基于球谐函数的高效混合 SE(3) 等变视觉运动流策略用于机器人操作
Efficient Hybrid SE(3)-Equivariant Visuomotor Flow Policy via Spherical Harmonics for Robot Manipulation
把球谐函数表示作为 SO(3) 等变的载体，并设计不变特征增强模块融合点云与图像，可直接迁移到任何需要旋转等变的多模态视觉编码器；同时证明整流流可与等变扩散策略稳定结合，为少步采样策略学习提供可复用方案。
原文依据 unifying efficient rectified flow with stable, multi-modal equivariant learning for the first time
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论现有等变方法虽然提升了数据效率，却存在计算开销大、依赖单模态输入，以及与快速采样方法结合时不稳定等问题。本文提出 E3Flow，一个旨在解决等变扩散策略关键局限的新框架。E3Flow 克服了上述挑战，首次成功地将高效的整流流与稳定的多模态等变学习统一起来。该框架以球谐函数表示为基础，以确保严格的 SO(3) 等变性。我们提出了一种新的不变特征增强模块（FEM），它动态融合混合视觉模态（点云与图像），将丰富的视觉线索注入球谐特征。我们在 MimicGen 的 8 个操作任务上评估 E3Flow，并进一步开展 4 项真实世界实验以验证其在物理环境中的有效性。仿真结果表明，E3Flow 相比最优的球谐扩散策略（SDP）在平均成功率上提升 3.12%，同时带来 7 倍的推理加速。因此，E3Flow 在性能、效率与数据效率之间展示了一种全新且高效的权衡，适用于机器人策略学习。代码：https://github.com/zql-kk/E3Flow。
英文原文摘要 1330 字符
While existing equivariant methods enhance data efficiency, they suffer from high computational intensity, reliance on single-modality inputs, and instability when combined with fast-sampling methods. In this work, we propose E3Flow, a novel framework that addresses the critical limitations of equivariant diffusion policies. E3Flow overcomes these challenges, successfully unifying efficient rectified flow with stable, multi-modal equivariant learning for the first time. Our framework is built upon spherical harmonic representations to ensure rigorous SO(3) equivariance. We introduce a novel invariant Feature Enhancement Module (FEM) that dynamically fuses hybrid visual modalities (point clouds and images), injecting rich visual cues into the spherical harmonic features. We evaluate E3Flow on 8 manipulation tasks from the MimicGen and further conduct 4 real-world experiments to validate its effectiveness in physical environments. Simulation results show that E3Flow achieves a 3.12% improvement in average success rate over the state-of-the-art Spherical Diffusion Policy (SDP) while simultaneously delivering a 7x inference speedup. E3Flow thus demonstrates a new and highly effective trade-off between performance, efficiency, and data efficiency for robotic policy learning. Code: https://github.com/zql-kk/E3Flow.