Research Output
Articles
Publication Date: 2025
Iranian Conference on Electrical Engineering, ICEE (26429527)pp. 326-331
This paper presents the design of a bilateral robotic system that integrates advanced control strategies to enhance the teleoperation performance. The system employs these strategies to enable smooth bidirectional communication of motion between the master and slave robots. The estimation of environmental interaction and human force eliminates the need for force sensors on both sides. Impedance-based control is utilized to ensure system stability and improve interaction accuracy. The proposed approach demonstrates effective human-environment interaction and precise teleoperation, as validated through simulation re-sults, showcasing its ability to maintain precise synchronization between the master and slave robots while dynamically adapting the estimation parameters. © 2025 IEEE.
Publication Date: 2025
International Journal of Systems Science (00207721)
This study presents the design, comprehensive analysis, and implementation of a nonlinear bilateral telerobotic system operating in a master-slave configuration. It focuses on the critical importance of transparency, which is essential for achieving realistic force feedback in bilateral teleoperation. While some prior research has investigated the concept of transparency in nonlinear systems, this work represents the first attempt to implement variable impedance control, along with real-time parameter estimation through adaptive rules, to achieve transparency in a nonlinear bilateral teleoperation system. The suggested approach combines robust position control with impedance-based force regulation, while an Extended Kalman Filter (EKF) estimates environmental stiffness and damping parameters online. This synthesis enables the system to adapt to variable interaction conditions and maintain stable and high-fidelity force reflection. In addition, the presented stability analysis using the Lyapunov-based approach guarantees the theoretical robustness of the system under various operating conditions. Extensive simulation studies are presented to confirm the potential of the proposed approach, and the implementation results also validate its practical reliability and effectiveness. This makes the system well-suited for advanced teleoperation, haptic interfaces, and other domains requiring precise control and accurate force reflection capabilities. © 2025 Informa UK Limited, trading as Taylor & Francis Group.
Publication Date: 2025
Aut Journal Of Mechanical Engineering (25882937)9(4)pp. 357-372
This paper presents an improved framework for deep reinforcement learning algorithms integrating online system identification, based on the Dyna-Q architecture. The proposed framework is designed to tackle the challenges of both Multi-Input Multi-Output and Multi-Input Single-Output systems in complex, industry-relevant environments, thereby significantly enhancing adaptability and reliability in industrial control systems. It should be noted that in the suggested novel framework, the system identification and model control processes run in parallel with the control process, ensuring a reliable backup in case of faults or disruptions. To verify the efficiency of the aforementioned approach, comparative evaluations in the presence of three of the most common deep reinforcement learning algorithms, i.e. Deep Q Network, Deep Deterministic Policy Gradient, and Twin Delayed Deep Deterministic Policy Gradient, are conducted on industry-relevant environments simulations available in OpenAI Gym, including the Cart Pole, Pendulum, and Bipedal Walker, each chosen to reflect specific aspects of the novel framework. Results demonstrate that the proposed method for leveraging both real and simulated experiences in this framework improves sample efficiency, stability, and robustness. © 2025, Amirkabir University of Technology. All rights reserved.
