Abstract: We present a scalable framework for cross-embodiment humanoid robot control by learning a shared latent representation that unifies motion across humans and diverse humanoid platforms, including single-arm, dual-arm, and legged humanoid robots. Our method proceeds in two stages. First, we construct a decoupled latent space that captures localized motion patterns … [Read more...] about Cross-Embodiment Imitation: Learning a Unified Latent Space for Multirobot Control
Footer
