Yang Qu

Autonomous underwater vehicles (AUVs) have been extensively employed in diverse marine applications, where depth-tracking control remains a critical technical challenge. Although previous studies have investigated various guidance law designs for underactuated AUVs, compensation for the attack-angle effect induced by heave velocity remains underexplored, particularly in the presence of extreme time-varying external disturbances and sharp path curvature variations. Existing line-of-sight (LOS) based methods, including integral LOS (ILOS) and adaptive LOS (ALOS), rely solely on the integral action of the pitch-tracking error to estimate the attack angle, which inevitably introduces inherent time-delay characteristics and induces overshoot and chattering in the depth-tracking response. Given that a system’s position and its velocity are uniquely determined by its acceleration, a response-tunable adaptive LOS (RTALOS) guidance design is proposed for AUV depth-tracking control task. This guidance law incorporates both the depth-tracking error and its velocity term as boundary constraints, generating an acceleration reference through a time-based planning polynomial to achieve accurate attack-angle estimation. The proposed method redefines attack-angle estimation as a new paradigm based on a second-order depth-tracking kinematic system, where the introduced velocity term acts as an adjustable damping effect to effectively suppress the depth-tracking overshoot and oscillation. Simulations were conducted to verify that the proposed guidance design could make the depth-tracking motion converge within a given time duration if the state-constrained acceleration was promptly executed. Compared to the selected ILOS and ALOS methods, the proposed RTALOS method can rapidly and accurately compensate for time-varying attack-angle effects via the estimation of attack angle, resulting in precise depth-tracking control performance, even under severe time-varying disturbances and when the pitch-tracking control performance is unsatisfactory.

This paper presents a positioning control method for underactuated unmanned surface vehicles (USVs) subject to environmental disturbances and wave-contaminated measurements. In underactuated dynamic positioning, surge motion and yaw motion can be directly regulated by the propulsion system, whereas sway motion cannot be directly controlled by an independent lateral thrust. Therefore, the lateral environmental-force component is utilized to induce the vehicle’s dynamic response to sway. To achieve this objective, a position-keeping guidance system taking into account the desired heading and the lateral positioning error is introduced in this paper. With this guidance mechanism, the lateral environmental-force component can drive the USV to reduce the cross-track error, thereby enabling underactuated positioning. A rotated coordinate system is established around the desired position, and the positioning error is decomposed into along-track and cross-track components. To improve the transient response, an error-rate feedback term is introduced into the rotated-angle update law for yaw-heading guidance design, which enhances the damping of the cross-track dynamics. Meanwhile, a wave-filtering observer is designed to make low-frequency position and velocity estimates for feedback control. Simulation results under multiple operating conditions show that the proposed observer reduces the amplitude and high-frequency variation of the control signals compared with the existing wave-filtering observer, and the proposed positioning control method achieves smaller positioning errors than the existing nonlinear positioning control (NPC). The comparative results also indicate that the proposed method is suitable for position keeping under constant or slowly varying environmental loads, moderate model uncertainty, and wave-contaminated measurements, whereas rapidly varying load directions may degrade the positioning accuracy.

Introduction: Deep learning model fusion has become one of the most effective methods to improve the performance of ensemble learning frameworks. However, the optimization of critical parameters within ensemble learning models to improve prediction accuracy remains a challenging issue. This study proposes a lightweight ensemble learning model fusion method based on post-hoc weighted averaging of predicted probabilities. Methods: By appropriately adjusting the fusion weight coefficient and the decision threshold, the optimal fusion strategy is investigated to improve performance metrics including accuracy, precision, recall, and F1 score. To verify the effectiveness of the proposed lightweight ensemble learning fusion method, it is applied to a medical classification task using lung computed tomography (CT) images, which aims to distinguish between pneumonia and lung cancer, two diseases with inter-class visual similarity. We construct a dataset containing 859 lung CT images representing pneumonia and lung cancer. First, we evaluated nine deep learning architectures from the VGG family (VGG11, VGG13, VGG16, VGG19) and the ResNet family (ResNet34, ResNet50, ResNeXt50, ResNet101, ResNeXt101). The results show that ResNet-based models consistently outperform VGG-based models. Therefore, we adopt the proposed lightweight weighted probability fusion strategy to integrate two complementary ResNet models, namely ResNet34 and ResNeXt50. Results: Experimental results show that the optimized fusion model achieves an accuracy of 96.67%, precision of 94.68%, recall of 98.88%, and F1 score of 96.74%, outperforming the individual models across all evaluation metrics. discussion: The performance enhancement stems from the complementary capabilities of the ensemble models, where one model corrects the misclassifications of the other. The weighted fusion strategy, governed by interpretable parameters (α and Ps), effectively mitigates individual model errors without requiring retraining of base models or complex meta-learners. Compared to traditional methods like Bagging, Boosting, and Stacking, the proposed approach offers greater simplicity, interpretability, and computational efficiency. The results underscore the method's potential in clinical decision support by improving diagnostic accuracy for diseases with similar imaging features. Discussion: These results show that the proposed lightweight ensemble learning method can enhance classification accuracy and decision robustness. This suggests that weighted probability fusion is effective for tasks with inter-class visual similarity. Conclusion: The proposed method provides a feasible strategy for a model ensemble framework in medical image analysis, particularly when balancing performance and computational efficiency.

