SUREFlow：用于鲁棒机器人操作的状态空间不确定性感知残差流匹配
SUREFlow: State-space Uncertainty-aware REsidual Flow Matching for Robust Robot Manipulation
浏览论文内容
中文总结 AI 辅助
研究针对机器人操作策略在复杂条件下的不稳定性问题，提出SUREFlow框架，基于Mamba主干联合预测动作速度与残差不确定性，能选择性细化动作维度，在LIBERO等平台实验中取得良好效果，提升了机器人操作的鲁棒性与效率。
中文摘要 AI 辅助
生成式视觉-语言-动作策略推动了机器人操作的发展，但在噪声、部分可观测性和随机初始条件下往往表现出不稳定性。在长时间展开过程中，小的速度误差会累积，降低执行可靠性。现有扩散和基于流的策略通常假设同方差残差，在动作生成中缺乏明确的不确定性建模。我们提出了SUREFlow，一个基于Mamba主干构建的状态空间不确定性感知残差流匹配框架。该方法联合预测动作速度和输入相关的残差不确定性，能够在无需环境反馈的情况下选择性地细化不可靠的动作维度，同时保持计算效率。在LIBERO上，SUREFlow平均成功率达到92.5%，比基于Mamba的MaIL高出34.2%。在LIBERO-PRO上，仅使用179M参数就达到了约49%的成功率，性能与具有3-7B参数的大型VLA相当。
英文摘要
Generative vision-language-action policies have advanced robot manipulation, but they often exhibit instability under noise, partial observability, and stochastic initial conditions. During extended rollouts, small velocity errors accumulate, degrading execution reliability. Existing diffusion and flow-based policies typically assume homoscedastic residuals and lack explicit uncertainty modeling within action generation, limiting robustness during iterative rollout. We propose SUREFlow, a state-space uncertainty-aware residual flow matching framework built on a Mamba backbone. The method jointly predicts action velocities and input-dependent residual uncertainty, enabling selective refinement of unreliable action dimensions without environment feedback while preserving computational efficiency. On LIBERO, SUREFlow achieves 92.5% average success rate (SR), outperforming the Mamba-based MaIL by 34.2%. On LIBERO-PRO, it attains around 49% SR using only 179M parameters, achieving performance comparable to large VLAs with 3-7B parameters. SUREFlow source code is available on: https://github.com/tanvirnwu/SUREFlow
发表机构
- School of Electronic and Electrical Engineering, Kyungpook National University（庆尚国立大学电子与电气工程学院）
机构由 AI 辅助整理，请以论文原文为准。
