With the rapid development of unmanned aerial vehicle (UAV) technology, UAVs have provided an innovative solution for floating debris monitoring. However, object detection in UAV images remains challenging due to high miss rates for small objects, insufficient low-level feature extraction and computational redundancy. This letter proposes an Efficient Floating Debris detection model based on YOLOv8n, named EFD-YOLO, to address these issues. First, the Edge Fusion Stem (EFStem) module is proposed to enhance low-level feature extraction through an integrated gate-attention mechanism. Second, the Multi-Branch Efficient Reparameterization Block (MBERB) is designed to achieve efficient cross-layer feature fusion. Experimental results demonstrate that compared to YOLOv8n, our model achieves a 6.3% improvement in mean Average Precision (mAP) on the UAV Floating Debris Dataset, while simultaneously reducing parameters by 26.7% and improving small object recall by 21.9%. The inference time of EFD-YOLO on the RK3588 edge device is as low as 30.5 ms, demonstrating real-time capability.

Dynamic obstacles pose one of the most significant safety challenges for autonomous robots operating in cluttered environments. This paper aims to achieve collision-free obstacle avoidance without sacrificing the prescribed performance requirements in the formation control of wheeled humanoid robots (WHRs). A novel dynamic obstacle avoidance strategy is proposed by introducing a virtual barrier potential field incorporating the obstacle’s position, velocity, and the relative angle with respect to the robot. To balance the predefined performance constraints and safety/connectivity requirements, a finite-time flexible performance function is developed to ensure finite-time convergence of the formation tracking errors to predetermined regions, while the performance boundaries can adjust flexibly when the performance constraints conflict with the collision avoidance and/or connectivity maintenance requirements. Based on the dynamic obstacle avoidance strategy and the flexible performance control, a distributed finite-time flexible performance formation control strategy is constructed, which achieves finite-time convergence of the formation tracking errors, dynamic obstacle avoidance for all robots, and connectivity maintenance among initially connected robots. Finally, the effectiveness of the proposed formation control strategy is demonstrated by both simulation and experimental results.

This paper presents a motion planning approach for rigid-soft hybrid robots that incorporates continuous expression and input mapping, aiming to achieve both tracking and collision avoidance. The conventional piecewise constant curvature model utilized in soft robots suffers from issues of discontinuity and singularity. These inherent drawbacks pose significant challenges when attempting to address the nonlinear problems associated with motion planning. To overcome these limitations, we establish a relationship between the length of drive cable and the coordination of robot terminal. Through the application of Taylor transformation, we effectively eliminate the control variation present in the denominator of this expression. Then, the nonlinear model predictive control (NMPC) with this model expression and input mapping is proposed for motion planning. By directly constructing the current input and output of the motion planning based on the combination of previous data and substituting the linearized part of the model with this data, we mitigate the impact of model inaccuracies on the solution process. Both the obstacles and robot are modeled as polyhedra, and the collision problem is reformulated in the form of continuous nonlinear inequalities. These expressions are then incorporated into the NMPC optimization function as collision avoidance constraints. This approach enables the attainment of a larger feasible movement area and more precise tracking results during the motion planning process. Finally, experimental and simulation results conducted on a rigid-soft hybrid robot demonstrate the feasibility and superiority of the proposed method, validating its effectiveness in practical applications.

