Whole-Body Dexterity

Current humanoid dexterous manipulation remains largely confined to end-effectors and simple grasps, falling short of humans’ ability to engage the entire body by bracing and sliding bulky objects against the arms and torso. We introduce Whole-Body Dexterity (WBD), a general framework that uses the robot's body and appendages as contact surfaces to grasp and manipulate objects. Our sim-to-real pipeline first generates a dataset of feasible whole-body grasps, then trains reinforcement-learning experts on a general any-to-any grasp objective by sampling initial and goal grasps from the dataset, and finally distills these experts into a single deployable proprioception-only policy. We show that the distilled policy transfers zero-shot to a real Unitree G1, where it repositions a basketball and a cardboard box to regions around the torso and completes a long-horizon task that stows a box under one arm, carries it from a shelf to a table, and places it. The controller operates interactively, steered by coarse motion references from a human teleoperator. Across real-world whole-body manipulation tasks, the distilled controller completes 90% of trials, compared with 18% for direct retargeting and 4% for a generalist whole-body controller.

BibTeX

@article{mcgartoll2026wholebody,
  title   = {Whole-Body Dexterity},
  author  = {Conor Mc Gartoll and An Dang and Pranay Thangeda
             and Arjun Gupta and Carolina Higuera and Nima Fazeli
             and Mustafa Mukadam and Manikantan Nambi},
  journal = {arXiv preprint arXiv:2610.22184},
  year    = {2026},
  url     = {https://arxiv.org/abs/2610.22184}
}