提出E3Flow框架，实现高效稳定的机器人操作视觉运动流策略。
Efficient Hybrid SE(3)-Equivariant Visuomotor Flow Policy via Spherical Harmonics for Robot Manipulation
- 基于球谐函数构建SO(3)等变表示，保证旋转对称性。
- 在模拟任务中成功率提升3.12%，推理速度加快7倍。
- 支持多模态输入，适合需要高效与稳定性的机器人控制场景。
现有等变方法虽提升数据效率，但存在计算开销大、依赖单模态输入及与快速采样方法结合时不稳定的问题。本文提出E3Flow框架，首次实现高效修正流与稳定多模态等变学习的统一。该框架基于球谐函数表示以确保严格的SO(3)等变性，并引入新颖的不变特征增强模块（FEM），动态融合点云与图像等多模态视觉信息，将丰富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，另开展4组真实世界实验验证其在物理环境中的有效性。仿真结果显示，相比最先进方法Spherical Diffusion Policy（SDP），E3Flow平均成功率提升3.12%，同时实现7倍推理加速。该工作展示了性能、效率与数据效率之间新的有效权衡。代码已开源：https://github.com/zql-kk/E3Flow。
原文摘要 · Abstract (English)
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.
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。