A Mobile Magnetic Manipulation Platform for Gastrointestinal Navigation with Deep Reinforcement Learning Control

TL;DR

This paper introduces a low-cost, mobile magnetic manipulation platform for gastrointestinal navigation that uses deep reinforcement learning to achieve precise control without complex calibration, enabling rapid deployment and large workspace coverage.

Contribution

The work presents a novel, model-free control system using DRL for magnetic robots, reducing setup time and calibration complexity in GI navigation.

Findings

Achieved RMSE of 1.18 mm on square path

Controlled a 7-mm magnetic capsule in 2D trajectories

Demonstrated effective tracking over a 30 cm by 20 cm workspace

Abstract

Targeted drug delivery in the gastrointestinal (GI) tract using magnetic robots offers a promising alternative to systemic treatments. However, controlling these robots is a major challenge. Stationary magnetic systems have a limited workspace, while mobile systems (e.g., coils on a robotic arm) suffer from a "model-calibration bottleneck", requiring complex, pre-calibrated physical models that are time-consuming to create and computationally expensive. This paper presents a compact, low-cost mobile magnetic manipulation platform that overcomes this limitation using Deep Reinforcement Learning (DRL). Our system features a compact four-electromagnet array mounted on a UR5 collaborative robot. A Soft Actor-Critic (SAC)-based control strategy is trained through a sim-to-real pipeline, enabling effective policy deployment within 15 minutes and significantly reducing setup time. We validated the platform by controlling a 7-mm magnetic capsule along 2D trajectories. Our DRL-based controller achieved a root-mean-square error (RMSE) of 1.18~mm for a square path and 1.50~mm for a circular path. We also demonstrated successful tracking over a clinically relevant, 30 cm * 20 cm workspace. This work demonstrates a rapidly deployable, model-free control framework capable of precise magnetic manipulation in a large workspace,validated using a 2D GI phantom.