English

EqvAfford: SE(3) Equivariance for Point-Level Affordance Learning

Robotics 2024-08-08 v2 Computer Vision and Pattern Recognition Machine Learning

Abstract

Humans perceive and interact with the world with the awareness of equivariance, facilitating us in manipulating different objects in diverse poses. For robotic manipulation, such equivariance also exists in many scenarios. For example, no matter what the pose of a drawer is (translation, rotation and tilt), the manipulation strategy is consistent (grasp the handle and pull in a line). While traditional models usually do not have the awareness of equivariance for robotic manipulation, which might result in more data for training and poor performance in novel object poses, we propose our EqvAfford framework, with novel designs to guarantee the equivariance in point-level affordance learning for downstream robotic manipulation, with great performance and generalization ability on representative tasks on objects in diverse poses.

Keywords

Cite

@article{arxiv.2408.01953,
  title  = {EqvAfford: SE(3) Equivariance for Point-Level Affordance Learning},
  author = {Yue Chen and Chenrui Tie and Ruihai Wu and Hao Dong},
  journal= {arXiv preprint arXiv:2408.01953},
  year   = {2024}
}

Comments

Accept to CVPRWorkshop on Equivariant Vision: From Theory to Practice 2024

R2 v1 2026-06-28T18:03:22.413Z