Magnet-Aware Control of Legged Robots

J. Playan Garai; S. B. Djuve; C. McGreavy; M. Khadiv

cs.ROOct 6, 2026

Magnet-Aware Control of Legged Robots

Authors: J. Playan Garai, S. B. Djuve, C. McGreavy, M. Khadiv

Organizations: Technical University of Munich (TUM), Munich, Germany · Conseil Europ´een pour la Recherche Nucl´eaire (CERN), BE/CEM/MRO, Geneva, Switzerland

Abstract

Autonomous robots can increase uptime and reduce human exposure in Big Science facilities, but strong magnetic fields needed for their operation corrupt sensors and induce pose-dependent mechanical wrenches that destabilize robots and challenge conventional reactive controllers. This paper presents a control framework for modeling, estimating, and dynamically compensating for spatially varying magnetic wrenches acting on legged robots to improve robustness in these fields. We introduce a custom physics plugin for the MuJoCo simulator to model magnetic forces on rigid-body elements, alongside an inverse field-estimation framework to infer the latent magnetic field directly from quadruped dynamic responses and any number of sensor readings. Furthermore, we develop a Magnet-Aware Model Predictive Control (MPC) and Whole-Body Control (WBC) architecture that predicts and counteracts magnetic perturbations during locomotion to increase the range of magnetic fields in which the robot can operate. The effectiveness of the framework is validated through both simulation and physical hardware experiments. We show our method increases the the maximum rejectable disturbances from magnetic field in the force space by a factor of 2.5 and and between 1.6-2 times in torque space compared to a non-compensated system. Within the proposed magnetic field, this constitutes an increase in the area in which the robot can operate by 29,34% of which 10,84% would have previously caused an immediate collapse to non-compensated controllers.

Figures & tables

Fig. 1: Robot moving through magnetic fields (dashed contour lines) experience induced disturbance wrenches due to their ferromagnetic components. Our method compensates for these disturbances (blue trace), allowing undisturbed movement and greater accessibility in magnetic field environments, where standard controllers would fail, leading to collapse (red trace)

Fig. 2: Block diagram of the proposed pipeline outlining the contributions. We present the pre-existing elements of the pipeline (grey), the components where we have applied modifications (blue, yellow, brown, purple), and the modifications themselves (green).

Fig. 3: Simulation model of our quadruped robotic system. The 12 motor joints are modeled as induced magnetic cylinders (blue disks). Four magnetometers (green) are distributed across the chassis in a tetrahedral configuration. Motion tracker markers (white) correspond to the physical experimental platform. We also represent the base frame (gray) and center of mass (red).

Field	Value	Notes
N	[0.2 0.2 0.6]	Normalized from [ 21 ]
V	$7.6969\text{\times}{10}^{-5}\text{\,}{\mathrm{m}}^{3}$	Obtained from motor CAD
$\mu_{r}$	1000	Pure iron (worst-case scenario)

TABLE I: Defined Magnetic Parameters values for Unitree GO-M8018-6 Motor

Fig. 4: Convergence results for a static magnetic field. We record the robot as it moves through a scene with a magnetic field of norm

0.07\text{\,}\mathrm{T}

. Optimizing over the results, we see that the algorithm eventually converges correctly to the proper magnetic field on the scene.

Fig. 5: MuJoCo simulation scene for coupled field-gradient experiments. As the Unitree Go2 traverses the spherical magnetic region towards the epicenter, spatial field gradients induce increasing physical wrenches on the leg motor assemblies.

Fig. 6: Experimental setup comparison. Right: Close-up of the MuJoCo simulation environment. Left: Physical laboratory testing ground with ground tape bounding the virtual magnetic field perimeter.

Fig. 7: Experimental results comparing uncompensated and compensated controllers. Left: Simulation performance showing maximum trajectory penetration depths into the spherical magnetic field before collapse. Right: Hardware-in-the-loop experiments demonstrating improved dynamic balance and trajectory tracking under virtual field perturbations.

Fig. 8: Simulations showing the resulting magnetic field from a proposed magnetic field for an FCC experiment. At top-down view is presented showcasing both the magnetic field norm (top) and the induced magnetic force norm expected (bottom). We present isodynamic lines at $0.1\text{\,}\mathrm{T}$ (cyan), $0.5\text{\,}\mathrm{T}$ (yellow), and $0.8\text{\,}\mathrm{T}$ (magenta).

Explore similar work

MagServo: Uncertainty-Resilient Hierarchical Magnetic Servoing via Learned Latent Representations
Oct 5, 2026Yuhan Tan, Yameng Zhang, Pei Liu +2Visual Servoing
Department of Bioengineering, Imperial College London, UK. · Department of Mechanical Engineering, The University of Hong Kong, Hong Kong SAR. · School of Computation, Information and Technology, Technical University of Munich, Germany.
Optimized Wrench Polytope Analysis for Real-Time Stability Control of Legged Robots in Complex Multi-Contact Configurations
Sep 15, 2026Friedrich Graaf, Elias Birkefeld, Christian Eichmann +5Legged Robots Torque
FZI Research Center for Information Technology, Karlsruhe, Germany · Machine Intelligence and Robotics Lab (MaiRo), Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany
ReCo: Response-Consistent Locomotion with Policy-Aware MPC for Legged Manipulation
Oct 1, 2026Kuankuan Sima, Yichao Gao, Chenxi Gu +2Agile Locomotion Robotic Manipulation Policies
Department of Electrical and Computer Engineering, National University of Singapore, Singapore 119077, Singapore · Department of Mechanical Engineering, National University of Singapore, Singapore 119077, Singapore

Oct 5, 2026, cs.ROJ/K move · Enter open · S save

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

Yuhan Tan, Yameng Zhang, Pei Liu, Yao Zhong+1

Department of Bioengineering, Imperial College London, UK. · Department of Mechanical Engineering, The University of Hong Kong, Hong Kong SAR. · School of Computation, Information and Technology, Technical University of Munich, Germany.

Visual Servoing

Open paper AskPDF arXiv

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.

Abstract

Explore similar work

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

Optimized Wrench Polytope Analysis for Real-Time Stability Control of Legged Robots in Complex Multi-Contact Configurations

ReCo: Response-Consistent Locomotion with Policy-Aware MPC for Legged Manipulation