Загрузка видео...

Не удалось загрузить видео

На главную

Genesis's generative framework supports generating 3D and fully interactive scenes for training robotic skills 5/n

63,536 просмотров • 1 год назад •via X (Twitter)

Комментарии: 14

Фото профиля Zhou Xian
Zhou Xian1 год назад

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

Фото профиля Zhou Xian
Zhou Xian1 год назад

Nvidia brought GPU acceleration to robotic simulation, speeding up simulation speed by more than one order of magnitude compared to CPU-based simulation. This brought numerous amazing robotic skills to life by leveraging large-scale GPU-parallelized simulation. Genesis pushes up this speed by another order of magnitude. Note that the speed improvement is achieved with no compromise in simulation accuracy. 2/n

Фото профиля Zhou Xian
Zhou Xian1 год назад

Genesis supports simulating various types of physical phenomena. We developed from scratch a unified physics engine that integrates various SOTA physics solvers (MPM, SPH, FEM, Rigid Body, PBD, etc.), supporting simulation of a wide range of materials: rigid body, articulated body, Cloth, Liquid, Smoke, Deformables, Thin-shell materials, Elastic/Plastic Body, Robot Muscles, etc. 3/n

Фото профиля Zhou Xian
Zhou Xian1 год назад

Genesis is the first-ever platform providing comprehensive support for soft muscles and soft robot and their interaction with rigid robots. Genesis also ships with a URDF-like soft-robot configuration system. 4/n

Фото профиля Zhou Xian
Zhou Xian1 год назад

Our generative agent autonomously proposes robotic tasks, design environments, write reward functions, and ultimately leading to automated generation of robotic policies. 6/n

Фото профиля Zhou Xian
Zhou Xian1 год назад

Genesis's generative framework supports data generation beyond robotics, such as character motion: 7/n

Фото профиля Zhou Xian
Zhou Xian1 год назад

Genesis's GPU parallellized IK solver is able to solve IK for 10,000 Franka arms simultaneously, under 2ms: 8/n

Фото профиля Zhou Xian
Zhou Xian1 год назад

We support native non-convex collision handling: 9/n

Фото профиля Zhou Xian
Zhou Xian1 год назад

Genesis supports a physically accurate tactile sensing simulation module: (Will be integrated into the main branch in a future release soon) 10/n

Фото профиля Zhou Xian
Zhou Xian1 год назад

Finally, a cute interactive physical Tetris game made with Genesis :) Thanks to all the amazing collaborators who together made everything possible over the last two years! There's no space here to @ every single one, but a huge kudos to the whole Genesis team! We welcome everyone from the open-source community to come join us and build Genesis with us together! 11/11

Фото профиля Digital Currency
Digital Currency2 лет назад

From 3D modeling to VR/AR development, our MSc in Metaverse program equips you with the technical skills to excel in the rapidly evolving digital world. Don't miss out—enroll today! #UNIC #MScMetaverse

Фото профиля Squaremusher
Squaremusher1 год назад

I’m confused, so does it create a 3d scene somewhere that we can access or does it just generate the end resulting 2d video? This is mind blowing either way.

Фото профиля Bill Harris
Bill Harris1 год назад

AttributeError: module 'genesis' has no attribute 'generate'

Фото профиля slimemax
slimemax1 год назад

Huh???

Похожие видео

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

3,814,717 просмотров • 1 год назад