This paper addresses the problem of safety-critical path-guided herding control for multiple-input multiple-output multi-agent systems under incomplete state measurement, safety constraints, and limited communication resources. Specifically, an output-feedback finite-time neural predictor is proposed to identify both model uncertainties and unknown state information. Subsequently, a distributed path-guided herding control strategy is designed, including patrolling, gathering, enclosing, and expelling. Control barrier functions are formulated as safety constraints, and a quadratic optimization problem is established. By using the neurodynamic optimization to solve the optimization problem, the optimal control law satisfying both safety constraints and state constraints is generated. Furthermore, a dynamic event-triggered communication method is proposed to reduce unnecessary communication, especially during the transient phase. By using the proposed herding control approach, the collision-free herding is guaranteed for input-to-state stability, and simulation results are provided to demonstrate the effectiveness of the approach.

Autonomous surface vehicles (ASVs) present considerable perception difficulties as small targets amidst complex maritime environments. Existing methods suffer from insufficient feature extraction, difficulties in estimating arbitrary orientations, and high computational demands on resource-constrained platforms. To address these bottlenecks, an efficient ASV-YOLO framework based on oriented bounding box (OBB) perception is proposed. First, a comprehensive ASV dataset is constructed via real–virtual fusion to provide a standardized evaluation benchmark. In the feature extraction network, a Dynamic Frequency-enhanced multi-cognitive visual adapter (DyFMona) module is introduced to enhance multi-scale feature perception and adaptive feature distribution adjustment. In the feature fusion network, a Multi-source Feature Fusion Mechanism (MFFM) employing channel attention with a multilayer perceptron is devised to dynamically weight multi-scale features. In the prediction head, a Shared Lightweight prediction Head (SL-Head) integrating shared convolutions with localization quality estimation is designed to improve the overall localization quality of oriented boxes. Experimental results demonstrate that ASV-YOLO achieves a precision of 99.1%, a recall of 98.5%, with mAP@0.5 and mAP@0.5:0.95 of 99.2% and 92.3%, respectively. The parameter count and training GPU memory are reduced by 17.05% and 32.05%, respectively, relative to the baseline. An inference speed of 289.7 FPS is attained.

Frequency control following a contingency event is of vital concern in power system operations. Leveraging inverter-based resources, it is not hard to shape the center of inertia (COI) frequency nicely. However, under weak grid conditions, it becomes insufficient to solely shape the COI frequency since this aggregate signal fails to reveal the inter-area oscillations. In this manuscript, we advocate for foolproof fine-tuning rules for frequency shaping control (FS) based on a systematic analysis of damping ratio and decay rate of inter-area oscillations to simultaneously meet specified metrics for frequency security and oscillatory stability. To this end, building on a modal decomposition, we simplify the oscillation damping problem into a pole-placement task for a set of scalar subsystems, which can be efficiently solved by only investigating the root locus of a scalar subsystem associated with the main mode, while FS inherently guarantees a Nadir-less COI frequency response. Through our proposed root-locus-based oscillatory stability analysis, we derive closed-form expressions for the minimum damping ratio and decay rate among inter-area oscillations in terms of networked system and control parameters under FS. Moreover, we propose useful tuning guidelines for FS which need only simple calculations or visualized tuning to not only shape the COI frequency into a first-order response that converges to a steady-state value within the allowed range but also ensure a satisfactory damping ratio and decay rate of inter-area oscillations following disturbances. As for the common virtual inertia control (VI), although similar oscillatory stability analysis becomes intractable, one can still glean some insights via the root locus method. Numerical simulations validate the proposed tuning for FS as well as the superiority of FS over VI in exponential convergence rate.

This article investigates the pursuit-evasion problem of multiple underactuated autonomous surface vehicles (ASVs) under velocity and collision avoidance constraints. A safety-critical pursuit-evasion game (PEG) method based on min-max optimization and neural network dynamic control is proposed. Specifically, an allocation strategy is designed at first based on the position information of the pursuing and evading ASVs to achieve a rational and efficient allocation of pursuit targets by minimizing pursuit distances. Next, a nominal PEG guidance law is proposed by combining model predictive control (MPC) with min-max optimization methods. Then, the nominal guidance law is optimized based on a heading-constrained control barrier function (CBF) such that a safety-critical guidance law for collision avoidance can be achieved. Finally, a predicator-based neural network is developed to estimate the uncertainty and external disturbance, and a dynamic control law is proposed to track the guidance signals without using any model parameters. It is proven that the closed-loop system is input-to-state stable (ISS), and the ASV system is safe. A robot-operating-system (ROS)-based simulation results demonstrate the effectiveness of the proposed safety-critical PEG method based on min-max optimization and neural network dynamic control.

