This paper proposes a novel three-dimensional prescribed-time cooperative guidance law (3-D PTCGL) using a dynamic event-triggered (DET) mechanism for multi-missile salvo attacks on a maneuvering target with impact angle constraints. A virtual leader strategy is utilized to generate reference states, and a prescribed-time extended state observer (PTESO) is designed to accurately estimate target accelerations. In the line-of-sight (LOS) direction, a cooperative guidance law is designed using consensus control theory, second-order sliding mode control (SMC) theory, and prescribed-time convergence theory, which can synchronize the range-to-go and relative velocity of multiple missiles within the prescribed time, thereby achieving a salvo attack. Meanwhile, to minimize communication frequency, the DET mechanism is incorporated into the LOS direction of the guidance law. In the LOS normal directions, guidance laws are designed based on second-order SMC and prescribed-time convergence theory to guarantee that the LOS angles and their rates rapidly converge to desired values within the prescribed time, enabling accurate attacks on maneuvering targets with specified LOS angles. Rigorous stability analysis is presented, and numerical simulations are performed.

Contribution: This article presents a virtual-real combination experiment system for multirotor autonomous aerial vehicle (AAV) assembly and swarm cooperation, featuring a novel multirotor AAV assembly and swarm cooperation virtual simulation experiment platform (MAAVASC-VSEP) with physical experiments. The experiment system enhances student engagement with cutting-edge AAV swarm technology. Background: The teaching of AAV swarm technology faces challenges such as complex multidisciplinary integration, abstract concepts, and limited experimental resources. Existing AAV courses often focus on AAV technology, lacking a comprehensive, interdisciplinary approach to swarm technology. Intended outcomes: The experiment system cultivates students' exploratory thinking and problem-solving skills, helping them understand the fundamental principles of AAV swarm technology and improving multidisciplinary engineering application abilities. Application design: Combining MAAVASC-VSEP with the corresponding physical experiments, the experiment system includes three inquiry-based tasks: multirotor AAV assembly and parameter tuning, AAV swarm link budgeting and networking, and swarm cooperation and obstacle avoidance. Findings: Student performance evaluation and student survey demonstrate that the experiment system effectively improves students' understanding of AAV swarm technology. Students in the experimental group outperformed students in the comparison group through more fault-tolerant exploratory attempts, indicating the system's significant effectiveness in fostering self-directed learning and problem-solving skills.

This paper addresses the challenge of high-precision localization for large-scale unmanned aerial vehicle (UAV) swarms in GNSS-denied environments, and proposes a novel tightly-coupled localization algorithm based on an improved particle filter. The proposed framework integrates inertial measurement units (IMU) and time difference of arrival (TDOA) techniques, leveraging the complementary advantages of IMU’s short-term accuracy and TDOA’s long-term stability. To enhance robustness against measurement outliers, a moving average filter is applied to preprocess TDOA measurements, and a Huber loss-based likelihood function is incorporated in the particle filter. Furthermore, a genetic algorithm is utilized to optimize the particle resampling process, thereby reducing particle degeneracy. A dynamic weight allocation mechanism is also introduced to adaptively balance the contributions of IMU and TDOA based on a real-time reliability assessment. Numerical simulations validate the effectiveness and superiority of the proposed method in large-scale UAV swarm localization scenarios.

This article investigates neural network (NN)-based prescribed performance control with collision avoidance for spacecraft formation systems in the presence of space perturbations and thruster faults. First, an artificial potential function is constructed to maintain spacecraft within communication range and avoid collisions. A prescribed performance function is then employed to constrain position errors within a preset boundary. Furthermore, a learning non-singular terminal sliding mode control (LNTSMC) law is developed to ensure that both the steady-state and transient performance of position tracking errors meet the prescribed performance constraints. A novel learning NN model is incorporated to estimate and compensate for the synthesized perturbations, utilizing an iterative learning algorithm to update the weights of the NN, thereby reducing computational complexity. The proposed LNTSMC scheme effectively addresses issues of inter-spacecraft collision avoidance, prescribed dynamic and steady-state control performance, and robust fault tolerance without imposing additional constraints on thruster faults. A rigorous stability analysis is provided, and the effectiveness and applicability of the proposed method are validated through simulation comparisons.

