Whole-Body Dexterity

Humanoid loco-manipulation remains predominantly hand-centric, falling short of humans’ ability to engage the entire body by bracing and sliding bulky objects against the forearms 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 cache 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 cache, and finally distills these experts into a single deployable policy. We show that the distilled policy transfers zero-shot to a real Unitree G1, where it repositions a basketball to regions around the torso and completes a long-horizon task that stows a box under one arm, carries it between shelves, and places it. In simulation the same controller refines corrupted expert commands into stable manipulation and transfers to object sizes withheld from training. The controller operates interactively, steered by coarse motion references from a human teleoperator. Across three real-world whole-body manipulation tasks, the distilled controller achieves 6× the task success rate of direct retargeting at 3× the speed, and completes tasks a generalist whole-body motion-tracking controller cannot.