MagServo: Uncertainty-Resilient Hierarchical Magnetic Servoing via Learned Latent Representations

2026-10-05

AI Summary

This study addresses the accuracy degradation in magnetic navigation control caused by modeling errors and noise interference. To overcome this, we propose a hierarchical learning framework based on latent magnetic features that achieves robust six-degree-of-freedom servo control without requiring explicit models or Jacobian supervision. Specifically, a masked autoencoder is employed to learn uncertainty-robust representations via reconstruction, effectively capturing state-dependent interaction dynamics. These representations are then integrated with nonlinear model predictive control (NMPC) and local Jacobian inversion to construct a hierarchical control strategy. Experimental results demonstrate that the proposed method outperforms baseline approaches in complex trajectory tracking tasks and generalizes to unseen configurations without retraining, achieving sub-millimeter positioning accuracy of 0.386 mm.

Abstract

Magnetic navigation provides contact-free and line-of-sight-independent feedback for robotic systems, yet existing approaches typically rely on explicit pose estimation or direct use of raw magnetic measurements, making accurate control susceptible to modeling errors, measurement noise, and disturbances. This work presents MagServo, a hierarchical learning-based framework for robust 6-DoF magnetic servoing directly using the learned latent magnetic feature. MagServo learns uncertainty-resilient magnetic representations through masked reconstruction and captures state-dependent interaction dynamics between robot motion and latent magnetic transitions without analytical magnetic models or explicit Jacobian supervision. Based on the learned dynamics, a hierarchical controller combines nonlinear model predictive control for coarse approach with local Jacobian inversion for precise fine regulation. Extensive physical experiments demonstrate submillimeter and subdegree accuracy, achieving mean terminal errors of 0.386 mm and 0.479 degree for 6-DoF pose reaching. MagServo further outperforms a localization-based control baseline in complex trajectory tracking and maintains robust performance under unseen magnetic-source configurations without retraining. A supplementary video of the real-robot experiments is available at https://youtu.be/rZt1NUP1Mr0.

Problem

• magnetic servoing
• uncertainty resilience
• 6-DoF control
• magnetic navigation
• robotic control

Innovation

• Magnetic Servoing
• Latent Representations
• Hierarchical Control
• Masked Reconstruction
• Model Predictive Control