MagGAT: Structure-Aware Spatiotemporal Graph Attention for Motor-Induced Magnetic Interference Compensation in Quadruped Robots
Open Access
Abstract
Permanent-magnet synchronous motors enable precise motion control in compact robots, but their leakage fields can corrupt onboard magnetometer measurements. Physics-based compensation is effective under fixed geometric conditions, whereas quadruped locomotion continuously changes the motor–sensor relationship. We propose MagGAT, a structure-aware spatiotemporal graph attention network that estimates compensated magnetic field signals from motor states and near-field measurements. A boom-mounted far-field magnetometer provides a pseudo-reference for supervised training and field-level evaluation. MagGAT combines a global–local dual-branch graph attention module for multi-motor spatial coupling with a gated recurrent unit for temporal disturbance modeling. Experiments on a Unitree Go2 quadruped used synchronized near-field and far-field measurements, joint angles, angular velocities, and commanded torques collected in indoor and outdoor environments. Across three runs with different random seeds, MagGAT achieved mean residual three-axis magnetic field RMSE values of 87.72–89.41 nT across the three test sequences and outperformed a physics-based fixed-parameter model, a static neural network method, and a temporal convolutional baseline. Ablation studies confirmed that both spatial graph modeling and temporal modeling contributed to compensation accuracy. These results support structure-aware spatiotemporal learning for suppressing motor-induced magnetometer interference on compact legged robots.Keywords
Funding Information
- No. 719 Research Institute, China State Shipbuilding Corporation Limited
This publication has 29 references indexed in Scilit:
- Zero Speed Sensorless Scheme for PMSM Drives Using Virtual Flux Signal Injection Based Hybrid Active Flux ObserverIEEE Transactions on Industrial Electronics, 2025
- Harmonic Localization Analysis of Radial Electromagnetic Force in Interior Permanent Magnet Synchronous Motors Influenced by Saliency EffectIEEE Transactions on Energy Conversion, 2025
- MUSE: A Real-Time Multi-Sensor State Estimator for Quadruped RobotsIEEE Robotics and Automation Letters, 2025
- Neural Network Calibration of Airborne Magnetometers2023
- Integration of an Aeromagnetic Measurement System Based on an Unmanned Aerial Vehicle Platform and Its Application in the Exploration of the Ma’anshan Magnetite DepositIEEE Access, 2020
- Advances in real‐world applications for legged robotsJournal of Field Robotics, 2018
- Velocity Measurement Technique for Permanent Magnet Synchronous Motors Through External Stray Magnetic Field SensingIEEE Sensors Journal, 2018
- ANYmal - toward legged robots for harsh environmentsAdvanced Robotics, 2017
- Small Signal Compensation of Magnetic Fields Resulting from Aircraft ManeuversIEEE Transactions on Aerospace and Electronic Systems, 1979
- Identification and Evaluation of Magnetic-Field Sources of Magnetic Airborne Detector Equipped AircraftIRE Transactions on Aeronautical and Navigational Electronics, 1961