الملخص
Teaching a humanoid to follow instructions with its whole body runs into two obstacles. Its action space is large and tightly coupled: legs, arms, and fingers must move together while the robot keeps its balance, which makes joint-level actions hard to learn. And humanoid demonstrations are scarce, so current humanoid generalist policies do not follow new instructions out of the box and are fine-tuned on teleoperated demonstrations of each task before deployment. Human demonstrations exist in far larger numbers, but a person's motion is not a robot command. We remove both obstacles by changing what the generalist policy predicts. We introduce VioLA, a generalist humanoid policy that predicts body and hand motion latents instead of joint commands. A pretrained body- and hand-controller execute these latents on the robot. Their corresponding motion encoders map human and robot motion into the same latent spaces. A human recording is therefore labeled in the policy's action space, and the training demonstration pool contains 140.6 million frames, 93.2% of them human. As a result, VioLA follows locomotion instructions on the real robot zero-shot, without task-specific fine-tuning, reaching 100% success where GR00T N1.7 and $Ψ_0$ reach 16.7% and 0%, respectively. It also reaches 88.6% manipulation success without task-specific fine-tuning. The same approach works across two VLA and one world-action model backbones. A generalist policy trained on human demonstrations alone performs locomotion tasks on the real robot zero-shot. Code and checkpoints will be released.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Albaba, M., Beißwenger, J., Manasyan, A., Marta, D., Black, M. J., Brendel, W., Krause, A., Martius, G., & Riedmiller, M. (2026). VioLA: Learning Generalist Humanoid Control Policies from Human Data. https://omanscience.com/ar/articles/viola-learning-generalist-humanoid-control-policies-from-human-data
MLA 9
Albaba, Mert, et al. "VioLA: Learning Generalist Humanoid Control Policies from Human Data." https://omanscience.com/ar/articles/viola-learning-generalist-humanoid-control-policies-from-human-data.
شيكاغو (المؤلف–التاريخ)
Albaba, Mert, Jens Beißwenger, Anna Manasyan, Daniel Marta, Michael J. Black, Wieland Brendel, Andreas Krause, Georg Martius, and Martin Riedmiller. 2026. "VioLA: Learning Generalist Humanoid Control Policies from Human Data." https://omanscience.com/ar/articles/viola-learning-generalist-humanoid-control-policies-from-human-data.
هارفارد
Albaba, M., Beißwenger, J., Manasyan, A., Marta, D., Black, M. J., Brendel, W., Krause, A., Martius, G. and Riedmiller, M. (2026) 'VioLA: Learning Generalist Humanoid Control Policies from Human Data', Available at: https://omanscience.com/ar/articles/viola-learning-generalist-humanoid-control-policies-from-human-data.
فانكوفر
Albaba M, Beißwenger J, Manasyan A, Marta D, Black MJ, Brendel W, et al. VioLA: Learning Generalist Humanoid Control Policies from Human Data. https://omanscience.com/ar/articles/viola-learning-generalist-humanoid-control-policies-from-human-data
IEEE
M. Albaba, J. Beißwenger, A. Manasyan, D. Marta, M. J. Black, W. Brendel, A. Krause, G. Martius, and M. Riedmiller, "VioLA: Learning Generalist Humanoid Control Policies from Human Data," https://omanscience.com/ar/articles/viola-learning-generalist-humanoid-control-policies-from-human-data.