This article presents a finite-time prescribed performance (FTPP) control approach based on a learning Chebyshev neural network (LCNN) for spacecraft attitude tracking with modeling uncertainties, actuator faults, and external disturbances. An FTPP function is designed to specify the desired accuracy boundary and finite-time convergence. Further, an FTPP-based learning sliding mode controller (LSMC) is constructed, where the lumped disturbance is approximated and compensated via a novel LCNN model. Unlike conventional adaptive CNN models, the LCNN model employs an iterative learning mechanism for adjusting the weights of the CNN model, reducing computing costs. The FTPP-based LSMC approach is presented with a detailed stability analysis. The proposed method offers a broad range of applications with the FTPP criteria satisfied. A series of simulations are performed to verify the validity and applicability of the proposed approach.

This paper studies the distributed state estimation problem for nonlinear systems with random transmission delays and transmission failures, and proposes a novel sequential hybrid consensus filtering algorithm. The covariance intersection method is used to reach consensus over priors, and the consensus on measurements is used to fuse the innovation information, which makes the proposed algorithm robust to transmission failures. A compensation scheme is proposed when there are one-step transmission delays. The consensus weight of the delayed information is derived, and with the compensation term, the local estimation accuracy is improved. Rather than waiting for all information from neighboring nodes, the proposed algorithm is implemented sequentially once information from a neighboring node is received during the consensus step. The rigorous theoretical performance analysis is presented, and the proposed algorithm is tested numerically on a single target tracking problem and a distributed navigation of satellite cluster problem.

Mobile robots play an important role in smart factories, though efficient task assignment and path planning for these robots still present challenges. In this paper, we propose an integrated task- and path-planning approach with precedence constrains in smart factories to solve the problem of reassigning tasks or replanning paths when they are handled separately. Compared to our previous work, we further improve the Regret-based Search Strategy (RSS) for updating the task insertions, which can increase the operational efficiency of machining centers and reduce the time consumption. Moreover, we conduct rigorous experiments in a simulated smart factory with different scales of robots and tasks. For small-scale problems, we conduct a comprehensive performance analysis of our proposed methods and NBS-ISPS, the state-of-the-art method in this field. For large-scale problems, we examine the feasibility of our proposed approach. The results show that our approach takes little computation time, and it can help reduce the idle time of machining centers and make full use of these manufacturing resources to improve the overall operational efficiency of smart factories.

In this article, the arbitrary‐oriented object detection problem with application in robotic grasping is addressed. A novel Jensen–Shannon divergence (JSD)– You Only Look Once (YOLO) model is proposed, which enables real‐time grasp detection with high performance. The one‐stage object detection network YOLOv5 is modified with a decoupled head, which solves the angle classification problem and rectangle parameter regression problem separately, such that the YOLOv5 network is applicable for robotic grasping and the detection accuracy is significantly improved. A circular smooth label angle classification method is proposed to tackle the boundary discontinuity problem in angle regression, and the periodicity of the angle prediction is guaranteed. A novel Jensen–Shannon intersection of union is designed to calculate the intersection over union of oriented rectangles, which aims to better measure the discrepancies between the prediction and the ground truth and to avoid the singularity problem when two rectangles are not overlapped. Extensive evaluation on the Cornell and visual manipulation relationship dataset datasets demonstrates the effectiveness of the JSD–YOLO model in general robotic grasp operations, with 99.7% and 95.7% image‐wise split accuracy, respectively.

This paper investigates dynamic modeling and stochastic feedback control problem of the space rigid-flexible manipulator. To establish the dynamic model of the system, the lateral deformation, longitudinal deformation and coupling deformation are considered. A decoupled feedback control method is applied for trajectory tracking under disturbance, and a replanning strategy in an event-triggered fashion is proposed. Computational results for modeling and trajectory tracking of a space rigid-flexible manipulator are presented.

The issue of active attitude fault-tolerant stabilization control for spacecrafts subject to actuator faults, inertia uncertainty, and external disturbances is investigated in this paper. To robustly and accurately reconstruct actuator faults, a novel mixed learning observer (MLO) is explored by combining the iterative learning algorithm and the repetitive learning algorithm. Moreover, to guarantee robust spacecraft attitude fault-tolerant stabilization, by synthesizing the mixed learning algorithm with the sliding mode controller, a novel mixed learning sliding-mode controller (MLSMC) is designed based on the separation principle, in which the mixed learning algorithm is used to update composite disturbances online, including fault errors, inertia uncertainty, and external disturbances. Finally, a numerical example is provided to demonstrate the effectiveness and superiority of our proposed spacecraft attitude fault-tolerant stabilization control approach.

