利用触觉对称性实现零样本旋转矫正，大幅降低触觉策略训练数据需求。
Residual Rotation Correction using Tactile Equivariance
- 基于视觉触觉传感器重建法向量场，利用SO(2)对称性设计等变网络
- 仅用少量样本即在真实机器人上实现未见姿态的零样本泛化
- 适合接触密集型操作任务，尤其适用于触觉数据稀缺场景
视觉-触觉策略学习通过引入触觉信息提升高接触密度操作能力，但触觉数据采集成本高，因此样本效率至关重要。本文提出EquiTac框架，利用物体在手中旋转的SO(2)固有对称性，提升视觉-触觉策略的学习效率与泛化能力。该方法首先从基于视觉的触觉传感器原始RGB输入中重建表面法向量场，使法向量场的旋转对应于物体在手中的实际旋转。随后，采用SO(2)-等变网络预测残差旋转动作，在推理时增强基础视觉-运动策略，实现无需额外重定向演示的实时旋转校正。在真实机器人上，EquiTac仅需极少训练样本即可实现对未见过的手持姿态的鲁棒零样本泛化，而基线方法即使使用更多数据也失败。据我们所知，这是首个显式编码触觉等变性用于策略学习的方法，构建了一个轻量、具备对称性感知能力的模块，显著提升了接触密集任务的可靠性。
原文摘要 · Abstract (English)
Visuotactile policy learning augments vision-only policies with tactile input, facilitating contact-rich manipulation. However, the high cost of tactile data collection makes sample efficiency the key requirement for developing visuotactile policies. We present EquiTac, a framework that exploits the inherent SO(2) symmetry of in-hand object rotation to improve sample efficiency and generalization for visuotactile policy learning. EquiTac first reconstructs surface normals from raw RGB inputs of vision-based tactile sensors, so rotations of the normal vector field correspond to in-hand object rotations. An SO(2)-equivariant network then predicts a residual rotation action that augments a base visuomotor policy at test time, enabling real-time rotation correction without additional reorientation demonstrations. On a real robot, EquiTac accurately achieves robust zero-shot generalization to unseen in-hand orientations with very few training samples, where baselines fail even with more training data. To our knowledge, this is the first tactile learning method to explicitly encode tactile equivariance for policy learning, yielding a lightweight, symmetry-aware module that improves reliability in contact-rich tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。