Zi-Yuan Dong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zi-Yuan Dong has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Linlin Ou
Zhejiang University of Technology
3 shared publications - Xinyi Yu
Zhejiang University of Technology
3 shared publications - Jun-Wei Zhu
Zhejiang University of Technology
1 shared publication Juntong Chen
Special Equipment Institute, Hangzhou Vocational and Technical College, China
1 shared publication- Libo Zhou
College of Information Engineering, Zhejiang University of Technology, Hangzhou, China
1 shared publication Linlin Ou
College of Information Engineering, Zhejiang University of Technology, China
1 shared publication
Latest Publications
- 8 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (8) , 9064-9071
Prescribed Performance-Based Data-Driven Adaptive Admittance Control for Physical Human-Robot Interaction
It has been a critical challenge to provide reliable performance constraints while ensuring safe stability for robotic systems, particularly in relatively complex human-robot interaction tasks. To overcome the limitation in traditional controllers where control accuracy is highly dependent on the dynamic model, a novel neural network-based data-driven sliding mode controller (NNDSMC) is proposed. It optimizes control strategies in real time by constructing a dynamic data model while considering interaction forces. On this basis, a data-driven prescribed performance control (DPPMC) method is proposed based on quadratic programming (QP), where faster transient response and greater steady-state tracking accuracy are guaranteed with the designed data-driven high-order control barrier function (DHCBF). To further realize compliant human-robot interaction, a novel data-driven adaptive admittance controller is developed, which combines the flexibility of model predictive control with the fast convergence of DPPMC. The whole design process does not involve any model information. The feasibility of the proposed method is validated through the Franka-Panda robot with seven degrees of freedom.
- 8 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (8) , 9064-9071
Prescribed Performance-Based Data-Driven Adaptive Admittance Control for Physical Human-Robot Interaction
It has been a critical challenge to provide reliable performance constraints while ensuring safe stability for robotic systems, particularly in relatively complex human-robot interaction tasks. To overcome the limitation in traditional controllers where control accuracy is highly dependent on the dynamic model, a novel neural network-based data-driven sliding mode controller (NNDSMC) is proposed. It optimizes control strategies in real time by constructing a dynamic data model while considering interaction forces. On this basis, a data-driven prescribed performance control (DPPMC) method is proposed based on quadratic programming (QP), where faster transient response and greater steady-state tracking accuracy are guaranteed with the designed data-driven high-order control barrier function (DHCBF). To further realize compliant human-robot interaction, a novel data-driven adaptive admittance controller is developed, which combines the flexibility of model predictive control with the fast convergence of DPPMC. The whole design process does not involve any model information. The feasibility of the proposed method is validated through the Franka-Panda robot with seven degrees of freedom.
- 26 January 2025
- Published by SAGE Publications in Transactions of the Institute of Measurement and Control
- Vol. 48 (7) , 1223-1237
Adaptive-constrained admittance control for physical human–robot interaction
In this paper, an adaptive constrained admittance control scheme is proposed, which can effectively solve physical human–robot interaction (pHRI) tasks with output constraints. To ensure the safety of robot behavior, the constraint controller is designed in the trajectory planning layer and the control layer. The asymmetric soft saturation function (ASSF) is designed to obtain variable compliant motion trajectories generated from the desired admittance model. In addition, the controller based on the asymmetric integral barrier Lyapunov function (AIBLF) is designed to deal directly with asymmetric Cartesian space constraints. Finally, radial basis function neural network (RBFNN) is utilized to approximate the dynamics uncertainty of the robot manipulator and to improve the tracking accuracy. According to the Lyapunov stability principles, it can be proved that all states of the closed-loop system are semi-globally uniformly ultimately bounded (SGUUB). Finally, the effectiveness of the proposed control scheme is demonstrated by several simulations and experiments.
- 26 January 2025
- Published by SAGE Publications in Transactions of the Institute of Measurement and Control
- Vol. 48 (7) , 1223-1237
Adaptive-constrained admittance control for physical human–robot interaction
In this paper, an adaptive constrained admittance control scheme is proposed, which can effectively solve physical human–robot interaction (pHRI) tasks with output constraints. To ensure the safety of robot behavior, the constraint controller is designed in the trajectory planning layer and the control layer. The asymmetric soft saturation function (ASSF) is designed to obtain variable compliant motion trajectories generated from the desired admittance model. In addition, the controller based on the asymmetric integral barrier Lyapunov function (AIBLF) is designed to deal directly with asymmetric Cartesian space constraints. Finally, radial basis function neural network (RBFNN) is utilized to approximate the dynamics uncertainty of the robot manipulator and to improve the tracking accuracy. According to the Lyapunov stability principles, it can be proved that all states of the closed-loop system are semi-globally uniformly ultimately bounded (SGUUB). Finally, the effectiveness of the proposed control scheme is demonstrated by several simulations and experiments.
