🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

We open sourced the URDF and MJCF importer extensions for NVIDIA Omniverse Isaac Sim: discourse.ros.org/t/open-sourcin… It lets developers improve the import of URDF (from Open Robotics) and MJCF (for Google DeepMind MuJoCo) and also serves as an example of writing your own extensions.

1. Legged systems have traditionally been controlled using trajectory optimization (TO). Such hierarchical model-based methods offer intuitive cost function tuning, accurate planning, and generalization. However, violations of modeling assumptions are common sources of failure.

Some fine educational material and useful, fun-to-read code to satisfy your nonlinear least-squares needs. Check out the new tutorial colab from the MuJoCo team github.com/google-deepmin… Channeling my inner Russ Tedrake 🧑‍🏫

Our collaboration with Google DeepMind has borne fruit! Or rather, a fruit fly 🪰🙂 Simulated with #MuJoCo physics, trained with imitation learning, capable of realistic locomotion, both on the ground and in the air. 1/n biorxiv.org/content/10.110… github.com/TuragaLab/flyb…

New research from Google DeepMind brings together soccer and robotics. Using reinforcement learning, robots display agile and reactive movements similar to a soccer player, no shin guards needed:) science.org/doi/10.1126/sc…

Easily replicate elements in MuJoCo models. The scene files in the video are both short and readable. Three Bowls: 45 lines. Newton's cradle: 70 lines. Stonehenge: 40 lines. youtu.be/5k0_wsIRAFc?si…

Simple Predictive Sampling solves bimanual manipulation tasks in near real time. Pretty neat, no? youtu.be/aCNCKVThKIE?si…

Check out the colab colab.research.google.com/github/google-…

Great new video tutorial for "simulate", MuJoCo's built-in interactive visualizer: youtube.com/watch?v=P83tKA… Credit: The patient M. Hamid 👏

Differential inverse kinematics controller on a Go1 quadruped regulating the pose of the root body and the position of the feet.

Just finished implementing collision avoidance in the diff IK solver as extra constraints in the QP. Really happy with the final result 😀

Safe bimanual control on ALOHA, powered by mink. Here I'm specifying collision avoidance between 1) left and right arm, 2) each arm and the 80/20 extrusions and 3) each arm and the table. (yes laptop hiccuped a bit due to the sheer amount of collision computation, but I can

We Google DeepMind simply couldn't have achieved this breakthrough without the powerful #MuJoCo simulation engine. Its flexibility, ease of use, and advanced modeling capabilities were absolutely critical to our research velocity. 🚀 #AI #Robotics #TableTennis

Really excited to see how far we can push GPU-accelerated manipulation in MuJoCo!

We have some extremely exciting MuJoCo/MJX release coming soon, can't wait to share :)

The ultimate test of any physics simulator is its ability to deliver real-world results. With MuJoCo Playground, we’ve combined the very best: MuJoCo’s rich and thriving ecosystem, massively parallel GPU-accelerated simulation, and real-world results across a diverse range of

📣MuJoCo announcement 📣 Thrilled to share that Google DeepMind has unveiled MuJoCo-Warp at NVIDIA's #GTC25! 🚀 We've expanded our open-source MuJoCo simulator with MuJoCo-Warp, leveraging NVIDIA’s Warp framework for incredible acceleration. This marks a significant step in

We built an AI model to simulate how a fruit fly walks, flies and behaves – in partnership with HHMI | Janelia. 🪰 Our computerized insect replicates realistic motion, and can even use its eyes to control its actions. Here’s how we developed it – and what it means for science. 🧵