← Back to Benchmarks
simmediumdexterousmetric · varies
DexMachina: Functional Retargeting for Bimanual Dexterous Manipulation
Description
We study the problem of functional retargeting: learning dexterous manipulation policies to track object states from human hand-object demonstrations. We focus on long-horizon, bimanual tasks with articulated objects, which is challenging due to large action space, spatiotemporal discontinuities, and embodiment gap between human and robot hands. We propose DexMachina, a novel curriculum-based algorithm: the key idea is to use virtual object controllers with decaying strength: an object is first