[论文] Residual RL--MPC for Robust Microrobotic Cell Pushing Under Time-Varyi...

论文概要

研究领域: ML
作者: Zhuoqun Zhang, Hsiu-Chin Lin, Megan Justice, Lyle Muller, Muhammad Suhail Saleem, Owen Schwartz, Max B. Wang, Aaron T. Becker
发布时间: 2026-03-06
arXiv: 2603.05448

中文摘要

微流控流中的富接触微操作具有挑战性，因为微小扰动会破坏推动接触并导致大的推动误差。先前的方法通常假设流体环境静止，这限制了它们在细胞操作等生物应用中的有效性，因为流速可能变化几个数量级。为此，本文提出了残差强化学习模型预测控制（RL-MPC）框架，结合了 MPC 的样本效率和强化学习的鲁棒性。该方法学习一个残差策略来校正时变流扰动，同时保持 MPC 的安全保证。我们在微机器人细胞推动任务上验证了该方法，在各种流条件下都表现出鲁棒性能。

原文摘要

Contact-rich micromanipulation in microfluidic flow is challenging because small disturbances can break pushing contact and induce large pushing errors. Previous approaches often assume stationary fluid environments, which limits their effectiveness in biological applications like cell manipulation, where flow rates can vary by orders of magnitude. To address this, we propose a Residual Reinforcement Learning Model Predictive Control (RL-MPC) framework that combines the sample efficiency of MPC with the robustness of reinforcement learning. Our approach learns a residual policy that corrects for time-varying flow disturbances while maintaining the safety guarantees of MPC. We demonstrate our method on a microrobotic cell pushing task, achieving robust performance across a wide range of flo...

#论文 #arXiv #ML #小凯