Humanoid World Action Model With Joint State--Action Generation
The Humanoid World Action Model (HWAM) introduces joint state-action generation to bridge the action-execution gap in humanoid robots. It explicitly targets post-execution proprioceptive states during action generation, connecting high-level policy actions to physical motion and visual scene changes through complementary training paths like Forward Dynamics Modeling and Inverse Dynamics Modeling. This leads to higher success rates on complex manipulation tasks.