Zhihuan Hu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zhihuan Hu has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Weidong Zhang
Hainan University
11 shared publications - Hongtian Chen
Shanghai Jiao Tong University
3 shared publications - Li Li
Department of Control Science and Engineering, College of Electronics and Information Engineering, State Key Laboratory of Autonomous Intelligent Unmanned System, Frontiers Science Center for Intelligent Autonomous Systems, Ministry of Education, Shanghai Research Institute for Intelligent Autonomous Systems, and Shanghai Institute of Intelligent Science and Technology, Tongji University, Shanghai, China
2 shared publications - Ruonan Liu
School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China
2 shared publications - Wei Xie
Department of Automation, Shanghai Jiao Tong University, Shanghai, China
2 shared publications Andy Wang
DNV GL Oil & Gas, Shanghai, China
1 shared publication
Latest Publications
- 15 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 56 (2) , 790-799
Event-Triggered Zero-Sum Game for Safety Control of Autonomous Surface Vehicles
This article investigates the problem of disturbance attenuation for autonomous surface vehicles (ASVs) subject to asymmetric time-varying saturation. To address this challenge, we propose a novel event-triggered (ET) zero-sum (ZS) differential game framework that integrates a barrier function and a nonquadratic value function, enabling simultaneous achievement of safety control and disturbance attenuation. Initially, by designing a barrier function, the control problem of the asymmetric time-varying saturated ASV system is transformed into an unsaturated form. Afterward, a nonquadratic value function is designed, and ZS games are employed to obtain the saturated-optimal control policy and the worst-case disturbance policy. Then, the ET method is introduced into policy execution and critic neural network learning. The scheme in this article ensures the safety and stability of the ASV while reducing computational burden and meeting the needs of disturbance attenuation. Finally, theoretical analysis and simulation experiments verify the feasibility of the ET ZS differential game approach.
- 15 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 56 (2) , 790-799
Event-Triggered Zero-Sum Game for Safety Control of Autonomous Surface Vehicles
This article investigates the problem of disturbance attenuation for autonomous surface vehicles (ASVs) subject to asymmetric time-varying saturation. To address this challenge, we propose a novel event-triggered (ET) zero-sum (ZS) differential game framework that integrates a barrier function and a nonquadratic value function, enabling simultaneous achievement of safety control and disturbance attenuation. Initially, by designing a barrier function, the control problem of the asymmetric time-varying saturated ASV system is transformed into an unsaturated form. Afterward, a nonquadratic value function is designed, and ZS games are employed to obtain the saturated-optimal control policy and the worst-case disturbance policy. Then, the ET method is introduced into policy execution and critic neural network learning. The scheme in this article ensures the safety and stability of the ASV while reducing computational burden and meeting the needs of disturbance attenuation. Finally, theoretical analysis and simulation experiments verify the feasibility of the ET ZS differential game approach.
- 11 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 55 (11) , 8469-8480
Stochastic Generalized Nash Equilibrium Seeking: Reflected Gradient Methods
This article concerns the stochastic generalized Nash equilibrium problem (NEP) characterized by uncertain expected value cost functions and shared constraints. In a full-decision information setting, we develop a novel distributed stochastic reflected forward–backward (FB) algorithm, which requires that each agent has access to the others’ decisions. Considering that agents only know the decisions from their immediate neighbors, a distributed stochastic RFB (SRFB) algorithm under partial-decision information is proposed. By recasting the problem as a monotone inclusion problem, both algorithms almost surely converge to a stochastic generalized Nash equilibrium by combining the stochastic approximation scheme and the variance reduction scheme. Finally, the numerical experiment validates the feasibility of the proposed algorithms and confirms the correctness of the theory.
- 11 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 55 (11) , 8469-8480
Stochastic Generalized Nash Equilibrium Seeking: Reflected Gradient Methods
This article concerns the stochastic generalized Nash equilibrium problem (NEP) characterized by uncertain expected value cost functions and shared constraints. In a full-decision information setting, we develop a novel distributed stochastic reflected forward–backward (FB) algorithm, which requires that each agent has access to the others’ decisions. Considering that agents only know the decisions from their immediate neighbors, a distributed stochastic RFB (SRFB) algorithm under partial-decision information is proposed. By recasting the problem as a monotone inclusion problem, both algorithms almost surely converge to a stochastic generalized Nash equilibrium by combining the stochastic approximation scheme and the variance reduction scheme. Finally, the numerical experiment validates the feasibility of the proposed algorithms and confirms the correctness of the theory.
- 6 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 55 (5) , 3464-3479
Co-Opetition Network-Based Group Decision-Making Under Incomplete Information
The integration of cooperation and competition strategies in game theory emphasizes the systematic nature of strategy spaces and group interactions, forming the basis for achieving win-win scenarios. This is particularly crucial under coalition constraints and incomplete information. Addressing these challenges, this article introduces a comprehensive mathematical method for policy formation using co-opetition topological networks. This method enables autonomous decision-making and game equilibrium in group decision scenarios, considering individual preferences amidst constraints like incomplete information and alliance limitations. Leveraging the complementary entropy theorem on superiority, inferiority, and fuzzy measures, we propose a cognitive model for information interaction and attribute fusion. Utilizing the ordered weighted averaging operator and average tree solutions aids in identifying optimal alliance structures. We subsequently discuss evaluating missing information to complete the topological network. Updating the cognitive model and value function, we develop a Gaussian oscillation heuristic algorithm to explore alliance and component strategy spaces. Simulation results are provided and analyzed to illustrate the performance and effectiveness of our approach.
