arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.01115cs.ROcs.CV
收藏

KAN We Flow? 通过KAN与RWKV实现3D操作的机器人操控进步

KAN We Flow? Advancing Robotic Manipulation with 3D Flow Matching via KAN & RWKV

School of Intelligent Engineering and Automation, Beijing University of Posts and Telecommunications (BUPT)(北京邮电大学智能工程与自动化学院);Beijing Hydrogen Intelligence Technology Co. Ltd.(北京氢能智能科技有限公司);School of Electronic and Information Engineering, South China University of Technology(华南理工大学电子与信息学院)

Zhihao Chen, Yiyuan Ge, Ziyang Wang, Youwei Zhang

AI总结:

KAN-We-Flow通过结合RWKV和KAN技术,实现轻量高效的3D机器人操作策略,显著提升性能与效率。

摘要:

基于扩散的视觉-运动策略在建模动作分布方面表现出色,但推理效率低下,因为从噪声到策略的递归去噪需要许多步骤和重型UNet后端,这阻碍了在资源受限的机器人上的部署。流匹配通过学习一步向量场来减轻采样负担,但先前的实现仍然继承了大型UNet式架构。在本工作中,我们提出了KAN-We-Flow,一种流匹配策略,借鉴了从视觉领域最近的Receptance Weighted Key Value(RWKV)和Kolmogorov-Arnold Networks(KAN)的进展,构建了一个轻量且高度可表达的3D操作后端。具体而言,我们引入了RWKV-KAN模块:RWKV首先执行高效的时域/通道混合以传播任务上下文,随后的GroupKAN层应用可学习的样条基组内功能映射,对RWKV输出的动作映射进行特征级非线性校准。此外,我们引入了动作一致性正则化(ACR),一种轻量级的辅助损失,通过欧拉外推强制预测的动作轨迹与专家演示之间的一致性,提供额外的监督以稳定训练并提高策略精度。不依赖大型UNet,我们的设计将参数减少了86.8%,保持了快速的运行时间,并在Adroit、Meta-World和DexArt基准上实现了最先进的成功率。我们的项目页面可以在\href{https://zhihaochen-2003.github.io/KAN-We-Flow.github.io/}{\textcolor{red}{link}}查看。

英文摘要:

Diffusion-based visuomotor policies excel at modeling action distributions but are inference-inefficient, since recursively denoising from noise to policy requires many steps and heavy UNet backbones, which hinders deployment on resource-constrained robots. Flow matching alleviates the sampling burden by learning a one-step vector field, yet prior implementations still inherit large UNet-style architectures. In this work, we present KAN-We-Flow, a flow-matching policy that draws on recent advances in Receptance Weighted Key Value (RWKV) and Kolmogorov-Arnold Networks (KAN) from vision to build a lightweight and highly expressive backbone for 3D manipulation. Concretely, we introduce an RWKV-KAN block: an RWKV first performs efficient time/channel mixing to propagate task context, and a subsequent GroupKAN layer applies learnable spline-based, groupwise functional mappings to perform feature-wise nonlinear calibration of the action mapping on RWKV outputs. Moreover, we introduce an Action Consistency Regularization (ACR), a lightweight auxiliary loss that enforces alignment between predicted action trajectories and expert demonstrations via Euler extrapolation, providing additional supervision to stabilize training and improve policy precision. Without resorting to large UNets, our design reduces parameters by 86.8\%, maintains fast runtime, and achieves state-of-the-art success rates on Adroit, Meta-World, and DexArt benchmarks. Our project page can be viewed in \href{https://zhihaochen-2003.github.io/KAN-We-Flow.github.io/}{\textcolor{red}{link}}

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。

↑