This article addresses domain protection strategies for multiple underactuated autonomous surface vehicles (ASVs) against a swarm of attackers. The position information of attacking ASVs is only accessible to a subset of defending ASVs. A three-layer safety-critical herding guidance method is proposed to guide multiple ASVs in herding swarm attackers towards a predefined safe area, thereby safeguarding an important domain with collision-free behaviors. Specifically, a distributed herding behavior generator is proposed to generate a set of tracking points at each stage of the protection strategy. Next, a dipole vector field-based method is proposed to track the generated points, enabling the formation of specific configurations aimed at repelling swarm attackers. Finally, a method for synthesizing any number of time-varying control barrier functions into a consolidated control barrier function is introduced. A predictive correction interior point method is applied to design optimal input constraints. Through stability and safety analysis, it is proven that the closed-loop defending system is input-to-state stable and is guaranteed to be safe. Virtual-reality and field experimentation results verify the effectiveness of the proposed safety-critical herding guidance method for domain protection.

This article investigates the cooperative pursuit of multiple pursuing autonomous surface vehicles (ASVs) against a faster-evading ASV within a complex marine environment. The information of the faster-evading ASV is only accessible to a subset of pursuing ASVs due to their inherent limited sensing range. A safety-critical distributed planning and control architecture is proposed, enabling the cooperative capture of faster-evading ASVs. Specifically, a distributed observer is developed first to create a mechanism for sharing the faster-evading ASV information among the pursuing ASVs. Next, a nominal cooperative pursuit trajectory planning method is developed based on an Apollonius circle technique, where an encircling task and a hunting task are designed to form an encirclement formation and approach the faster-evading ASV, respectively. A safety optimization problem is then formulated to modify the nominal trajectory, outlining a collision-free capture trajectory for the pursuing ASVs. Finally, a guidance method and an extended-state-observer-based dynamic control method are proposed to track the planned pursuit trajectory. It is proven that the closed-loop system is input-to-state stable. A robot-operating-system-based simulation results show the effectiveness of the proposed safety-critical cooperative pursuit planning and control method.

International pressure to decarbonize shipping compels stakeholders across the maritime supply chain to adopt emission reduction strategies. This study develops a game-theoretic model to examine emission reduction decisions within a port-carrier-shipper supply chain under a carbon tax framework, considering shippers’ dual preferences for low-carbon performance and service quality. Two strategies-Shore Power (SP) and Clean Energy switching (CE)-are analyzed. The findings show that stronger low-carbon preference increase profits but may raise total emissions, while stronger service preference can reduce profits under equal power structure. Higher carbon taxes reduce emissions but also lower profits and social welfare. Only SP achieves both profit and emission objectives under moderate low-carbon preference and carbon tax. Port dominance favors profits, carrier dominance favors emission reduction, and the welfare-optimal structure depends jointly on service preference and public environmental concern. The findings offer theoretical and managerial insights into balancing economic and environmental performance in decarbonizing maritime supply chains.

The Arctic ecological environment is extremely sensitive, making it imperative to minimize emissions during the commercial use of Arctic shipping routes. This study developed a system dynamics (SD) model to evaluate the effectiveness of various emission reduction policies in Arctic shipping. The SD model simulated the emission processes under multiple policy scenarios, including energy, operational, investment, and market-based policies by capturing the complex feedback mechanisms among Arctic shipping activities, policy interventions, emissions, and sea ice extent. The simulation results indicated that operational policies, particularly speed reduction measures, were the most effective and resource-efficient strategies for achieving rapid emission reductions. Energy policies, such as transitioning to liquefied natural gas, demonstrated substantial environmental benefits. Furthermore, investment policies and market-based mechanisms significantly contributed to long-term emission reductions.

In this brief, a model-free adaptive disturbance rejection controller is proposed for permanent magnet synchronous motor (PMSM) position tracking control. First, a filtering adaptive extended state observer (FAESO) is designed to estimate the moment of inertia and the load torque. As such, the PMSM can maintain a good control performance even if the moment of inertia is unknown. Second, in order to enhance the anti-interference ability of PMSM, a super-twisting algorithm (STA) based control law is designed. Finally, the effectiveness of the proposed controller is verified through simulations.

