Video2Act: A Dual-System Video Diffusion Policy with Robotic Spatio-Motional Modeling

Understand

Robust perception and dynamics modeling are fundamental to real-world robotic policy learning.

• Recent methods employ video diffusion models (VDMs) to enhance robotic policies, improving their understanding and modeling of the physical world.
• However, existing approaches overlook the coherent and physically consistent motion representations inherently encoded across frames in VDMs.
• To this end, we propose Video2Act, a framework that efficiently guides robotic action learning by explicitly integrating spatial and motion-aware representations.