Maglev-Pentabot: Magnetic Levitation System for Non-Contact Manipulation using Deep Reinforcement Learning

• URL: http://arxiv.org/abs/2511.21149v1
• Date: Wed, 26 Nov 2025 08:10:59 GMT
• Title: Maglev-Pentabot: Magnetic Levitation System for Non-Contact Manipulation using Deep Reinforcement Learning
• Abstract summary: 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.
• Score: 6.530215277181797
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Non-contact manipulation has emerged as a transformative approach across various industrial fields. However, current flexible 2D and 3D non-contact manipulation techniques are often limited to microscopic scales, typically controlling objects in the milligram range. In this paper, we present a magnetic levitation system, termed Maglev-Pentabot, designed to address this limitation. The Maglev-Pentabot leverages deep reinforcement learning (DRL) to develop complex control strategies for manipulating objects in the gram range. Specifically, we propose an electromagnet arrangement optimized through numerical analysis to maximize controllable space. Additionally, an action remapping method is introduced to address sample sparsity issues caused by the strong nonlinearity in magnetic field intensity, hence allowing the DRL controller to converge. Experimental results demonstrate flexible manipulation capabilities, and notably, our system can generalize to transport tasks it has not been explicitly trained for. Furthermore, our approach can be scaled to manipulate heavier objects using larger electromagnets, offering a reference framework for industrial-scale robotic applications.