This paper addresses the cooperative path following control of second-order uncertain nonlinear multi-agent systems subject to input constraints and safety constraints. Firstly, a predictor is developed based on neural networks to accurately approximate system nonlinearities and external disturbances. Then, control Lyapunov functions (CLFs) combined with control barrier functions (CBFs) are utilized to formulate the cooperative path following control objectives and safety constraints. A CLF-CBF-quadratic programming (QP) approach using neurodynamic optimization is developed to generate optimal control signals within the constraints to ensure both stability and safety. Compared to existing CBF-based safety-critical approaches designed for high-order systems where multiple time derivatives are required, a CBF backstepping method is proposed herein to consider the top-level of system without using multiple derivatives. The control objective of cooperative path following is realized and the input-to-state safety is guaranteed by using the proposed method. Simulation results of a fleet of autonomous surface vehicles are presented to demonstrate the effectiveness of the proposed CLF-CBF-QP method in cooperative path following.

This paper investigates the problem of ensuring the stable operation of multiple high-speed train systems under the threat of False Data Injection (FDI) attacks. Due to the wireless communication characteristics of railway networks, high-speed train systems are particularly vulnerable to FDI attacks, which can compromise the accuracy of train data and disrupt cooperative control strategies. To mitigate this risk, we propose a Distributed Model-Free Adaptive Predictive Control (DMFAPC) scheme, which is data-driven and does not rely on an accurate system model. First, by using a dynamic linearization method, we transform the nonlinear high-speed train system model into a dynamically linearized model. Then, based on the above linearized model, we design a DMFAPC control strategy that ensures bounded train velocity tracking errors even in the presence of FDI attacks. Finally, the stability of the proposed scheme is rigorously analyzed using the contraction mapping method, and simulation results demonstrate that the scheme exhibits excellent robustness and stability under attack conditions.

Unmanned surface vehicles (USVs) face significant challenges in trajectory tracking tasks within complex marine environments due to hydrodynamic uncertainties and environmental disturbances. This paper addresses the high-precision trajectory tracking problem for an USV under actuator constraints and time-varying ocean disturbances. A predictive-based trajectory tracking control method via physics-informed neural network (PC-PINN) is proposed to achieve tracking performance while ensuring computational efficiency. The PINN serves as a dynamics approximator by embedding the USV governing equation into a composite loss function that balances data fidelity and physics constraints. The model predictive controller then utilizes the PINN predictions to solve a receding-horizon optimal control problem with actuator constraints. Simulation results validate the effectiveness of the proposed PC-PINN method for USV trajectory tracking task. Copyright (c) 2025 The Authors. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0/)

This paper investigates the path-guided distributed formation control of networked autonomous surface vehicles (ASVs) subject to model uncertainties and environmental disturbances. A safety-certified path-guided coordinated control method is proposed for multiple ASVs to achieve a distributed formation in obstacle environments. Specifically, a neural predictor with a high-order tuner is presented to approximate unknown nonlinearities with accelerated learning performance. Subsequently, control Lyapunov functions (CLFs) and control barrier functions (CBFs) are constructed for mapping stability constraints and safety constraints on states to control inputs. A quadratic optimization problem is constructed with the norm of control inputs as the objective function, CLFs and CBFs as constraints. Neurodynamic optimization is used to deal with the quadratic programming problem and generate the optimal kinetic control signals, thereby attaining the desired safe formation. Unlike the high-order CBF, a CBF backstepping method is proposed to establish safety constraints such that repeated time derivatives of system nonlinearities can be avoided. The multi-ASVs system is ensured to be input-to-state safe irrespective of high-order relative degree. Through the Lyapunov theory, the multi-ASVs system is proven to be input-to-state stable. Finally, simulation results are presented to validate the efficacy of the presented safety-certified distributed formation control for networked ASVs.

The finite-control set model predictive control (FCS-MPC) algorithm faces challenges because of its high dependence on model accuracy and significant computational demands for three-level pulse width modulation (PWM) rectifier systems. To respond to these challenges, this paper proposes a data-driven neural network and sector judgment based FCS-MPC approach for three-level PWM rectifiers. First, building a data-driven neural network estimator to approximate uncertain parameters and control input gains in the mathematical model of the rectifier through a parallel learning approach. Second, the estimated system parameters are used in the finite set model prediction controller, the model-predicted formulas are reformulated to derive the predicted reference space voltage vectors, and only three candidate switching state voltage vectors are selected for computational optimization in each cycle according to different sector boundary conditions, which reduces the computational workload by 89% compared to 27 traversals of the traditional MPC for optimization in each cycle. Finally, using simulation comparison experiments, It has been verified that the introduced method can quickly track the predicted parameters and effectively decrease the total harmonic distortion (THD) besides reduce the active and reactive power fluctuations.

