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

• URL: http://arxiv.org/abs/2601.15545v1
• Date: Thu, 22 Jan 2026 00:30:11 GMT
• Title: A Mobile Magnetic Manipulation Platform for Gastrointestinal Navigation with Deep Reinforcement Learning Control
• Abstract summary: This paper presents a compact, low-cost mobile magnetic manipulation platform that overcomes this limitation using Deep Reinforcement Learning (DRL)<n>A Soft Actor-Critic (SAC)-based control strategy is trained through a sim-to-real pipeline, enabling effective policy deployment within 15 minutes.<n>We validated the platform by controlling a 7-mm magnetic capsule along 2D trajectories.
• Score: 7.422367337001037
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• PAKE: Learning Whole-Body Loco-Manipulation with Partial Kinematic Embeddings [9.606500800831322]
  We propose a novel whole-body control framework for high-precision loco-manipulation.<n>We introduce a new Kinematic Normalizing Flow model, trained on a large-scale kinematic dataset.<n>We validate our approach on the quadrupedal robot equipped with a six-DoF robotic arm.
  arXiv  Detail & Related papers  (2026-07-13T03:12:09Z)
• Mag-VLA: Vision-Language-Action Model for Bimanual Magnetically Actuated Microrobot Manipulation [6.712605140495474]
  We propose Mag-VLA, a vision-language-action (VLA) model for dexterous magnetic microrobot manipulation.<n>Our framework adapts a Qwen2.5-VL-7B backbone using Low-Rank Adaptation (LoRA) to process visual observations and language instructions for action prediction.<n>In real-robot experiments, Mag-VLA achieves a 90% approach success rate across all tasks and transport success rates of 80%, 70%, and 50% as task difficulty increases.
  arXiv  Detail & Related papers  (2026-05-27T13:44:00Z)
• Pitch Angle Control of a Magnetically Actuated Capsule Robot with Nonlinear FEA-based MPC and EKF Multisensory Fusion [0.3694429692322632]
  This paper presents a model-based framework for magnetic pitch control of an ingestible capsule robot actuated by a four-coil electromagnetic array.<n>Experiments on a compliant stomach-inspired surface demonstrate robust pitch reorientation from both horizontal and upright configurations.<n>These results establish finite-element-informed MPC with sensor fusion as a scalable strategy for pitch regulation, controlled docking, and future multi-degree-of-freedom capsule locomotion.
  arXiv  Detail & Related papers  (2026-02-11T07:59:52Z)
• NanoCockpit: Performance-optimized Application Framework for AI-based Autonomous Nanorobotics [50.594459728605734]
  Small form factor, i.e., a few 10s grams, severely limits onboard computational resources to sub-SI100milliwatt microcontroller units (MCUs)<n>Our framework achieves ideal end-to-end latency, i.e. zero overhead due to serialized tasks, delivering quantifiable improvements in closed-loop control performance.
  arXiv  Detail & Related papers  (2026-01-12T12:29:38Z)
• Maglev-Pentabot: Magnetic Levitation System for Non-Contact Manipulation using Deep Reinforcement Learning [6.530215277181797]
  We present a magnetic levitation system, termed Maglev-Pentabot, designed to address non-contact manipulation limitations.<n>The Maglev-Pentabot leverages deep reinforcement learning to develop complex control strategies for manipulating objects in the gram range.<n>Our system can be scaled to manipulate heavier objects using larger electromagnets, offering a reference framework for industrial-scale robotic applications.
  arXiv  Detail & Related papers  (2025-11-26T08:10:59Z)
• Training on the Fly: On-device Self-supervised Learning aboard Nano-drones within 20 mW [52.280742520586756]
  Miniaturized cyber-physical systems (CPSes) powered by tiny machine learning (TinyML), such as nano-drones, are becoming an increasingly attractive technology. Simple electronics make these CPSes inexpensive, but strongly limit the computational, memory, and sensing resources available on board. We present a novel on-device fine-tuning approach that relies only on the limited ultra-low power resources available aboard nano-drones.
  arXiv  Detail & Related papers  (2024-08-06T13:11:36Z)
• Reaching the Limit in Autonomous Racing: Optimal Control versus Reinforcement Learning [66.10854214036605]
  A central question in robotics is how to design a control system for an agile mobile robot. We show that a neural network controller trained with reinforcement learning (RL) outperformed optimal control (OC) methods in this setting. Our findings allowed us to push an agile drone to its maximum performance, achieving a peak acceleration greater than 12 times the gravitational acceleration and a peak velocity of 108 kilometers per hour.
  arXiv  Detail & Related papers  (2023-10-17T02:40:27Z)
• Navigation of micro-robot swarms for targeted delivery using reinforcement learning [0.0]
  We use the Reinforcement Learning (RL) algorithms Proximal Policy Optimization (PPO) and Robust Policy Optimization (RPO) to navigate a swarm of 4, 9 and 16 microswimmers. We look at both PPO and RPO performances with limited state information scenarios and also test their robustness for random target location and size.
  arXiv  Detail & Related papers  (2023-06-30T12:17:39Z)
• Real-Time Model-Free Deep Reinforcement Learning for Force Control of a Series Elastic Actuator [56.11574814802912]
  State-of-the art robotic applications utilize series elastic actuators (SEAs) with closed-loop force control to achieve complex tasks such as walking, lifting, and manipulation. Model-free PID control methods are more prone to instability due to nonlinearities in the SEA. Deep reinforcement learning has proved to be an effective model-free method for continuous control tasks.
  arXiv  Detail & Related papers  (2023-04-11T00:51:47Z)
• Robust, High-Rate Trajectory Tracking on Insect-Scale Soft-Actuated Aerial Robots with Deep-Learned Tube MPC [0.0]
  We present an approach for agile and computationally efficient trajectory tracking on the MIT SoftFly, a sub-gram MAV (0.7 grams) Our strategy employs a cascaded control scheme, where an adaptive attitude controller is combined with a neural network policy trained to imitate a trajectory tracking robust tube model predictive controller (RTMPC) We experimentally evaluate our approach, achieving position Root Mean Square Errors lower than 1.8 cm even in the more challenging maneuvers, obtaining a 60% reduction in maximum position error compared to our previous work, and robustness demonstrating to large external disturbances.
  arXiv  Detail & Related papers  (2022-09-20T21:30:16Z)
• OSCAR: Data-Driven Operational Space Control for Adaptive and Robust Robot Manipulation [50.59541802645156]
  Operational Space Control (OSC) has been used as an effective task-space controller for manipulation. We propose OSC for Adaptation and Robustness (OSCAR), a data-driven variant of OSC that compensates for modeling errors. We evaluate our method on a variety of simulated manipulation problems, and find substantial improvements over an array of controller baselines.
  arXiv  Detail & Related papers  (2021-10-02T01:21:38Z)
• ReLMoGen: Leveraging Motion Generation in Reinforcement Learning for Mobile Manipulation [99.2543521972137]
  ReLMoGen is a framework that combines a learned policy to predict subgoals and a motion generator to plan and execute the motion needed to reach these subgoals. Our method is benchmarked on a diverse set of seven robotics tasks in photo-realistic simulation environments. ReLMoGen shows outstanding transferability between different motion generators at test time, indicating a great potential to transfer to real robots.
  arXiv  Detail & Related papers  (2020-08-18T08:05:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.