Загрузка видео...

Не удалось загрузить видео

На главную

We are back again :) After three weeks of quiet building. Introducing Genesis World 1.0, our latest simulation platform, the second release in our full-stack suite. Open-sourced. Robotics is still bottlenecked by the 1× speed of the physical world. Every model, checkpoint, and data recipe eventually needs to be...

320,116 просмотров • 4 месяцев назад •via X (Twitter)

Комментарии: 65

Фото профиля Genesis AI
Genesis AI4 месяцев назад

If you are interested in learning more about Genesis World, and our thoughts on the role of simulation for robotics research going forward, see our technical blog post:

Фото профиля Jie Wang
Jie Wang4 месяцев назад

very impressive! I like how the Yo-yo get simulated here

Фото профиля Genesis AI
Genesis AI4 месяцев назад

Thank you @JieWang_ZJUI! 🪀

Фото профиля Nikolaus West
Nikolaus West4 месяцев назад

Congrats, this looks amazing! Was having a conversation with folks from a bunch of great robotics companies last week and the consensus after the last Genesis release was that sim for manipulation was dead. If even the top sim-team had moved away from it, what hope is there? What a short lived conclusion!

Фото профиля Genesis AI
Genesis AI4 месяцев назад

♥️ Glad to push the robotics space forward!

Фото профиля Jiafei Duan
Jiafei Duan4 месяцев назад

Really great job! Loving it

Фото профиля Genesis AI
Genesis AI4 месяцев назад

Thank you @DJiafei!

Фото профиля Animesh Garg
Animesh Garg4 месяцев назад

very well done! Congrats to the team for building so many sim features.

Фото профиля Genesis AI
Genesis AI4 месяцев назад

Thank you @animesh_garg! Excited for the community to try them out!

Фото профиля Caitlin Kalinowski
Caitlin Kalinowski4 месяцев назад

Exciting progress!

Фото профиля Genesis AI
Genesis AI4 месяцев назад

Thanks Caitlin!

Фото профиля Utkarsh Singh
Utkarsh Singh4 месяцев назад

open-sourcing is a smart move. let the community run with it.

Фото профиля Genesis AI
Genesis AI4 месяцев назад

We agree 💯

Фото профиля Jie Wang
Jie Wang4 месяцев назад

looks like a typo here?

Фото профиля Genesis AI
Genesis AI4 месяцев назад

Thank you for noticing this! fixing it

Фото профиля Uğur Yekta Başak
Uğur Yekta Başak4 месяцев назад

many companies will need it. they just don’t know it yet. congrats again for the launch!

Фото профиля Genesis AI
Genesis AI4 месяцев назад

Thank you @uguryektabasak!

Фото профиля kvick
kvick4 месяцев назад

I love Elastoplastic thin shell manipulation, i do it every day

Фото профиля Astrelle Capital
Astrelle Capital4 месяцев назад

Robotics simulation getting that much faster is the kind of compounding progress we track.

Фото профиля Genesis AI
Genesis AI4 месяцев назад

Totally!

Фото профиля Seth Winterroth 🤖
Seth Winterroth 🤖4 месяцев назад

the execution from this team is unprecedented

Фото профиля Genesis AI
Genesis AI4 месяцев назад

Thanks Seth for your continuous support!

Фото профиля Zhi (Leo) Wang
Zhi (Leo) Wang4 месяцев назад

Congrats! Great work!

Фото профиля Genesis AI
Genesis AI4 месяцев назад

Thank you for checking us out @TX_Leo_Wang!

Фото профиля Roozbeh Mottaghi
Roozbeh Mottaghi4 месяцев назад

Keep up the good work. Great move to open source it. Would love to see more profiling for contact rich manipulation.

Фото профиля Genesis AI
Genesis AI4 месяцев назад

Thanks Roozbeh!

Фото профиля eric gervet
eric gervet4 месяцев назад

Keep up the amazing breakthroughs @gs_ai_ 🙌😊

Фото профиля Genesis AI
Genesis AI4 месяцев назад

Thanks Eric!

Фото профиля مازن وذكاء الآلات
مازن وذكاء الآلات4 месяцев назад

It’s all about scale now, for robotics too! I think this is exactly the right direction: turn the wall-clock bottleneck into a compute problem, while shrinking the sim-to-real gap.

Фото профиля Genesis AI
Genesis AI4 месяцев назад

Totally!

Фото профиля مازن وذكاء الآلات
مازن وذكاء الآلات4 месяцев назад

I think this is a big deal. Robotics has been bottlenecked by wall clock time for too long. Turning iteration into a compute problem is the game.

Фото профиля Benjamin
Benjamin4 месяцев назад

Unfathomably incredible.

Фото профиля Genesis AI
Genesis AI4 месяцев назад

Thanks Benjamin!

