WholeBodyWAM: Generalizing Pre-trained World-Action Priors to Humanoid Loco-Manipulation via WBC-Grounded Coordination
WholeBodyWAM is introduced, which jointly predicts future visual dynamics, manipulation actions, and whole-body control intents for generalizable humanoid loco-manipulation and preserves pre-trained world-action priors while grounding heterogeneous whole-body controller (WBC) semantics and coordinating whole-body behav...