The paper proposes a low-cost teleoperation system using wearable inertial measurement units (IMUs) to securely and responsively control a robotic arm. The system employs a machine-learning approach for authentication using logistic regression on time series data from the IMUs during handling tasks. Experiments with 16 operators performing three handling tasks demonstrate that random forest outperforms other classifiers in task identification, achieving a macro F1-score of 75.60%. Logistic regression performs best in user identification and authentication tasks, achieving an average Equal Error Rate of approximately 8.89%. The system highlights the potential for biometric-based teleoperation to advance consumer technology applications in healthcare, IoT, and immersive environments.
The system uses wearable IMU sensors to capture motion data during robotic arm teleoperation. A machine learning pipeline performs task recognition (classifying handling tasks using Random Forest) and user authentication (verifying operator identity using Logistic Regression on time series features). The approach enables secure, biometric-based control of robotic manipulators.
@article{stan2025authenticated,
title={Authenticated Robotic Teleoperation with Task Recognition},
author={Stan, Ionel Eduard and Amrani, Hamza and Napoletano, Paolo and D'Auria, Daniela},
journal={IEEE Consumer Electronics Magazine},
volume={15},
number={1},
pages={33--40},
year={2025},
doi={10.1109/MCE.2025.3546049},
publisher={IEEE}
}