← Back to all news
arXiv AI By Chen Tessler, Yifeng Jiang, Alec Otto, Yi Shi, Umar Iqbal, Gal Chechik, Xue Bin Peng

METATRON: A Promptable Whole-Body Execution Layer for Humanoids

Read the original on arXiv AI →

METATRON is a promptable whole‑body execution layer for humanoid robots that combines a generative base policy with a programmable skill layer. The base policy, trained on motion capture, synthetic recovery, and retargeted scene‑interaction data, receives partial goals—timed body‑part targets, velocity commands, and style cues—called a prompt, and generates diverse, coordinated whole‑body motions. After training, the policy is frozen and task intent is expressed through stateful programs (skills) that issue prompts at each control step; these skills are ordinary code refined by coding agents that analyze motion data and fit compact rules, enabling the robot to walk, recover, pick up objects, sit, climb, and perform acrobatics without further policy training.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Oct 9

VioLA: Learning Generalist Humanoid Control Policies from Human Data

VioLA is a generalist humanoid control policy that predicts body and hand motion latents instead of joint commands, enabling a pretrained controller to execute these latents on a robot. By aligning human and robot motion in shared latent spaces, the policy can be trained on a large dataset of 140.6 million frames, 93.2% of which are human demonstrations. As a result, VioLA can follow locomotion and manipulation instructions on a real robot zero‑shot, achieving 100% locomotion success and 88.6% manipulation success without task‑specific fine‑tuning.

By Mert Albaba, Jens Bei{\ss}wenger, Anna Manasyan, Daniel Marta, Michael J. Black, Wieland Brendel, Andreas Krause, Georg Martius, Martin Riedmiller
roboticsfine-tuning
More like this →
arXiv AI
Oct 16

Whole-Body Dexterity

Whole-Body Dexterity (WBD) is a framework that enables robots to use their entire body and appendages as contact surfaces for grasping and manipulating objects. The approach generates a dataset of feasible whole-body grasps, trains reinforcement‑learning experts on a repositioning objective, and distills them into a single policy that relies on proprioception and object geometry. The distilled policy achieves zero‑shot transfer to a real Unitree G1 robot, successfully completing complex tasks such as stowing a box under one arm and moving it from a shelf to a table, with a 90% success rate in real‑world trials.

By Conor Mc Gartoll, An Dang, Pranay Thangeda, Arjun Gupta, Carolina Higuera, Nima Fazeli, Mustafa Mukadam, Manikantan Nambi
robotics
More like this →
arXiv Machine Learning
Jul 28

Learning Reusable Hybrid Motion Priors for Humanoid Locomotion from Motion Imitation

arXiv:2607. 24083v1 Announce Type: new Abstract: Reinforcement learning can produce robust humanoid controllers, but each new task is typically trained as a separate policy with its own reward design and training process.

By Valerio Belli (UNIROMA, UCL), Valerio Modugno (UCL), Enrico Mingo Hoffman (HUCEBOT), Fabio Amadio (HUCEBOT)
reinforcement-learningroboticsefficiency
More like this →
arXiv AI
Aug 3

CLIFT: Turning Gemini Robotics On-Device into Humanoid Specialists via Non-Invasive Closed-Loop Iterative Fine-Tuning

arXiv:2607. 29172v1 Announce Type: cross Abstract: While robot foundation models are growing increasingly capable, the strongest models are typically trained on proprietary data and remain closed-source, limiting downstream users' ability to adapt them to new tasks, embodiments, and deployment settings.

By Yuxin Chen, Hari Srikanth, Nathan Jew, Menglin Wu, Pengcheng Wang, Junli Ren, Masayoshi Tomizuka, Peng Xu, Jinyu Xie, Thomas Tian
llmsreinforcement-learningroboticsfine-tuning
More like this →