arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.17486cs.RO
收藏

EquiForm: 基于3D点云的噪声鲁棒SE(3)等价政策学习

EquiForm: Noise-Robust SE(3)-Equivariant Policy Learning from 3D Point Clouds

School of Industrial Engineering, Purdue University(工业工程学院,普渡大学)

Zhiyuan Zhang, Yu She

AI总结:

EquiForm通过引入噪声鲁棒的几何去噪模块和对比等价对齐目标,提升基于3D点云的政策学习在噪声和遮挡下的鲁棒性与泛化能力。

摘要:

基于3D点云的视觉模仿学习通过提供几何感知、外观不变的观察,推动了机器人操作的发展。然而,基于点云的策略仍然对传感器噪声、姿态扰动和遮挡引起的伪影高度敏感,这些因素会扭曲几何结构并破坏所需用于稳健泛化等价性假设。现有等价方法主要将对称约束编码到神经网络架构中,但并未明确纠正噪声引起的几何偏差或在学习的表示中强制等价一致性。我们引入EquiForm,一种针对基于点云操作的噪声鲁棒SE(3)等价政策学习框架。EquiForm阐述了噪声引起的几何失真如何导致观测到动作映射中的等价性偏差,并引入了一个几何去噪模块以在嘈杂或不完整观察下恢复一致的3D结构。此外,我们提出了一种对比等价对齐目标,强制在刚体变换和噪声扰动下保持表示的一致性。基于这些组件,EquiForm形成了一种灵活的政策学习流水线,集成了噪声鲁棒的几何推理与现代生成模型。我们在16个模拟任务和4个现实世界操作任务上评估了EquiForm,涵盖了多样化的物体和场景布局。与最先进的点云模仿学习方法相比,EquiForm在模拟中平均提高了17.2%,在现实世界实验中提高了28.1%,证明了其强大的噪声鲁棒性和空间泛化能力。

英文摘要:

Visual imitation learning with 3D point clouds has advanced robotic manipulation by providing geometry-aware, appearance-invariant observations. However, point cloud-based policies remain highly sensitive to sensor noise, pose perturbations, and occlusion-induced artifacts, which distort geometric structure and break the equivariance assumptions required for robust generalization. Existing equivariant approaches primarily encode symmetry constraints into neural architectures, but do not explicitly correct noise-induced geometric deviations or enforce equivariant consistency in learned representations. We introduce EquiForm, a noise-robust SE(3)-equivariant policy learning framework for point cloud-based manipulation. EquiForm formalizes how noise-induced geometric distortions lead to equivariance deviations in observation-to-action mappings, and introduces a geometric denoising module to restore consistent 3D structure under noisy or incomplete observations. In addition, we propose a contrastive equivariant alignment objective that enforces representation consistency under both rigid transformations and noise perturbations. Built upon these components, EquiForm forms a flexible policy learning pipeline that integrates noise-robust geometric reasoning with modern generative models. We evaluate EquiForm on 16 simulated tasks and 4 real-world manipulation tasks across diverse objects and scene layouts. Compared to state-of-the-art point cloud imitation learning methods, EquiForm achieves an average improvement of 17.2% in simulation and 28.1% in real-world experiments, demonstrating strong noise robustness and spatial generalization.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