Related papers

• T-Rex: Tactile-Reactive Dexterous Manipulation [139.71263755530654]
  We introduce a variable-rate Mixture-of-Transformers (MoT) architecture equipped with a novel temporal tactile VQ-VAE encoder.<n>We demonstrate the effectiveness of tactile-reactive policies on 12 manipulation tasks requiring delicate force control and deformable object manipulation.
  arXiv  Detail & Related papers  (2026-06-15T17:59:55Z)
• ULTRA: Unified Multimodal Control for Autonomous Humanoid Whole-Body Loco-Manipulation [55.467742403416175]
  We introduce a physics-driven neural algorithm that translates large-scale motion capture to humanoid embodiments.<n>We learn a unified multimodal controller that supports both dense references and sparse task specifications.<n>Results show that ULTRA generalizes to autonomous, goal-conditioned whole-body loco-manipulation from egocentric perception.
  arXiv  Detail & Related papers  (2026-03-03T18:59:29Z)
• From Transportation to Manipulation: Transforming Magnetic Levitation to Magnetic Robotics [0.0]
  This paper introduces the 6D-Platform MagBot, a low-cost six degrees of freedom parallel kinematic that couples two movers into a composite robotic platform.<n> Experiments show that the 6D-Platform MagBot achieves sub-millimeter positioning accuracy and supports fully autonomous pick up and drop off.<n>This work advances Magnetic Levitation towards Magnetic Robotics, enabling manufacturing solutions that are more agile, efficient, and adaptable.
  arXiv  Detail & Related papers  (2026-03-02T15:37:34Z)
• A Precise Real-Time Force-Aware Grasping System for Robust Aerial Manipulation [5.804333840515478]
  Aerial manipulation requires force-aware capabilities to enable safe and effective grasping and physical interaction.<n>We propose a novel force-aware grasping framework incorporating six low-cost, sensitive skin-like tactile sensors.<n>The proposed framework enables precise force-aware grasping control, allowing safe manipulation of fragile objects and real-time weight measurement of grasped items.
  arXiv  Detail & Related papers  (2026-02-09T12:40:34Z)
• A Mobile Magnetic Manipulation Platform for Gastrointestinal Navigation with Deep Reinforcement Learning Control [7.422367337001037]
  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.
  arXiv  Detail & Related papers  (2026-01-22T00:30:11Z)
• Magnetic field estimation using Gaussian process regression for interactive wireless power system design [6.102646086243458]
  Wireless power transfer with coupled resonators offers a promising solution for the seamless powering of electronic devices.<n>Interactive design approaches that visualize the magnetic field and power transfer efficiency can facilitate the understanding and exploration of these systems.<n>We introduce a machine learning approach using Gaussian Process Regression (GPR), demonstrating for the first time the rapid estimation of the entire magnetic field and power transfer efficiency for near-field coupled systems.
  arXiv  Detail & Related papers  (2025-10-22T06:26:38Z)
• Dexplore: Scalable Neural Control for Dexterous Manipulation from Reference-Scoped Exploration [58.4036440289082]
  Hand-object motion-capture (MoCap) offer large-scale, contact-rich demonstrations and hold promise for dexterous robotic scopes.<n>We introduce Dexplore, a unified single-loop optimization that performs repositories and tracking to learn robot control policies directly from MoCap at scale.
  arXiv  Detail & Related papers  (2025-09-11T17:59:07Z)
• End-to-End Low-Level Neural Control of an Industrial-Grade 6D Magnetic Levitation System [0.0]
  This paper presents the first neural controller for 6D magnetic levitation.<n>Trained end-to-end on interaction data from a proprietary controller, it directly maps raw sensor data and 6D reference poses to coil current commands.<n>Results underscore the practical feasibility of learning-based neural control in complex physical systems.
  arXiv  Detail & Related papers  (2025-09-01T11:33:30Z)
• Machine learning assisted tracking of magnetic objects using quantum diamond magnetometry [33.7054351451505]
  Remote magnetic sensing can be used to monitor the position of objects in real-time.<n>In this work, we demonstrate a Machine Learning (ML) method that can be trained exclusively on experimental data.<n>Our results open up the possibility to apply this ML method more generally for real-time monitoring of magnetic objects.
  arXiv  Detail & Related papers  (2025-02-20T16:11:38Z)
• Characterisation of a levitated sub-mg ferromagnetic cube in a planar alternating-current magnetic Paul trap [0.0]
  We characterize a sub-mgmagnetic cube levitated in an alternating-current planar magnetic Paul trap at room temperature. This technique sets out a path for MHz librational modes in the micron-sized particle limit, allowing for magnetic coupling to superconducting circuits and spin-based quantum systems.
  arXiv  Detail & Related papers  (2024-08-13T11:54:34Z)
• Stable magnetic levitation of soft ferromagnets for macroscopic quantum mechanics [0.0]
  We propose a system for passive magnetic levitation and three-dimensional harmonic trapping of soft ferromagnets. The utilization of soft ferromagnet's internal collective spin excitation may allow quantum mechanical phenomena with particles as large as the sub-millimeter-scale.
  arXiv  Detail & Related papers  (2023-03-31T07:22:49Z)
• Multi-Scale Control Signal-Aware Transformer for Motion Synthesis without Phase [72.01862340497314]
  We propose a task-agnostic deep learning method, namely Multi-scale Control Signal-aware Transformer (MCS-T) MCS-T is able to successfully generate motions comparable to those generated by the methods using auxiliary information.
  arXiv  Detail & Related papers  (2023-03-03T02:56:44Z)
• Output Feedback Tube MPC-Guided Data Augmentation for Robust, Efficient Sensorimotor Policy Learning [49.05174527668836]
  Imitation learning (IL) can generate computationally efficient sensorimotor policies from demonstrations provided by computationally expensive model-based sensing and control algorithms. In this work, we combine IL with an output feedback robust tube model predictive controller to co-generate demonstrations and a data augmentation strategy to efficiently learn neural network-based sensorimotor policies. We numerically demonstrate that our method can learn a robust visuomotor policy from a single demonstration--a two-orders of magnitude improvement in demonstration efficiency compared to existing IL methods.
  arXiv  Detail & Related papers  (2022-10-18T19:59:17Z)
• Surpassing the Energy Resolution Limit with ferromagnetic torque sensors [55.41644538483948]
  We evaluate the optimal magnetic field resolution taking into account the thermomechanical noise and the mechanical detection noise at the standard quantum limit. We find that the Energy Resolution Limit (ERL), pointed out in recent literature, can be surpassed by many orders of magnitude.
  arXiv  Detail & Related papers  (2021-04-29T15:44:12Z)
• Ferromagnetic Gyroscopes for Tests of Fundamental Physics [49.853792068336034]
  A ferromagnetic gyroscope (FG) is a ferromagnet whose angular momentum is dominated by electron spin polarization and that will precess under the action of an external torque. We model and analyze FG dynamics and sensitivity, focusing on practical schemes for experimental realization.
  arXiv  Detail & Related papers  (2020-10-17T07:13:50Z)
• 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.