Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Our 6ft humanoid HumanPlus at Stanford can autonomously put on a Nike skateboard shoe, tie shoelaces, stand up and walk. Using two transformers & dual RGB vision, it integrates two recipes of general robotics end-to-end: - imitating humans in real world - large-scale RL in sim

246,224 görüntüleme • 2 yıl önce •via X (Twitter)

10 Yorum

Zipeng Fu profil fotoğrafı
Zipeng Fu2 yıl önce

More autonomous skills of HumanPlus can be found here:

Zipeng Fu profil fotoğrafı
Zipeng Fu2 yıl önce

Team: @zipengfu*, @qingqing_zhao_*, @Qi_Wu577*, @GordonWetzstein, @chelseabfinn project website: hardware: code:

Barrett profil fotoğrafı
Barrett2 yıl önce

What happens if I sneak behind it and tie the laces together when it’s not looking

Neil Lawrence profil fotoğrafı
Neil Lawrence2 yıl önce

But can it then say "I don't have to outrun the lion, I only have to outrun you."?

whistle profil fotoğrafı
whistle2 yıl önce

why does it need shoes…

Hang Zhao profil fotoğrafı
Hang Zhao2 yıl önce

This is truly impressive!

Zipeng Fu profil fotoğrafı
Zipeng Fu2 yıl önce

Thanks Hang!

stellarstrain profil fotoğrafı
stellarstrain2 yıl önce

Why 6 ft, 5.11 would have been better.

Ophelia profil fotoğrafı
Ophelia2 yıl önce

Finally some sick sneakers on a bot. It's about time.

Happy profil fotoğrafı
Happy2 yıl önce

wow😮

Benzer Videolar

Trained a humanoid entirely in a 3D scan of the office. Zero real-world fine-tuning. It just walked in and worked. RL needs hundreds of thousands of attempts, and real robots can't afford to crash. A misjudged gap or a glass door collision breaks hardware and costs hours resetting. So you train in a sim. But sim policies usually train on randomized, untextured geometry; depth is easy to fake. The robot learns structure, not the real world: no materials, no lighting, no idea what anything actually is. RGB cameras carry all of that but training RGB policies in generic fake worlds won’t generalize to the real world. Niantic Spatial 🌎 Scaniverse reconstructs your scan of the real deployment site. One 360° camera walkthrough → photorealistic 3D Gaussian splat at metric scale → collision mesh pulled from the same reconstruction, so vision and physics match exactly. Drops straight into NVIDIA Isaac Sim/Lab, no manual conversion. Flexion simulation-first approach then seamlessly enables the training of RGB-only nav policies inside that reconstruction. With added domain randomization + large image encoders for robustness, this deploys straight to hardware. No real-world fine-tuning. Deployment: months of on-site adaptation → days. Tune into the NVIDIA livestream on 12 August to hear how these companies are closing the sim2real gap: NVIDIA Robotics ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

119,163 görüntüleme • 25 gün önce