Dear Editor, This letter presents a finite-time online parameter self-learning disturbance rejection surge speed control method for a marine surface vehicle (MSV). Specifically, a finite-time parameter self-learning robust exact differentiator based (RED-based) observer is first employed for estimating the unknown hydrodynamic parameters and the unknown control input coefficient separately, ensuring the finitetime convergence for both. The environmental disturbances and the dynamic modeling errors are also estimated simultaneously. Subsequently, a self-learning disturbance rejection control law is designed based on the estimated information. Finally, Lyapunov method is applied to prove the stability of the system. Hardware-in-the-loop experiment verifies the effectiveness of the proposed control method.

Cooperative steering of the captain and automated system can effectively reduce the necessity of extremely accurate environment perception of intelligent surface vehicles (ISVs), and enhance the safety and fault-tolerance of decision-making and motion control. This paper presents a human-machine shared line-of-sight (LOS) path following control method of under-actuated ISVs in complex sea environments with dynamic and static obstacles. At the kinematics level, a human-machine shared LOS guidance law is presented based on a dynamic authority mechanism determined by a shared weighted coefficient. The proposed guidance law not only preserves the simplicity and interpretation of the LOS guidance, but also enables the ISVs to combine the complementary strengths of the captain and the automated system. At the kinetic level, an adaptive extended state observer (AESO) is developed to estimate model uncertainties and environmental disturbances, and a model-free kinetic control method is constructed based on the AESO. By using the input-to-state stability theory, uniformly and ultimately bounded of the closed-loop system is analyzed. The simulation results are provided to validate the effectiveness of the human-machine shared LOS path following control method.

[Objectives]A dynamic event-triggered collaborative path-following control method for mul-tiple unmanned surface vehicles(USVs)is proposed,considering the constraints of network bandwidth re-sources,model uncertainties,and external environmental disturbances.[Methods]Specifically,a dynamic variable is introduced to design a dynamic event-triggered mechanism at the cooperation layer,and a dynamic event-triggered path parameter update law is developed to reduce network traffic.Additionally,a path-para-meter predictor is designed to estimate the path parameters of neighboring USVs during the communication in-terval.In the guidance layer,a line-of-sight-based guidance law is proposed.Finally,in the control layer,a su-per-twisting observer is used to estimate the total disturbances,and a super-twisting dynamic control law is de-veloped based on the estimated disturbances.[Results]Stability and Zeno behavior analyses demonstrate that the closed-loop system is input-to-state stable,and the proposed approach does not exhibit Zeno behavior.Comparative simulation results validate the effectiveness of the proposed dynamic event-triggered cooperative path-following control method for USVs.[Conclusions]The proposed method can achieve cooperative path following while reducing both transient and steady-state network traffic.

The universal application of the hub-and-spoke maritime network makes feeder line network key to restricting the quality and efficiency of maritime transportation. However, container liner routes in feeder line network are susceptible to the changes in shipment demand and international fuel prices. Therefore, based on the hub-and-spoke maritime network, this paper constructs a robust optimization model of container liner routes in feeder line network. Under the capacity and time constraints, routes optimization and ship equipment under uncertain environment are analysed. An improved tabu search algorithm was designed based on the characteristics of the model. The example analysis proves that the model can still ensure the robustness of routes under uncertain environment, which is more applicable than the deterministic model.

This paper presents an autonomous docking guidance law for maritime autonomous surface ships (MASSs) to avoid different types of obstacles in complicated harbor environments. Firstly, a dynamic vector field-based guidance law is proposed to drive the MASS towards desired berthing position and direction synchronously. Then, the velocity optimization method is proposed based on the guidance velocity signal derived from the dynamic vector field. Through converting the obstacle avoidance constraints into velocity guidance vector constraints, the control barrier functions is utilized to construct a quadratic programming problem, which in turn leads to the optimal guidance velocity. By using the present method, the MASS can realize the autonomous docking task with automatic obstacle avoidance. Simulation results demonstrate the feasibility of the proposed method.

This paper is concerned with the state and distur-bance estimation of autonomous surface vehicles (ASVs) in the presence of measurement noises. The velocity state information is unmeasured and the lumped disturbances consisting of internal model uncertainties and external environmental disturbance are unknown. Specifically, i n t he presence of measurement noises, a nonlinear cascade extended state observer (CESO) based on position-orientation measurement is presented to estimate unmeasured velocity and unknown lumped disturbances. The stability of the overall cascade system is validated through input-to-state stability theory and cascade theory. Simulation results are shown to confirm the effectiveness of the p roposed observer scheme.