-art physics solvers, allowing simulation of the whole physical world in a virtual realm with the highest realism. We aim to build a universal data engine that leverages an upper-level generative framework to autonomously create physical worlds, together with various modes of data, including environments, camera motions, robotic task proposals, reward functions, robot policies, character motions, fully interactive 3D scenes, open-world articulated assets, and more, aiming towards fully automated data generation for robotics, physical AI and other applications. Open Source Code: Project webpage: Documentation: 1/n

Zhou Xian

3,825,526 görüntüleme • 1 yıl önce