This paper presents a control framework for magnetically actuated micron-scale robots ($\mu$bots) designed to mitigate disturbances and improve trajectory tracking. To address the challenges posed by unmodeled dynamics and environmental variability, we combine data-driven modeling with model-based control to accurately track desired trajectories using a relatively small amount of data. The system is represented with a simple linear model, and Gaussian Processes (GP) are employed to capture and estimate disturbances. This disturbance-enhanced model is then integrated into a Model Predictive Controller (MPC). Our approach demonstrates promising performance in both simulation and experimental setups, showcasing its potential for precise and reliable microrobot control in complex environments.

翻译：本文提出了一种用于磁驱动微米级机器人（$\mu$bot）的控制框架，旨在抑制扰动并改善轨迹跟踪性能。为应对未建模动力学和环境变化带来的挑战，我们通过结合数据驱动建模与基于模型的控制方法，利用相对少量的数据实现了对期望轨迹的精确跟踪。该系统采用简单线性模型进行表征，并引入高斯过程（GP）来捕获和估计扰动。随后，将该扰动增强模型集成到模型预测控制器（MPC）中。所提方法在仿真和实验环境中均展现出优异的性能，展示了其在复杂环境中实现微型机器人精确可靠控制的潜力。