Gathering Physical Particles with a Global Magnetic Field Using Reinforcement Learning
Gathering Physical Particles with a Global Magnetic Field Using Reinforcement Learning
复制标题
DOI：
10.1109/iros47612.2022.9982256
复制
发表时间：
2022-10
期刊：
影响因子：
--
通讯作者：
Matthias Konitzny;Yitong Lu;J. Leclerc;S. Fekete;Aaron T. Becker
中科院分区：
文献类型：
--
作者：
Matthias Konitzny;Yitong Lu;J. Leclerc;S. Fekete;Aaron T. Becker
对于靶向治疗递送和干预中的生物医学应用，大量的微米级颗粒（“试剂”）必须通过迷宫状环境（“血管系统”）移动到目标区域（“肿瘤”）。由于有限的机载能力，这些代理人不能自主移动;相反，他们是由一个外部的全球性的力量，统一作用于所有粒子的控制。在这项工作中，我们演示了如何使用随时间变化的磁场来收集粒子到所需的位置。我们使用强化学习来训练网络，以有效地收集粒子。解释了克服模拟与现实差距的方法，并将训练好的网络部署在一组迷宫和目标位置上。硬件实验表明，快速收敛，传感器和驱动噪声的鲁棒性。为了鼓励扩展并作为强化学习社区的基准，代码可在Github上获得。
For biomedical applications in targeted therapy delivery and interventions, a large swarm of micro-scale particles (“agents”) has to be moved through a maze-like environment (“vascular system”) to a target region (“tumor”). Due to limited on-board capabilities, these agents cannot move autonomously; instead, they are controlled by an external global force that acts uniformly on all particles. In this work, we demonstrate how to use a time-varying magnetic field to gather particles to a desired location. We use reinforcement learning to train networks to efficiently gather particles. Methods to overcome the simulation-to-reality gap are explained, and the trained networks are deployed on a set of mazes and goal locations. The hardware experiments demonstrate fast convergence, and robustness to both sensor and actuation noise. To encourage extensions and to serve as a benchmark for the reinforcement learning community, the code is available at Github.