This study focuses on the novel reinforcement learning control strategy of a nonlinear two-degrees-of-freedom (2-DOF) helicopter system for tracking the desired trajectory while minimizing the tracking error. First, gradient descent algorithm is incorporated in the context of the reinforcement learning control scheme to obtain the adaptive laws. Subsequently, considering the uncertainties in the nonlinear system, radial basis function (RBF) neural networks (NNs) are exploited to approximate the unknown internal dynamics. In contrast to the previous studies, aiming at accelerating the convergence in reinforcement learning control, a barrier Lyapunov function is constructed to constrain the states to ensure that the tracking error rapidly converges to a neighborhood of zero. Under the proposed control strategy, the states of the closed-loop system are proven to be semi-globally uniformly ultimately bounded through rigorous Lyapunov analyses, and the state constraints are satisfied. Furthermore, the simulations and experiments conducted on a Quanser laboratory platform reveal that the proposed control functions are suitable and effective. Note to Practitioners—This paper is motivated by designing a reinforcement learning control strategy to enhance online learning capability and control performance of the controller for a nonlinear 2-DOF helicopter system. The control framework is divided into the design of the critic and actor NNs, responsible primarily for evaluating the control performance and approximating uncertainties in the system separately. Unlike the adaptive NN control, the actor NN weights are updated by combining information of states and inputs from the critic NN. In addition, aiming at accelerating the convergence, a barrier Lyapunov function is constructed to constrain the states to ensure that the tracking error rapidly converges to a neighborhood of zero. Finally, the proposed control strategy is validated in simulation and experiment on the Quanser laboratory platform.

Limited computational resource is one of the features of the embedded system including unmanned marine surface vehicle (MSV). Under this practical constraint, we aim to develop a distributed formation control algorithm for a group of uncertain MSVs, whose computational burden is low. The uncertainty and disturbance estimator (UDE) is employed to compensate for the modeling uncertainties, the unknown environmental disturbances, and the unavailable derivative of the virtual control inputs, such that the formation errors converge asymptotically to zero. Meanwhile, the prescribed performance control technique is applied to ensure that the convergence rates of the formation errors are faster than predefined values. In addition, collision avoidance and connectivity preservation among the neighboring vehicles are guaranteed, while the obstacle avoidance is also ensured. As no parameter update law is required to calculate, the computational burden is reduced significantly. The effectiveness of the proposed UDE-based formation control algorithm is validated through comparative simulation.

Since real‐world multiview data frequently contains numerous samples that are not observed from some viewpoints, the incomplete multiview clustering (IMC) issue has received a great deal of attention recently. However, most existing IMC methods choose to zero‐fill the missing instances, which leads to the failure to exploit information hidden in the missing instances, and high‐order interactions between various views. To tackle these problems, we proposed an effective IMC method using low‐rank tensor ring completion, which was demonstrated to be powerful in exploiting high‐order correlation. Specifically, we first stack the incomplete similarity graphs of all views into a 3rd‐order incomplete tensor and then restore it via the tensor ring decomposition. Next, using an adaptive weighting technique, we apply multiview spectral clustering to all entire graphs in order to balance the contributions of different viewpoints and identify the consensus representation for grouping. Finally, we employ the alternating direction method of multipliers (ADMM) to optimize the suggested model. Numerous experimental findings on numerous different datasets show that the suggested approach is superior to other cutting‐edge approaches.

Recently, with the development of the marine economy, marine risers have garnered increasing attention as they present facile and reliable methods for oil and gas transportation. However, these risers are susceptible to vibrations, which can lead to system performance degradation and fatigue damage. Therefore, effective vibration control strategies are required to address this issue. In this study, a novel adaptive fault-tolerant control (FTC) strategy is adopted to suppress the vibrations of a 3-D riser-vessel system against the effects of actuator failures, backlash-like hysteresis, and external disturbances. A barrier-based Lyapunov function is merged to eliminate the time-varying output constraints of the system. Adaptive FTC laws with projection mapping operators are designed to compensate for parameter uncertainties and consider input nonlinearities to improve system robustness. Finally, a rigorous Lyapunov analysis and numerical simulations are performed to verify the validity of the proposed controller and guarantee uniformly bounded stability of the system.

