Existing retargeting often produces artifacts like foot-skating and penetration ❌. To compensate, RL policies rely on complex ad-hoc reward terms, forcing a trade-off between accurate motion tracking and correcting errors like slipping or bad contacts. OmniRetarget fixes this

The result of this high-quality data? We can train diverse skills like box carrying 📦, slope crawling 🐾, and platform climbing 🧗 with a radically simplified RL process! All policies use just 5 reward terms, achieving successful zero-shot sim-to-real transfer! 🎯➡️🦾 3/9

What about scalability? OmniRetarget transforms a SINGLE human demo into diverse motion clips. We can systematically vary terrain height, object size, and initial poses. Best of all, these augmented skills transfer directly from sim to our real-world hardware! 🤖➡️🦾 4/9

And it's not just for a specific robot! Our framework is highly general and adapts to different robot embodiments, including the @UnitreeRobotics H1 and the @boosterobotics T1. We can retarget complex object-carrying and platform-climbing skills across these different robots with

But how much better is our data? 🤔 Compared to widely-used baselines, our motions show far fewer physical artifacts—virtually zero foot-skating and penetration—while better preserving contact. This allows us to use an open-sourced RL framework (BeyondMimic) without

Our grand finale: A complex, long-horizon dynamic sequence, all driven by a proprioceptive-only policy (no vision/LIDAR)! In this task, the robot carries a chair to a platform, uses it as a step to climb up, then leaps off and performs a parkour-style roll to absorb the landing.

Standing on the shoulders of giants! Our work builds on amazing research in the community💡. We use the "interaction mesh" 🕸️ [1], [2] to preserve spatial relationships and leverage the minimal RL formulation from works like BeyondMimic [3]. Our long-horizon sequence is a nod to

We are open-sourcing over 4 hours of high-quality, retargeted trajectories! Website: https://omniretarget.github.io ArXiv: https://arxiv.org/abs/2509.266... Datasets: https://huggingface.co/dataset... Huge shout out to the amazing team: @lujieyang98, @x_h_ucb, @akanazawa, @pabbeel, @carlo_sferrazza,

@zhenkirito123 Beautiful results!!! And cliffhanger 😂

@brenthyi Thanks Brent! Yeah there are more exciting parkour-style motions on the way 🚗🚗🚗😝

@zhenkirito123 climbed like a real human. Soon, we will see robot parkour competitions.

@zhenkirito123 Very cool work

@zhenkirito123 Incredible work! Really solid result

@zhenkirito123 @Scobleizer This looks like a huge step forward for more natural humanoid motion 👏

@zhenkirito123 This is truly impressive to see how generalizeable this is and also simplifies the skill transfer process to potentially hundreds of humanoid robot vendors. Won’t be surprised to see lots of robotics companies building upon this work in the future.

@zhenkirito123 Impressive work! Fixing retargeting artifacts at the source rather than with complex reward engineering is the right approach. The long-horizon parkour sequence is stunning!

@zhenkirito123 this is what the community needs:) and these videos are really impressive!

@zhenkirito123 I don’t know you personally yet, but you superstar better than 1000 Kardashians and Ronaldo 🚀🤖

@zhenkirito123 Pelvic and hip mobility is bloody amazing

@zhenkirito123 Impressive work on solving those artifact issues! Streamlined RL with fewer reward terms is a game changer. What's next for scalability challenges?

@zhenkirito123 That’s some really nice work! Congratulations!

@zhenkirito123 @grok What's the meaning of retargeting?

@zhenkirito123 @TairanHe99 If you had to choose which is more efficient, learning from Third-Person Human or Learning from Motion Capture

@zhenkirito123 Interesting work! Specially since it doesn’t need to undergo curriculum training. Could OmniRetarget be made adaptive to the downstream RL task or policy uncertainty, dynamically refining trajectories?

@zhenkirito123 Wow interesting stuff and you say it's generalizable to other robots? Def interested 😁

@zhenkirito123 Very impressive

@zhenkirito123 OmniRetarget: Where human grace meets robotic agility. A leap into a new era of interaction! 🤖✨

@zhenkirito123 @Threadreaderapp unroll

@zhenkirito123 Congrats! When will you open-source the motion retargeting code🥹

@zhenkirito123 6

@zhenkirito123 @Tesla_Optimus

@zhenkirito123 wow!!! 🥹🫶 amazing job this is so cool!!

@zhenkirito123 That's great.

@zhenkirito123