- 6 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 55 (5) , 3464-3479
Co-Opetition Network-Based Group Decision-Making Under Incomplete Information
The integration of cooperation and competition strategies in game theory emphasizes the systematic nature of strategy spaces and group interactions, forming the basis for achieving win-win scenarios. This is particularly crucial under coalition constraints and incomplete information. Addressing these challenges, this article introduces a comprehensive mathematical method for policy formation using co-opetition topological networks. This method enables autonomous decision-making and game equilibrium in group decision scenarios, considering individual preferences amidst constraints like incomplete information and alliance limitations. Leveraging the complementary entropy theorem on superiority, inferiority, and fuzzy measures, we propose a cognitive model for information interaction and attribute fusion. Utilizing the ordered weighted averaging operator and average tree solutions aids in identifying optimal alliance structures. We subsequently discuss evaluating missing information to complete the topological network. Updating the cognitive model and value function, we develop a Gaussian oscillation heuristic algorithm to explore alliance and component strategy spaces. Simulation results are provided and analyzed to illustrate the performance and effectiveness of our approach.
- 7 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 74 (6) , 8745-8755
A Composite Observer-Based Optimal Attitude Tracking Control for FWEPAUV via Reinforcement Learning
The foldable wave-energy powered autonomous underwater vehicle (FWEPAUV) is capable of directly generating sufficient electrical energy from seawater when its body aligns perpendicular to the wave flow direction. Its precise attitude control is of vital importance in long-term navigation missions. This article presents a neural network-based adaptive optimized attitude control approach for an FWEPAUV system, considering unmeasurable yaw angular velocity, system uncertainties, and external disturbances. The composite observer and radial basis function neural networks (RBF NNs) are established to estimate the yaw angular velocity, system uncertainties, and disturbances. The estimated signals are then jointly utilized to compensate for the redundant signals in the control channel, thereby enhancing robustness. A composite-observer-actor-critic reinforcement learning architecture is proposed to learn the optimal value function, generate the control torque, and achieve the balance between the control accuracy and cost. The introduced prescribed performance mechanism ensures the smoothness of the FWEPAUV's transient response and the accuracy of the steady-state response while guaranteeing all error signals semi-globally uniformly ultimately bounded (SGUUB). The effectiveness of the developed approach is exemplified via a case study.
- 7 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 74 (6) , 8745-8755
A Composite Observer-Based Optimal Attitude Tracking Control for FWEPAUV via Reinforcement Learning
The foldable wave-energy powered autonomous underwater vehicle (FWEPAUV) is capable of directly generating sufficient electrical energy from seawater when its body aligns perpendicular to the wave flow direction. Its precise attitude control is of vital importance in long-term navigation missions. This article presents a neural network-based adaptive optimized attitude control approach for an FWEPAUV system, considering unmeasurable yaw angular velocity, system uncertainties, and external disturbances. The composite observer and radial basis function neural networks (RBF NNs) are established to estimate the yaw angular velocity, system uncertainties, and disturbances. The estimated signals are then jointly utilized to compensate for the redundant signals in the control channel, thereby enhancing robustness. A composite-observer-actor-critic reinforcement learning architecture is proposed to learn the optimal value function, generate the control torque, and achieve the balance between the control accuracy and cost. The introduced prescribed performance mechanism ensures the smoothness of the FWEPAUV's transient response and the accuracy of the steady-state response while guaranteeing all error signals semi-globally uniformly ultimately bounded (SGUUB). The effectiveness of the developed approach is exemplified via a case study.
- 31 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 32 (11) , 6573-6582
Fault Detection of Unmanned Surface Vehicles: The Fuzzy Multiprocessor Implementation
In this article, we study the fault detection problem of unmanned surface vehicles through the implementation of fuzzy multiprocessors. By employing the Takagi–Sugeno fuzzy technique, the linear approximation of unmanned surface vehicles is obtained, and a fuzzy multiprocessor architecture is proposed to estimate the state of unmanned surface vehicles. With the residual signal generated by multiprocessors, a detection logic is designed to realize the fault detection. Based on the Lyapunov method, sufficient conditions are given to ensure that the error dynamic system is asymptotically stable and meets the given $H_{\infty }$ and $H\_$ performance. Assisted by genetic algorithms, a two-step optimization algorithm is proposed to optimize the mixed $H_{\infty }$ and $H\_$ performance. Finally, case studies are provided to verify the effectiveness and superiority of the proposed method.