This study is aimed to design a fault-tolerant control using a broad learning neural network (BLNN) for a two-degree-of-freedom (2-DOF) nonlinear helicopter system. Compared with the conventional radial basis function neural network, the BLNN can approximate uncertainties and unknown functions with smaller tracking errors by adding incremental and enhancement nodes. Considering possible actuator faults in during actual application, an adaptive auxiliary parameter is established to prevent their effects on control. Through direct Lyapunov method, the stability and convergence of the closed-loop system are analyzed. The results from simulations and experiments conducted on a 2-DOF helicopter laboratory platform of Quanser demonstrate the validity and feasibility of the proposed control method.

This study focuses on an adaptive fault-tolerant boundary control (BC) for a flexible string (FS) in the presence of unknown external disturbances, dead zone, and actuator fault. To tackle these issues, by employing some transformations, a part of the unknown dead zone and external disturbance can be regarded as a composite disturbance. Subsequently, an adaptive fault-tolerant BC is developed by utilizing strict formula derivations to compensate for unknown composite disturbance, dead zone, and actuator fault in the FS system. Under the proposed control strategy, the closed-loop system proves to be uniformly ultimately bounded, and the vibration amplitude is guaranteed to converge ultimately to a small compact set by choosing suitable design parameters. Finally, a numerical simulation is performed to demonstrate the control performance of the proposed scheme.

We propose an adaptive neural-network-based fault-tolerant control scheme for a flexible string considering the input constraint, actuator gain fault, and external disturbances. First, we utilize a radial basis function neural network to compensate for the actuator gain fault. In addition, an observer is used to handle composite disturbances, including unknown approximation errors and boundary disturbances. Then, an auxiliary system eliminates the effect of the input constraint. By integrating the composite disturbance observer and auxiliary system, adaptive fault-tolerant boundary control is achieved for an uncertain flexible string. Under rigorous Lyapunov stability analysis, the vibration scope of the flexible string is guaranteed to remain within a small compact set. Numerical simulations verify the high control performance of the proposed control scheme.

This study is concerned with the dynamical analysis and vibration attenuation for a three-dimensional (3-D) suspension cable system of a helicopter preceded by output constraints and input backlash. First, the dynamic model of a 3-D suspension cable is constructed in accordance with Hamilton’s principle. Then, a backlash inverse compensator is established to tackle the input backlash nonlinearities. Subsequently, three boundary controllers together with output signal barrier functions are proposed to dampen the oscillations while not violating the cable swing constraints. The uniform boundedness of the closed-loop system is guaranteed with recourse to the direct Lyapunov’s method. Finally, the validity and efficiency of the derived control laws are testified through simulation results.

In this study, an adaptive robust control technique for an uncertain riser-vessel system in a three-dimensional space is developed. A projection mapping technique and a hyperbolic tangent function are exploited to construct novel adaptive robust controllers based on adaptive laws dynamically updated online to restrain the vibration, tackle parametric uncertainties, compensate for the unknown upper bound of disturbances, and ensure robustness of the coupled system. Lyapunov’s method is adopted to analyze and demonstrate the bounded stability of the closed-loop system. Simulation results are provided to validate the feasibility and effectiveness of the proposed approach.

This paper presents a novel model predictive control (MPC) method for the single-inductor multi-output (SIMO) converter. The novel MPC method combines the conventional MPC strategy and the event-triggered control strategy, i.e. event-triggered MPC (ET-MPC). On one hand, the proposed ET-MPC method inherits the feature of fast dynamic response of MPC to reduce the cross regulation of SIMO converter; On the other hand, the MPC scheme is activated when the state of the SIMO converter triggers a preset triggering condition. Therefore, the unnecessary online computation and switching actions can be avoided, since the MPC scheme is suspended if the triggering condition is inactive. Consequently, the ET-MPC method has two advantages over the conventional MPC method: i) lower computational burden, ii) and less switching actions which contribute to lower switching losses. Moreover, the weighting factor for tuning the switching frequency can be deleted because the unnecessary switching action are all removed. The steady-state operation and dynamic performance cases are studied. The results demonstrate that PS-CRS is able to regulate the SI-MIMO DC-DC converter effectively and robustly.