WECO:Equivariant, Generalizable Robot Actions from Object-Centric World Changes

Generalizing robot manipulation beyond the training distribution remains difficult because demonstrations sparsely cover variations in object appearance, geometry, and workspace configuration. We introduce WECO, a world–action framework that separates what should change in the world from how a fixed robot embodiment should realize that change. Given a predicted visual future, WECO extracts a structured object-centric world change consisting of a coarse rigid transformation $(\mathbf{R},\mathbf{t})$ and sparse contact or alignment references. A geometry-conditioned inverse dynamics model combines this target change with an object-centered mesh of the current state to predict short action chunks in closed loop. Experiments across multiple manipulation primitives show strong robustness to appearance changes and encouraging transfer across object geometry and workspace positions. These preliminary results suggest that structured object-level world changes provide a useful inductive bias for manipulation generalization.