# 面向 SE(3)-等变视觉运动策略的阶段条件化可供性场

> 原文链接：https://robotics.hellobike.com/papers/2026-10-12-2610-17281
> 频道：papers | 更新日期：2026-10-12 | 标签：arxiv, cs.RO
> 核心摘要：针对全局 SE(3) 等变假设难适应任务相关区域变化，方法学习 PAF 点云评分，并在 MimicGen 与多物体真机任务上验证。

# 面向 SE(3)-等变视觉运动策略的阶段条件化可供性场

::: v-pre
> 原文链接：[Phase-Conditioned Affordance Fields for SE(3)-Equivariant Visuomotor Policies](https://arxiv.org/abs/2610.17281)（arXiv 2610.17281 · 发布日期：2026-10-12）

**Phase-Conditioned Affordance Fields for SE(3)-Equivariant Visuomotor Policies**

针对全局 SE(3) 等变假设难适应任务相关区域变化，方法学习 PAF 点云评分，并在 MimicGen 与多物体真机任务上验证。

## 核心要点

- 现有 SE(3)-等变视觉运动策略依赖全局刚体变换假设，在真实操作中相关区域会随物体变化。
- 方法在观测点云上学习阶段条件化可供性场，为每个点生成策略可利用的得分。
- 得分加权质心作为阶段条件化锚点规范化观测与动作，得分也作为逐点特征输入。
- 在多个 MimicGen 任务和多物体真机任务中，PAF 提升成功率并优于基线，光照变化下仍领先。

**验证范围与局限**：验证范围包括不同空间随机化下的多个 MimicGen 任务，以及多物体真机任务和光照变化。

## 英文摘要 (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.

作者：Xinzhe Chen, Liqi Huang, Sihua Ren, Haowen Sun, Mingyang Li, Zeyang Liu, Xingyu Chen, Xuguang Lan
:::

## 原始参考来源 (Sources)

- [arXiv 2610.17281：Phase-Conditioned Affordance Fields for SE(3)-Equivariant Visuomotor Policies](https://arxiv.org/abs/2610.17281)