AFUN: Towards an Affordance Foundation Model for Functionality Understanding

Researchers introduced AFUN, an affordance foundation model for robot functionality understanding.

Given a single RGB-D observation and a language instruction, it predicts a task-specific functional mask and a 3D post-contact motion curve.

The team also built a large-scale data pipeline that unifies robot, human, simulation, and real-world scan data into one affordance schema.

AFUN outperformed baselines on affordance segmentation, contact-point prediction, and 3D motion benchmarks.

It worked on real-world robot manipulation without finetuning or task-specific heuristics, improving open-world generalization.