arXiv cs.AI· Xinzhe Chen, Liqi Huang, Sihua Ren, Haowen Sun, Mingyang Li, Zeyang Liu, Xingyu Chen, Xuguang Lan·· 3 天前AI 评分22
面向 SE(3) 等变视觉运动策略的相位条件可供性场
Phase-Conditioned Affordance Fields for SE(3)-Equivariant Visuomotor Policies
AI 导读
研究提出相位条件可供性场（PAF），在观测点云上学习逐点分数，用其分数加权质心作为相位条件锚点对观测与动作做规范化，并将分数作为逐点特征，从而在保留全局 SE(3) 等变性的同时引入局部几何归纳偏置。在多种空间随机化下的 MimicGen 任务中，PAF 持续提升底层策略成功率；在多物体真机任务上优于基线，并在光照变化下保持领先。该工作已被 CoRL 2026 接收。
正文 · 原文
Abstract:SE(3)-equivariance provides a useful geometric inductive bias for visuomotor policies, encoding that actions covary with rigid transformations of the observation. However, existing SE(3)-equivariant visuomotor policies build this bias on a global equivariance assumption that treats the entire observation as governed by a single rigid transformation, which breaks down in real-world manipulation tasks where the task-relevant region changes across different objects. We address this by learning a phase-conditioned affordance field (PAF) over the observed point cloud, a per-point score that the SE(3)-equivariant policy uses in two complementary ways. Its score-weighted centroid serves as a learned, phase-conditioned anchor that canonicalizes the observation and the action around the active region, replacing the fixed gripper-frame reference, and the score itself is appended as a per-point feature. This introduces a local geometric inductive bias, while preserving the policy's global SE(3) equivariance. We validate on multiple MimicGen tasks under varying spatial randomization, and PAF consistently improves the success rate of the underlying policy. On multi-object real-robot tasks, PAF outperforms baselines and keeps its lead under lighting variations.
| Comments: | Accepted to the 10th Conference on Robot Learning (CoRL 2026). Project page: this https URL |
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.17281 [cs.RO] |
| (or arXiv:2610.17281v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.17281 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xinzhe Chen [view email]
[v1]
Mon, 12 Oct 2026 18:35:08 UTC (4,891 KB)
来源：arXiv cs.AI · arxiv.org