Making multimodal affordance research transparent and reproducible.

Affordance Sheet is a structured documentation for multimodal affordance prediction, connecting methods, datasets, evaluation protocols, and validation.

From individual papers to a reproducible research ecosystem.

Affordance prediction models are difficult to compare fairly due to fragmented problem formulations, inconsistent dataset annotations, incomplete reporting of experimental setups, and limited access to code and model weights.

Existing methods are mostly tested in controlled laboratory environments, leaving their generalization to novel conditions, robustness against occlusions, and human safety in physical interactions largely unvalidated.

Affordance Sheet provides a common structure for documenting these dimensions, making methods easier to understand, compare, and reproduce.

01

Structured documentation

Describe formulation, architecture, datasets, experiments, and validation using a common structure.

02

Reproducibility

Make missing information and reproducibility challenges explicit across research methods.

03

Research database

Explore documented methods, datasets, metrics, and robot validation through a shared database.