This paper addresses the image-based visual servoing (IBVS) control problem with an uncalibrated camera, unknown dynamics, and constraints. A novel data-driven uncalibrated IBVS (UIBVS) strategy is proposed, incorporated with the Koopman-based model predictive control (KMPC) algorithm and the adaptive robust Kalman filter (ARKF). First, to alleviate the need for calibration of the camera’s intrinsic and extrinsic parameters, the ARKF with an adaptive factor is utilized to estimate the image Jacobian matrix online, thereby eliminating the laborious camera calibration procedures and improving robustness against camera disturbances. Then, a data-driven MPC strategy is proposed, wherein the unknown nonlinear dynamic model is learned using the Koopman operator theory, resulting in a linear Koopman prediction model. Only input–output data are used to construct the prediction model, and hence, the proposed approach is robust against model uncertainties. Furthermore, with a symmetric quadratic cost function, the proposed approach solves the quadratic programming problem online, and visibility constraints as well as joint torque constraints are taken into account. As a result, the proposed KMPC scheme can be implemented in real time, and the UIBVS performance degradation which arises from the control torque constraints can be avoided. Simulations and comparisons for a 2-DOF robotic manipulator demonstrate the feasibility of the proposed approach. Simulation results further validate that the computation time of the proposed approach is comparable to the one of kinematic-based methods.

This paper addresses the arbitrary-oriented object detection problem with application in robotic grasping. A novel JSD-YOLO (Jensen-Shannon divergence YOLO) model is proposed, which enables real-time grasp detection with high performance. The one-stage object detection network YOLOv5 is modified with a decoupled head, which solves the angle classification problem and rectangle parameter regression problem separately, such that the YOLOv5 network is applicable for robotic grasping and the detection accuracy is significantly improved. A circular smooth label angle classification method is proposed to tackle the boundary discontinuity problem in angle regression, and the periodicity of the angle prediction is guaranteed. A novel JSIoU is designed to calculate the IoU of oriented rectangles, which aims to better measure the discrepancies between the prediction and the ground truth and to avoid the singularity problem when two rectangles are not overlapped. Extensive evaluation on the Cornell and VMRD datasets demonstrates the effectiveness of the JSD-YOLO model in general robotic grasp operations, with 99.7% and 95.7% image-wise split accuracy, respectively.

This paper studies the learning-based model predictive control problem for nonlinear systems with model uncertainties and control constraints. First, a prediction model is constructed offline. The prediction model is composed of a nominal model derived using the first principle with known parameters, and a learning model constructed via the LSTM network to account for model uncertainties and unknown disturbances. Then control input increments are optimized using an online model predictive controller with constraints. Simulation results for trajectory tracking with a robotic arm are presented to verify the robustness and feasibility of the proposed approach.

This paper addresses the robust attitude synchronization issue in a multi-spacecraft formation system subjected to limited communication, space disturbances, modeling uncertainties, and actuator faults. To accommodate limited inter-spacecraft communication, a dynamic event-triggered mechanism is designed to reduce the communication trigger frequency by dynamically adjusting the trigger threshold. Moreover, an event-based distributed self learning neural-network control (SLN2C) law is developed to guarantee robust attitude synchronization during multi-spacecraft formation. In the SLN2C scheme, a learning radial basis function neural network (RBFNN) model is proposed to online approximate and compensate for lumped disturbances, in which an iterative learning algorithm with a variable learning intensity is adopted to update the weight matrix of the RBFNN model. Compared with the traditional fixed learning intensity, a variable one can reduce initial oscillation and weaken the saturation response. Numerical simulations and comparisons are performed to illustrate the effectiveness and superiority of the proposed event-based spacecraft attitude synchronization control method.

微型三轴气浮台教学系统属于航天器姿态确定与控制地面仿真系统.该系统能够从硬件结构、姿态测量与控制算法、嵌入式软件等各个方面模拟卫星姿态确定与控制系统,让学生在实验室环境中就能切身感受卫星系统的工程原理与运行过程.该系统可用于支撑航天器系统工程、航天器姿态确定、航天器导航技术等课程的教学工作,帮助学生实现对航天知识的深度掌握,培养具备从事航天器专业科学研究工作能力的高级人才.