Фото профиля Sanskar Pandey
Sanskar Pandey4 месяцев назад

Great lab!

Фото профиля Genesis AI
Genesis AI4 месяцев назад

Thanks for your support!

Фото профиля Xiaoyang Lyu
Xiaoyang Lyu4 месяцев назад

Congrats! The simulation lives again!

Фото профиля Genesis AI
Genesis AI4 месяцев назад

♥️

Фото профиля AI Mastery Guide
AI Mastery Guide4 месяцев назад

One hour in reality becoming 100 days in simulation is the sentence that changes how you think about robotics entirely

Фото профиля Genesis AI
Genesis AI4 месяцев назад

💯

Фото профиля AI Mastery Guide
AI Mastery Guide4 месяцев назад

nice

Фото профиля paras
paras4 месяцев назад

congrats on launch! excited to try :)

Фото профиля Genesis AI
Genesis AI4 месяцев назад

Can't wait to see what you build with it :)

Фото профиля Krish Mehta
Krish Mehta4 месяцев назад

Crushing it

Фото профиля Genesis AI
Genesis AI4 месяцев назад

♥️

Фото профиля Gabriel Noya
Gabriel Noya4 месяцев назад

Very cool

Фото профиля Genesis AI
Genesis AI4 месяцев назад

Thank you @gabrielnoya7!

Фото профиля Kevin Peterson
Kevin Peterson4 месяцев назад

Incredible work!

Фото профиля Marlon
Marlon4 месяцев назад

Just in time for some new projects I have cooking

Фото профиля Genesis AI
Genesis AI4 месяцев назад

🔥🔥🔥

Фото профиля Kingston Kuan
Kingston Kuan4 месяцев назад

that yo-yo simulation is insane

Фото профиля Genesis AI
Genesis AI4 месяцев назад

Thanks for checking us out! 🪀🪀🪀

Фото профиля Kingston Kuan
Kingston Kuan4 месяцев назад

would be interested in modeling ethernet cables for our datacenter simulations

Фото профиля Di Huang
Di Huang4 месяцев назад

Great work for the whole community!

Фото профиля Genesis AI
Genesis AI4 месяцев назад

Thank you @huangDi6! We are excited for the community to try them out!

Фото профиля Vector Wang
Vector Wang4 месяцев назад

Really cool work! Can wait to experience it. Great contribution to the field.

Фото профиля Genesis AI
Genesis AI4 месяцев назад

Thanks Vector! Can't wait for the community to try it out!

Фото профиля Jai
Jai4 месяцев назад

Anyone who has worked with Gazebo will probably vouch for how insanely impressive this is

Фото профиля Genesis AI
Genesis AI4 месяцев назад

Appreciate it Jai!

Фото профиля alby13
alby134 месяцев назад

this overall looks very impressive

Фото профиля g
g4 месяцев назад

Woah cool

Фото профиля Zaky Vids
Zaky Vids4 месяцев назад

@gs_ai_ This is incredible However, heavy local VRAM /storage limits lock out a considerable segment of population I was thinking about WebGPU/WASM via the Quadrants compiler which could likely enable Local-first, browser-based sandboxes allowing anyone to test instantly

Фото профиля BenUsesAI
BenUsesAI4 месяцев назад

finally a sim stack that actually cuts the bottleneck instead of adding more tools. this is the one ai to rule all robotics workflows

Фото профиля Genesis AI
Genesis AI4 месяцев назад

@BenUsesAI1 🦾

Фото профиля Ze YUAN
Ze YUAN4 месяцев назад

Thank you for open-sourcing Genesis World 1.0! 🙌 This is huge for the community — the performance and physics improvements look outstanding. Excited to try it out!

Фото профиля Genesis AI
Genesis AI4 месяцев назад

@ZeYUAN324134 💯💯💯 Excited for you to try it out!

Похожие видео

That's sick! 🤯 Genesis AI simulates robots playing yo-yo! 🪀 Genesis AI just open-sourced Genesis World 1.0, and it might be one of the most important infrastructure releases in robotics this year. Robotics is still bottlenecked by the 1× speed of the physical world. Every model needs to be tested on real hardware, slowly, expensively, with limited coverage. Genesis World 1.0 from Genesis AI flips that equation: One hour in reality becomes 100 days in simulation. That turns a wall-clock bottleneck into a compute problem. And compute problems are solvable. The technical stack they rebuilt from scratch is serious: → GPU-accelerated cross-platform compiler via Quadrants, 10x faster launch time and up to 4.6x runtime vs the initial Genesis release → Penetration-free multi-physics contact solvers, the thing that makes simulation actually trustworthy → Unified rigid AND deformable physics in a single engine → Nyx, a high-performance path-traced rendering engine purpose-built for physical AI The sim-to-real gap has historically been the graveyard of robotics research. Policies that work beautifully in simulation fall apart on real hardware. Genesis World 1.0 is a direct attack on that problem. And it's fully open-source. The companies that master simulation infrastructure will train better robots faster than anyone else. Find it here: Genesis World 1.0: Quadrants: Nyx: Theophile Gervet, Zhou Xian congrats! 👏🏼 ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