- 24 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-11
A Novel Data-Driven-Based Anti-Disturbance Fault-Tolerant Control Method With Application to Franka-Panda Robot
Sensor faults have always been an essential and challenging problem in data-driven fault-tolerant control (DDFTC). Nevertheless, few studies in DDFTC have simultaneously considered the FTC problem under disturbance. To address the issue with both measurement noise and sensor fault, an iterative learning-based fault-tolerant control strategy (ILFTC) is presented when dynamics are completely unknown. Firstly, an improved data-based unscented Kalman filter mechanism is designed for the FTC scheme, which enhances the feasibility of the data-driven approaches under measurement disturbance. Then, the adaptive estimation algorithm with a switching mechanism is designed to improve the flexibility of the controller. Furthermore, a data-driven fault detection method is constructed under the framework of broad learning system (BLS), which improves the detection accuracy while avoiding the need for precise model parameters in designing the fault detection observer. Finally, simulations and an application to the Franka-Panda robot demonstrate the superiority of the presented algorithm. Compared with the existing DDFTC schemes, smaller tracking error and superior data signal-to-noise ratio can be obtained.
- 24 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-11
A Novel Data-Driven-Based Anti-Disturbance Fault-Tolerant Control Method With Application to Franka-Panda Robot
Sensor faults have always been an essential and challenging problem in data-driven fault-tolerant control (DDFTC). Nevertheless, few studies in DDFTC have simultaneously considered the FTC problem under disturbance. To address the issue with both measurement noise and sensor fault, an iterative learning-based fault-tolerant control strategy (ILFTC) is presented when dynamics are completely unknown. Firstly, an improved data-based unscented Kalman filter mechanism is designed for the FTC scheme, which enhances the feasibility of the data-driven approaches under measurement disturbance. Then, the adaptive estimation algorithm with a switching mechanism is designed to improve the flexibility of the controller. Furthermore, a data-driven fault detection method is constructed under the framework of broad learning system (BLS), which improves the detection accuracy while avoiding the need for precise model parameters in designing the fault detection observer. Finally, simulations and an application to the Franka-Panda robot demonstrate the superiority of the presented algorithm. Compared with the existing DDFTC schemes, smaller tracking error and superior data signal-to-noise ratio can be obtained.
- 13 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 29 (2) , 1331-1341
A New Reinforcement Learning Fault-Tolerant Tracking Control Method With Application to Baxter Robot
The fault-tolerant control problem of the flexible multijoint manipulator is a difficult issue due to its strong nonlinearity and coupling. This article proposes a reinforcement learning (RL) based model-free adaptive fault-tolerant control (MFAFTC) algorithm for the multi-joint manipulator. First, a parameter estimation mode switching mechanism is designed based on the two dimensions of the time axis and the sampling period, where an iterative estimation structure is introduced to identify some key parameters online accurately. Meanwhile, the radial basis function neural network is used to identify the spring interference as well as actuator fault, and a compensation fault-tolerant control strategy is proposed. Moreover, the computation complexity is optimized via designing the critic–actor mechanism with an event-trigger parameter selection strategy. Finally, the superiority and effectiveness of the proposed method are verified by the application to the Baxter robot.
- 13 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 29 (2) , 1331-1341
A New Reinforcement Learning Fault-Tolerant Tracking Control Method With Application to Baxter Robot
The fault-tolerant control problem of the flexible multijoint manipulator is a difficult issue due to its strong nonlinearity and coupling. This article proposes a reinforcement learning (RL) based model-free adaptive fault-tolerant control (MFAFTC) algorithm for the multi-joint manipulator. First, a parameter estimation mode switching mechanism is designed based on the two dimensions of the time axis and the sampling period, where an iterative estimation structure is introduced to identify some key parameters online accurately. Meanwhile, the radial basis function neural network is used to identify the spring interference as well as actuator fault, and a compensation fault-tolerant control strategy is proposed. Moreover, the computation complexity is optimized via designing the critic–actor mechanism with an event-trigger parameter selection strategy. Finally, the superiority and effectiveness of the proposed method are verified by the application to the Baxter robot.