This article addresses high-precision trajectory tracking for fully actuated hexarotor unmanned aerial vehicles (UAVs) subject to model uncertainty and external disturbances. To exploit the repetitive nature of UAV missions, an adaptive iterative learning control (AILC) scheme is developed, which incrementally enhance tracking accuracy using historical data form previous executions. The controller is designed based on the decoupled translational dynamics of a six-rotor tilted-propeller platform and incorporates adaptive laws that jointly estimate and compensate for reference input errors, aerodynamic drag, residual attitude deviations, and lumped disturbances. Rigorous convergence and boundedness are established via a composite energy function (CEF) analysis in the iteration domain. The approach is validated via MATLAB simulations, PX4-based software-in-the-loop (SITL) in Gazebo and real-flight experiments on a laboratory hexarotor platform. To the best of current knowledge, this work: 1) represents the first application of AILC to a fully actuated hexarotor UAV, showing significant improvements in trajectory-tracking accuracy over benchmark methods; and 2) demonstrates the platform’s potential for attitude-stable logistics tasks such as liquid transport through real-flight tests.

Cascaded guidance, state estimation, and control systems have been successfully implemented in autonomous underwater vehicles. However, disordered convergence sequences among subsystems fundamentally induce system oscillations and instabilities. Here, we introduce a temporal-sequencing-convergent cascaded guidance, state estimation, and control system for depth-tracking of underactuated autonomous underwater vehicles. It establishes an ordered convergence architecture: state estimation converges first with a planning window t_d, followed by control execution with a planning time window t_c, and guidance finally converges with a planning time window t_f, adhering to a temporal-sequencing-convergent criterion t_d < t_c < t_f. This architecture, validated through experiments, ensures stable and efficient depth-tracking performance owing to well-ordered convergence of subsystems. Conversely, experiments violating the temporal-sequencing-convergent criterion exhibited prominent oscillatory depth-tracking responses. Our method outperformed selected approaches, achieving a lower average depth-tracking error of 1.32 cm under sudden external disturbances. Notably, even with prominent pitch-tracking errors using a PD controller, our proposed guidance design also showcased remarkable attack-angle compensation capability, thereby maintaining precise depth-tracking performance.

Existing state estimation methods use a combination of measurement error and fixed gains to update high-order states. However, if these fixed gains are not finetuned, it will inevitably lead to significant phase distortion and violation of calculus relationship among updated states. To handle these issues, this article proposes a high-order state-filtering system that directly uses measurement data, thereby providing precise high-order differential states for potential applications. The estimated highest order derivative is produced by an online planned polynomial that satisfies all state-error constraints. To fulfill calculus relationship among updated states, each low-order state is uniquely determined by the integration of this highest order derivative. To validate the effectiveness of the proposed state-filtering system, it is applied to closed-loop position control of a brushless direct current (BLDC) motor. In this application, its rotor angle is measured by a high-resolution encoder. Compared to a differentiator, a high-gain observer, and a Kalman filter, the proposed method outperforms them by eliminating the need for parameter optimization, being insensitive to the sampling time step, effectively mitigating phase distortion, and strictly satisfying calculus relationship among updated states. Experimental results have verified the superiority and robustness of the proposed method.

This paper presents a real-time emergency collision-avoidance method for unmanned surface vehicles (USVs) with the International Regulations for Preventing Collisions at Sea (COLREGS) flexibly obeyed. The pivotal issue is that some traffic vessels may violate the demands of this convention, which would increase the risk of collision if the USV blindly obeys the COLREGS rules. To avoid mandatory compliance with these COLREGS rules, a real-time truncated velocity obstacle (TVO) algorithm is proposed to assign a collision-free velocity vector for the control system to realize. Considering a reasonable trade-off between safety and the COLREGS rules, the proposed collision-avoidance method expands the TVO’s area based on the velocity uncertainties of traffic vessels, which greatly enhance the safety of collision-avoidance operations and encourage the USV to follow the COLREGS rules. To promptly realize an assigned collision-free velocity, this paper also develops a discrete simultaneous planning and executing (SPAE) controller design. The proposed discrete controller is divided into three parts: online polynomial planning to satisfy the constraints of tracking errors, an accurate uncertainty estimation, and an algebraic control law to promptly execute the planned polynomial. Numerical results have validated the reliability and intelligibility of the proposed collision-avoidance method. Furthermore, simulated and experimental results have validated the effectiveness of the proposed controller design.