The authors extend an SE(3)-equivariant visuomotor policy with a phase-conditioned affordance field, a per-point score computed over the observed point cloud.
Per-point affordance fields let equivariant policies focus on task-relevant regions
The authors show that replacing the fixed gripper-frame anchor with a learned, score-weighted centroid improves success rates on simulation and real-robot tasks while preserving SE(3) equivariance.
Independent
Xinzhe Chen · Liqi Huang · Sihua Ren · Haowen Sun · Mingyang Li · Zeyang Liu · +2 more
Research Digest··2 min read
The authors introduce phase-conditioned affordance fields (PAF), per-point scores learned by an SE(3)-equivariant visuomotor policy.
Why this paper
Independent
In one line
A phase-conditioned affordance field improves SE(3)-equivariant visuomotor policies by learning per-point scores that anchor actions to task-relevant regions.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§