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

2025-11-26

AI Summary

Existing flexible non-contact manipulation techniques are largely restricted to microgram- to milligram-scale objects, failing to achieve precise three-dimensional control of gram-scale payloads. This paper proposes a deep reinforcement learning–based magnetic levitation system. A numerically optimized asymmetric electromagnetic coil configuration is designed, and an action-space remapping mechanism is introduced to mitigate sample sparsity and policy convergence difficulties arising from strong magnetic field nonlinearities. Crucially, the method achieves stable two- and three-dimensional non-contact manipulation of gram-scale objects without requiring prior physical modeling. Experiments demonstrate cross-task generalization: the system accurately transports objects along previously untrained trajectories. Moreover, both hardware architecture and control algorithm exhibit scalability toward hundred-gram payloads. This work establishes a novel paradigm for industrial-grade flexible manipulation.

Technology Category

• Intelligent Robots: Manipulation
• Multiagent Systems: Multiagent Learning
• Search and Optimization: Learning to Search

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

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.

Problem

• Extends non-contact manipulation from microscopic to gram-scale objects
• Overcomes magnetic field nonlinearity using deep reinforcement learning
• Provides scalable framework for industrial robotic manipulation systems

Innovation

• Magnetic levitation system for gram-scale manipulation
• Deep reinforcement learning for complex control strategies
• Electromagnet arrangement optimized through numerical analysis