航天器姿态控制系统作为航天器的重要分系统之一,在航天器三轴稳定控制、姿态敏捷机动等方面起着重要的作用.在航天专业实践教学中,由于无法模拟真实的空间环境,学生无法直观地了解航天器的姿态控制过程,给相关课程的学习带来一定的难度.微型三轴气浮台控制系统是航天器地面半物理仿真设备的核心,能够验证全新的航天器智能控制算法,与课堂理论知识相结合,对于航天类专业实践课起到了很好的支撑作用.

深空探测航天器距离远、环境复杂,测控站遥测和遥控操作不能满足控制的实时性和安全性要求,自主管理技术是提高航天器对未知环境的应对能力、提升飞控实效性的主要手段.回顾了深空探测航天器自主管理技术发展的现状,分析了实现自主管理的关键技术,并结合深空探测工程实施和技术发展需求,提出了未来航天器自主管理系统体系结构和软件架构,并进行了仿真实验.

为了满足未来航天器在轨服务部件升级、替换以及航天器大规模快速制造等任务需求,本文提出一种基于分布式智能部件的航天器GNC系统架构,实现无缆化和去中心化.该架构航天器各智能部件间采用无线网络进行信息传输和融合,实现姿态确定与控制.由于无线网络信息传输存在时延问题,分布式智能执行机构所计算的输出力矩也会有一定差异,从而导致航天器姿态控制精度降低.本文利用一致性控制理论,考虑各执行机构之间存在数据传输时延、航天器参数不确定性以及存在干扰力矩等问题,研究基于分布式智能执行机构的航天器姿态协同控制问题,设计一种自适应递阶饱和分布式协同姿态控制律,并通过数学仿真和半物理仿真本文提出的航天器架构和控制方法的有效性.结果表明:在考虑网络传输时延等不确定性情况下,所提出的姿态协同控制方法显著提高了姿态控制精度,可实现分布式智能执行机构协同工作.本文提出的方法为基于分布式部件的新型架构航天器应用奠定基础.

This paper addresses the problem of learning the optimal control policy for a nonlinear stochastic dynamical system with continuous state space, continuous action space and unknown dynamics. This class of problems are typically addressed in stochastic adaptive control and reinforcement learning literature using model-based and model-free approaches respectively. Both methods rely on solving a dynamic programming problem, either directly or indirectly, for finding the optimal closed loop control policy. The inherent `curse of dimensionality' associated with dynamic programming method makes these approaches also computationally difficult. This paper proposes a novel decoupled data-based control (D2C) algorithm that addresses this problem using a decoupled, `open loop - closed loop', approach. First, an open-loop deterministic trajectory optimization problem is solved using a black-box simulation model of the dynamical system. Then, a closed loop control is developed around this open loop trajectory by linearization of the dynamics about this nominal trajectory. By virtue of linearization, a linear quadratic regulator based algorithm can be used for this closed loop control. We show that the performance of D2C algorithm is approximately optimal. Moreover, simulation performance suggests significant reduction in training time compared to other state of the art algorithms.

Mobile robots are being widely used in smart manufacturing, and efficient task assignment and path planning for these robots is an area of high interest. In previous studies, task assignment and path planning are usually solved as separate problems, which can result in optimal solutions in their respective fields, but not necessarily optimal as an integrated problem. Meanwhile, precedence constraints exist between sequential processing operations and material delivery tasks in the manufacturing environment. Thus, those planning methods developed for warehousing and logistics may not simply apply to the environment of smart factories. In this paper, we propose an integrated task and path planning approach based on Looking-backward Search Strategy (LSS) and Regret-based Search Strategy (RSS). In the stage of task assignment, the real paths for mobile robots are identified based on the Cooperative A* (CA*) algorithm and the time and energy consumed by mobile robots and machining centers are calculated. Then a greedy strategy working with LSS or RSS is used to search reasonable task assignments in time-series, which can generate a joint optimal solution for both task assignment and path planning. We verify the validity of the proposed approach in a simulated smart factory and the results show that our approach can improve the operation efficiency of the smart factory and save the time and energy consumption effectively.