ORCID iD
Dey - https://orcid.org/0009-0001-4180-2697
Sahoo - https://orcid.org/0000-0001-6113-3278
Narayanan - https://orcid.org/0000-0002-9505-7143
Document Type
Article
Subject Area(s)
Robotics, Control Systems, Neural Networks
Abstract
Safe control of human-in-the-loop (HIL) robotic manipulators is critical for applications such as assistive robotics, teleoperation in hazardous environments, and collaborative manufacturing. However, this remains challenging due to the lack of a unified framework that simultaneously addresses safety constraints, external disturbances, unmodeled dynamics, and dynamic role switching in the HIL setting. In this paper, we propose a novel NN-driven HIL control framework in which human–robot dyadic interaction occurs through the haptic channel. Using Lyapunov stability analysis, we theoretically show that the proposed NN-based controller ensures accurate joint trajectory tracking, compensates for system uncertainties, and adapts to human inputs modeled as external forces on robot joints, thereby enabling seamless role transitions. Furthermore, we enforce safety through control barrier function (CBF)-based torques that guarantee joint positions and velocities remain within prescribed safe sets. Unlike prior approaches that assume known dynamics or focus solely on or adaptability, our framework achieves model-free, disturbance-resilient, and safety-certified HIL control. Using numerical simulations in representative human-robot interaction scenarios and extensive comparative analysis, we validate the effectiveness of the proposed data-driven control method in ensuring safe, adaptive, and stable control.
Digital Object Identifier (DOI)
Publication Info
Preprint version IEEE Transactions on Industrial Informatics, 2025.
APA Citation
Dey, R., Sahoo, A., & Narayanan, V. (2026). Safe data-enabled control of human-in-the-loop robotic manipulator systems. IEEE Transactions on Industrial Informatics, 22(2), 1529–1539. https://doi.org/10.1109/tii.2025.3628219
Rights
© 2026 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.