- 31 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 32 (11) , 6573-6582
Fault Detection of Unmanned Surface Vehicles: The Fuzzy Multiprocessor Implementation
In this article, we study the fault detection problem of unmanned surface vehicles through the implementation of fuzzy multiprocessors. By employing the Takagi–Sugeno fuzzy technique, the linear approximation of unmanned surface vehicles is obtained, and a fuzzy multiprocessor architecture is proposed to estimate the state of unmanned surface vehicles. With the residual signal generated by multiprocessors, a detection logic is designed to realize the fault detection. Based on the Lyapunov method, sufficient conditions are given to ensure that the error dynamic system is asymptotically stable and meets the given $H_{\infty }$ and $H\_$ performance. Assisted by genetic algorithms, a two-step optimization algorithm is proposed to optimize the mixed $H_{\infty }$ and $H\_$ performance. Finally, case studies are provided to verify the effectiveness and superiority of the proposed method.
- 26 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-9
A Physics-Guided Wavelet Feature Extraction Method for Fault Diagnosis of Thruster Blades
Unmanned Surface Vehicles (USVs) are more environmentally friendly than traditional vessels, reducing emissions and minimizing their impact on aquatic ecosystems. In this paper, a thruster fault diagnosis method based on physics-guided wavelet features is proposed, specifically for application in USVs. First, the transformation coefficient components are computed through wavelet decomposition. Next, the physical components undergo a reconstruction process to obtain segmented transformation signals. Finally, fault-relevant features are extracted and trained using a convolutional neural network, while the unlabeled features are utilized to test the network for thruster fault diagnosis. An experimental platform based on a USV prototype confirmed the validity of this method, demonstrating its superiority over existing methods.
- 26 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-9
A Physics-Guided Wavelet Feature Extraction Method for Fault Diagnosis of Thruster Blades
Unmanned Surface Vehicles (USVs) are more environmentally friendly than traditional vessels, reducing emissions and minimizing their impact on aquatic ecosystems. In this paper, a thruster fault diagnosis method based on physics-guided wavelet features is proposed, specifically for application in USVs. First, the transformation coefficient components are computed through wavelet decomposition. Next, the physical components undergo a reconstruction process to obtain segmented transformation signals. Finally, fault-relevant features are extracted and trained using a convolutional neural network, while the unlabeled features are utilized to test the network for thruster fault diagnosis. An experimental platform based on a USV prototype confirmed the validity of this method, demonstrating its superiority over existing methods.
- 7 August 2024
- Published by Elsevier in Neurocomputing
- Vol. 604
A stochastic primal–dual algorithm for composite constrained optimization
- 7 August 2024
- Published by Elsevier in Neurocomputing
- Vol. 604
A stochastic primal–dual algorithm for composite constrained optimization
- Open Access
- 2 June 2024
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 12 (6) , 933
Graph Search-Based Path Planning for Automatic Ship Berthing
Ship berthing is one of the most challenging operations for crews, involving optimal trajectory generation and intricate harbor maneuvering at low speed. In this paper, we present a practical path-planning method that generates smooth trajectories for an underactuated surface vehicle (USV) traveling in a confined harbor environment. Our approach introduces a Generalized Voronoi Diagram (GVD)-based path planner to handle the unberthing phase. The hybrid A* search-based path finding method is used for the transportation phase. A simple planner based on a Bézier curve is proposed for the berthing phase. To track the target path, an adaptive pure pursuit method and proportional-derivative (PD) controller is used. The performance of the given method is tested numerically and experimentally on a catamaran with a pair of non-steerable thrusters. The results demonstrate that the proposed algorithm can achieve a successful berthing operation through static obstacle handling and smooth trajectory generation.
- 2 June 2024
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 12 (6) , 933
Open AccessGraph Search-Based Path Planning for Automatic Ship Berthing
Ship berthing is one of the most challenging operations for crews, involving optimal trajectory generation and intricate harbor maneuvering at low speed. In this paper, we present a practical path-planning method that generates smooth trajectories for an underactuated surface vehicle (USV) traveling in a confined harbor environment. Our approach introduces a Generalized Voronoi Diagram (GVD)-based path planner to handle the unberthing phase. The hybrid A* search-based path finding method is used for the transportation phase. A simple planner based on a Bézier curve is proposed for the berthing phase. To track the target path, an adaptive pure pursuit method and proportional-derivative (PD) controller is used. The performance of the given method is tested numerically and experimentally on a catamaran with a pair of non-steerable thrusters. The results demonstrate that the proposed algorithm can achieve a successful berthing operation through static obstacle handling and smooth trajectory generation.
- 6 May 2024
- Published by Elsevier in Ocean Engineering
- Vol. 306, 117950
Heterogeneous cross domain coordinated control of ASV-AUV system for maritime search and rescue
- 6 May 2024
- Published by Elsevier in Ocean Engineering
- Vol. 306, 117950
Heterogeneous cross domain coordinated control of ASV-AUV system for maritime search and rescue
- 17 June 2021
- Published by Elsevier in Ocean Engineering
- Vol. 234, 108902
Development of an experimental system for the twin-lift decommissioning operation
- 17 June 2021
- Published by Elsevier in Ocean Engineering
- Vol. 234, 108902
Development of an experimental system for the twin-lift decommissioning operation