Yiling Qiao

11/11 Today, we are more convinced than ever: human-level manipulation is no longer a question of if. It's a question of how fast we get there. We are approaching the endgame for robotics. Read more about GEN-26.5 in our technical blog post: genesis.ai/blog/gene-26-5…

10/ Even Rush E :)

9/ And plays piano.

8/ Does wire harnessing.

7/ Grasps multiple objects with different ways, all at once with a single hand.

6/ Handles a delicate straw.

5/ Makes a smoothie.

4/ Rubik’s Cube solving has been a long-standing challenging benchmark for robotic manipulation. The task requires fine-grained control under the geometric and kinematic constraints imposed by the cube itself. Prior state-of-the-art is still the single-handed solver from OpenAI’ in 2019. For the first time, we can solve a Rubik's Cube using two hands together, powered by GENE.

3/ Carries laboratory experiment with mm-level precision and complex tool usage.

2/ GENE-26.5 cooks in an unsimplified, real-world setting with more than 20 subtasks.

So lucky to live in this era, working on the most exciting problem with the best people at the best place: Genesis. It feels amazing that the ambitious plans can be achieved by having conviction, working the full stack from the lowest level up, and carefully getting every seemingly small detail right. Robotics is a long-term and systematic problem. This is a great milestone where every piece comes together, and we're just getting started. More to come!

We are back. After one year of quiet building. Introducing GENE-26.5, our first robotic brain that takes a major step toward human-level capability. For years, robotics has struggled to learn from the world’s largest and valuable data source: Humans. Solving it means rethinking the whole stack from the ground up: - A robotics-native foundation model. - A 1:1 human-like robotic hand. - A noninvasive data collection glove for motion, force, and touch. - A simulator that turns weeks of experiments into minutes. GENE-26.5 is trained across language, vision, proprioception, tactile, and action. We designed a set of tasks to test how far we can go with this new paradigm. Fully autonomous, 1x speed, one model, same weights. (Enjoy with sound on) We are approaching the endgame for robotics. And this is just a beginning.

Today, We’re launching Genesis AI — a global physical AI lab and full-stack robotics company — to build generalist robots and unlock unlimited physical labor. We’re backed by $105M in seed funding from @EclipseVentures, @khoslaventures, @Bpifrance, HSG, and visionaries including @ericschmidt and @Xavier75 . General-purpose robots will be the next chapter in human history. Half of global GDP is physical. Less than 5% is automated. Today’s robots are too narrow, rigid, and expensive to scale. We need a new generation of adaptable, foundation-model-driven systems. We are a new generation of robotics builders, united by a shared mission to push the boundaries of physical AI. Our team brings together the minds behind many recent key advances spanning robotics, imitation learning, RL, simulation, GPU compilers, and foundation models — bridging historically siloed communities. We co-created UMI and Diffusion Policy, pioneered RL for superhuman drone racing, and scaled robotic data pipelines at NVIDIA GR00T. We introduced the paradigm of generative simulation, built Genesis, Jiminy, Flightmare, and GVBD Voxels, and invented the IPC algorithm. We built cross-platform GPU compilers VeriGPU, DeepCL, Coriander, and the original PyTorch, and industry-leading rendering engines at Epic, Unity, and Google. We also spearheaded the first multimodal foundation models at Mistral AI and Apple Intelligence. Now, we’ve come together at Genesis AI to close the loop, and build what’s next. Join us → genesis-ai.company/join-us

We’re excited to share some updates on Genesis since its release: 1. We made a detailed report on benchmarking Genesis's speed and its comparison with other simulators (github.com/zhouxian/genes…) 2. We’ve launched a Discord channel and a WeChat group to foster communications between users and contributors 3. We released Genesis 0.2.1 today with new features including faster cached kernel loading, docker file support, smoke simulation, RL training example for drones, multilingual documentation support, together with various new APIs. A heartfelt thank you to the open-source community for contributing to this collaborative effort!

@Stone_Tao Thanks for trying out our code and providing feedback! I'm looking into this issue.

I am guessing this will be fixed, but for now it is incorrect to say this is faster than other simulators. It's just faster when it comes to locomotion. I will likely post a proper benchmark report next week and share thoughts on what differs from framework to framework

so far Genesis is the one of the most feature rich simulators out there, combining many many things and makes for a great general data gen platform. Unfortunately it's still some distance away from supporting fast & stable simulation for most things, including basic manipulation

@deedzgao haha, thank you, Alexander!

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: genesis-world.readthedocs.io/en/latest/user…). The Genesis physics engine and simulation platform is fully open source at github.com/Genesis-Embodi…. 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: github.com/Genesis-Embodi… Project webpage: genesis-embodied-ai.github.io Documentation: genesis-world.readthedocs.io 1/n

Can GPTs generate infinite and diverse data for robotics? Introducing RoboGen, a generative robotic agent that keeps proposing new tasks, creating corresponding environments and acquiring novel skills autonomously! code: github.com/Genesis-Embodi… 👇🧵 (better with audio)

Submissions of 4 to 8 pages, including extended abstracts, short papers, and long papers, are all welcomed. We will have both oral and poster presentations. Submit at: openreview.net/group?id=robot…… Submission deadline: 2023/10/06 Notification of acceptance: 2023/10/16

Welcome to our CoRL2023 workshop! We invite you to share your latest research and ideas in the fields of LLM, Autonomous Agents, Robotics, and more! Homepage: generalist-robots.github.io