57,061 просмотров • 4 месяцев назад

Robotics has a massive, silent bottleneck. It isn’t just data collection—it’s the brutal 1x speed of the physical world. Genesis AI Genesis AI just unveiled Genesis World 1.0, and they are attempting to turn the notorious Sim2Real gap into a pure compute problem. Evaluating a robotics foundation model across edge cases usually means hundreds of hours of physical lab testing. With Genesis World 1.0, what traditionally takes nearly a week of continuous, real-world operation is being compressed into 30 minutes in simulation. What makes this different from just dropping a robot model into an off-the-shelf game engine? 1️⃣ Nyx Renderer: A custom, real-time path-traced engine rendering noise-free 1080p frames in under 4ms. Game engines use rasterization tricks that confuse AI; Nyx uses physically accurate multi-bounce lighting so the model's "eyes" see exactly what real sensors see. 2️⃣ Quadrants Compiler: A custom Python-to-GPU compiler to run heavily parallelized multi-physics simulations (rigid bodies, fluids, deformables) natively across architectures. 3️⃣ Evaluation First: They aren't rushing to train on synthetic data. They are using this purely for closed-loop evaluation to perfect the physics first, currently claiming an impressive 89% correlation with real-world hardware tests. If the industry can accurately evaluate models in simulation without the physical world bottleneck, humanoid development stops moving at wall-clock time and starts scaling with compute.

Humanoids daily

17,302 просмотров • 4 месяцев 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

Zhou Xian

3,822,134 просмотров • 1 год назад

Exciting updates on Project GR00T! We discover a systematic way to scale up robot data, tackling the most painful pain point in robotics. The idea is simple: human collects demonstration on a real robot, and we multiply that data 1000x or more in simulation. Let’s break it down: 1. We use Apple Vision Pro (yes!!) to give the human operator first person control of the humanoid. Vision Pro parses human hand pose and retargets the motion to the robot hand, all in real time. From the human’s point of view, they are immersed in another body like the Avatar. Teleoperation is slow and time-consuming, but we can afford to collect a small amount of data. 2. We use RoboCasa, a generative simulation framework, to multiply the demonstration data by varying the visual appearance and layout of the environment. In Jensen’s keynote video below, the humanoid is now placing the cup in hundreds of kitchens with a huge diversity of textures, furniture, and object placement. We only have 1 physical kitchen at the GEAR Lab in NVIDIA HQ, but we can conjure up infinite ones in simulation. 3. Finally, we apply MimicGen, a technique to multiply the above data even more by varying the *motion* of the robot. MimicGen generates vast number of new action trajectories based on the original human data, and filters out failed ones (e.g. those that drop the cup) to form a much larger dataset. To sum up, given 1 human trajectory with Vision Pro -> RoboCasa produces N (varying visuals) -> MimicGen further augments to NxM (varying motions). This is the way to trade compute for expensive human data by GPU-accelerated simulation. A while ago, I mentioned that teleoperation is fundamentally not scalable, because we are always limited by 24 hrs/robot/day in the world of atoms. Our new GR00T synthetic data pipeline breaks this barrier in the world of bits. Scaling has been so much fun for LLMs, and it's finally our turn to have fun in robotics! We are building tools to enable everyone in the ecosystem to scale up with us. Links in thread:

Jim Fan

364,670 просмотров • 2 лет назад

Karol Hausman is the co-founder and CEO of Physical Intelligence, a robotics company building a general-purpose “AI brain for the physical world.” The company has raised more than $1 billion in funding to develop foundation models that allow robots to operate across many machines, environments, and tasks rather than being programmed for a single purpose. In our conversation, we explore: • The moment a lecture from Sergey Levine convinced him to abandon his PhD research direction and pivot fully to deep learning • The case for building a general “AI brain” for the physical world rather than a single specialized robot • The role of real-world data in training robots, the limits of simulation, and how deployment could create a powerful data flywheel • The unique challenges of physical intelligence and why robots must operate with far higher reliability than language models Thank you to the partners who make this possible - Brex: The intelligent finance platform: - Granola: The app that might actually make you love meetings: Timestamps (00:00) Intro (04:05) Karol’s early fascination with robots (18:21) Karol’s entry point to robotics and PhD program (25:49) Combining robotics with LLMs: The Taylor Swift demo (30:48) The 1970s SHRDLU AI experiment (39:40) How research shapes what Physical Intelligence builds (49:07) The return of reinforcement learning in robotics (1:00:00) NVIDIA’s simulation engines (1:07:31) Compensating for missing senses

Mario Gabriele 🦊

27,871 просмотров • 6 месяцев назад

Excited to announce GR00T N1, the world’s first open foundation model for humanoid robots! We are on a mission to democratize Physical AI. The power of general robot brain, in the palm of your hand - with only 2B parameters, N1 learns from the most diverse physical action dataset ever compiled and punches above its weight: - Real humanoid teleoperation data. - Large-scale simulation data: we are open-sourcing 300K+ trajectories! - Neural trajectories: we apply SOTA video generation models to “hallucinate” new synthetic data that features accurate physics in pixels. Using Jensen’s words, “systematically infinite data”! - Latent actions: we develop novel algorithms to extract action tokens from in-the-wild human videos and neural generated videos. GR00T N1 is a single end-to-end neural net, from photons to actions: - Vision-Language Model (System 2) that interprets the physical world through vision and language instructions, enabling robots to reason about their environment and instructions, and plan the right actions. - Diffusion Transformer (System 1) that “renders” smooth and precise motor actions at 120 Hz, executing the latent plan made by System 2. We deploy N1 on GR1 robot, 1X Neo robot, and a large collection of simulation benchmarks. N1 achieves up to +30% boost in diverse manipulation tasks for household and industrial settings. While humanoid robots are the main focus of N1, our model also supports cross-embodiment. We finetune it to work on the $110 HuggingFace LeRobot SO100 robot arm! Open robot brain runs on open hardware. Sounds just right. Let’s solve robotics, together, one token at a time. Links to our Whitepaper, Github repo, HuggingFace model, and open dataset page in the thread: 🧵

Jim Fan

467,395 просмотров • 1 год назад

We trained a robot dog to balance and walk on top of a yoga ball purely in simulation, and then transfer zero-shot to the real world. No fine-tuning. Just works. I’m excited to announce DrEureka, an LLM agent that writes code to train robot skills in simulation, and writes more code to bridge the difficult simulation-reality gap. It fully automates the pipeline from new skill learning to real-world deployment. The Yoga ball task is particularly hard because it is not possible to accurately simulate the bouncy ball surface. Yet DrEureka has no trouble searching over a vast space of sim-to-real configurations, and enables the dog to steer the ball on various terrains, even walking sideways! Traditionally, the sim-to-real transfer is achieved by domain randomization, a tedious process that requires expert human roboticists to stare at every parameter and adjust by hand. Frontier LLMs like GPT-4 have tons of built-in physical intuition for friction, damping, stiffness, gravity, etc. We are (mildly) surprised to find that DrEureka can tune these parameters competently and explain its reasoning well. DrEureka builds on our prior work Eureka, the algorithm that teaches a 5-finger robot hand to do pen spinning. It takes one step further on our quest to automate the entire robot learning pipeline by an AI agent system. One model that outputs strings will supervise another model that outputs torque control. We open-source everything! Welcome you all to check out the paper, more videos, and try the codebase today: Code:

Jim Fan

909,210 просмотров • 2 лет назад

🚨 BREAKING: ABB Robotics + NVIDIA close the sim-to-real gap with 99% accuracy! 👾 ABB Robotics is integrating NVIDIA Omniverse libraries into RobotStudio to deliver physical AI for industry, closing the gap from virtual training to real-world deployment with up to 99% accuracy. RobotStudio HyperReality, available second half of 2026, will fundamentally change how quickly manufacturers can scale production: reducing costs by up to 40%, accelerating time-to-market by 50%, and cutting setup and commissioning times by up to 80%. For decades, the deficit between simulation accuracy and real-world lighting, materials, and environments has limited manufacturers' ability to design advanced manufacturing processes in the virtual world. The only robot manufacturer with a virtual controller running the same firmware as the hardware, ensuring near-perfect correlation between simulation and real-world performance. The system uses physically accurate simulations and foundation models endlessly optimized with real-world data feedback. These models can train any number of ABB robots anywhere in the world with industrial-grade reliability. Foxconn is using RobotStudio HyperReality for consumer electronics assembly. Assembly robots are trained virtually using synthetic data to perfect multiple production processes across various scenarios, then moved to production lines with 99% accuracy. This eliminates physical training and tests, reducing setup times and costs. Workr is demonstrating AI-powered robotic systems at NVIDIA GTC 2026. Built on ABB technology, trained with synthetic data using NVIDIA Omniverse, deployed without operators needing programming knowledge . 🚨 I’ll be onsite in San Jose during GTC 2026, and will be showing all the cool stuff that ABB Robotics prepared this year! Can’t wait! 🫡 ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

22,482 просмотров • 6 месяцев назад