This paper introduces a Physics-Informed Koopman Neural Operator (PI-KNO) for augmented dynamics visual servoing of multirotors that integrates Koopman operator theory with neural networks. The proposed method establishes a structured learning framework that effectively captures complex system dynamics while embedding physics-based priors. Unlike fully data-driven approaches, PI-KNO improves generalization and minimizes reliance on extensive real-world training data by employing a hybrid loss function that combines physics-informed constraints with real-time observations. The learned model is incorporated into a monotonically weighted nonlinear model predictive control (NMPC) framework, ensuring precise trajectory tracking while adhering to state and input constraints. Experimental results demonstrate that PI-KNO reduces training time by 16.81% and enhances tracking accuracy by 19.56% compared to conventional Data-Driven Koopman Neural Operators (DD-KNO) and Physics-Informed Neural Networks (PINN). Additionally, under 70.83% uncertainty in camera parameters, PI-KNO achieves 10.6% and 22.2% lower tracking errors than PINN and DD-KNO, respectively. These findings underscore the robustness and efficiency of the proposed approach for real-time multirotor visual servoing applications. Note to Practitioners - This work presents an implementation oriented view of a learning based predictive controller for aerial robots designed to operate within the limits of onboard computation and sensing. The proposed PI-KNO approach combines physical modeling and data driven learning to create an accurate and stable dynamic predictor suitable for real time deployment. The architecture is distributed between an NVIDIA Jetson and a Pixhawk. The Jetson runs the vision front end, state estimator, PI-KNO predictor, and NMPC optimizer. The estimator fuses visual and inertial data to provide position, velocity, and attitude states, while the NMPC computes high level motion commands at about 30Hz using the PI-KNO rollout. The Pixhawk executes inner rate loops at 250Hz through the native autopilot for attitude stabilization and motor mixing. Communication between the Jetson and Pixhawk uses standard MAVLink setpoints, requiring no firmware modification. The training workflow begins with a nominal visual servoing multirotor model and limited flight data, from which the operator is trained offline using a physics-informed regularizer. At runtime, the estimator updates the state, PI-KNO predicts short horizon dynamics, the NMPC optimizes control sequences, and the Pixhawk executes the commands. This setup achieves reliable tracking across trajectories, maintains physical consistency under uncertainty, and fits within the computational limits of embedded hardware.

In this paper, a finite-time robust safe cooperative control strategy is proposed for heterogeneous multi-agent systems (HMAS) in cluttered obstacle environments under input saturation, external disturbances, and Denial-of-Service (DoS) attacks. An adaptive event-triggered observer is designed at the cyber layer to achieve distributed resilient tracking under DoS-induced communication networks. At the physical layer, a distributed control scheme based on finite-time robust control barrier function (FT-RCBF) is first developed to ensure fast obstacle avoidance for HMAS. The proposed method is applied to a cooperative forest traversal and monitoring task for ground-air autonomous systems, and its effectiveness and robustness are verified through simulations.

This paper investigates the distributed bipartite tracking problem for heterogeneous multi-agent systems (MASs) on signed directed networks. Leaders with both cooperative and competitive interactions and two different types of followers form the heterogeneous MASs. The dynamics of each agent are described in strict feedback form by parameters of different structures. The so-called reference signal tracking approach is employed in the hierarchical design to generate reference signal generators and bipartite tracking controllers. The control gains of leaders and followers are integrated into the design of reference signal generators, which utilize locally estimated states and remain independent of the communication topology. The convergence of the proposed heterogeneous MASs is proved. The simulation result demonstrates the effectiveness of the proposed hierarchical design.

Mean field reinforcement learning (MFRL) addresses the problem of dimensional explosion for large-scale multiagent systems. However, MFRL averages the actions of neighbors equally while discarding the diversity and distinct features between individuals, which may lead to poor performance in many application scenarios. In this article, a new MFRL algorithm termed temporal weighted mean filed Q-learning (TWMFQ) is proposed. TWMFQ introduces a temporal compensated multihead attention structure to construct the weighted mean-field framework, which can sort out the complex relationships within the swarm into the interactions between specific agent and the weighted virtual mean agent. This approach allows the mean Q-function to represent the swarm behavior more informatively and comprehensively. In addition, an advanced sampling mechanism called mixed experience replay is established, which enriches the diversity of samples and prevents the algorithm from falling into local optimal solution. The comparison experiments on MAgent and multi-USV platform justify the superior performance of TWMFQ across different population sizes.

This article presents a novel learning-based collaborative control framework to ensure communication security and formation safety of nonlinear multiagent systems (MASs) subject to denial-of-service (DoS) attacks, model uncertainties, and barriers in environments. The framework has a distributed and decoupled design at the cyber-layer and the physical layer. A resilient control Lyapunov function-quadratic programming (RCLF-QP)-based observer is first proposed to achieve secure reference state estimation under DoS attacks at the cyber-layer. Based on deep reinforcement learning (RL) and control barrier function (CBF), a safety-critical formation controller is designed at the physical layer to ensure safe collaborations between uncertain agents in dynamic environments. The framework is applied to autonomous vehicles for area scanning formations with barriers in environments. The comparative experimental results demonstrate that the proposed framework can effectively improve the resilience and robustness of the system.

This article discusses the robust predefined output containment (RPOC) control problem for heterogeneous nonlinear multiagent systems having multiple uncertain nonidentical leaders. In order to solve this problem, a new kind of distributed observer-based RPOC control framework is presented. First, for obtaining the information of nonidentical leaders' dynamics, including uncertain parameters in leaders' system matrices, output matrices, states, and outputs, four kinds of adaptive observers are constructed in a fully distributed form without any knowledge of the dynamics of nonidentical leaders, exactly. Second, on the basis of adaptive learning technique, a new RPOC controller is then developed by using the presented observers, where the adaptive observers can make up for the uncertain parameter in followers' dynamics, and the solutions of output regulation equations can be obtained adaptively by the developed adaptive strategy. Furthermore, with the help of the output regulation method and Lyapunov stability theory, the RPOC criteria for the considered system under unknown nonidentical leaders' dynamics are derived from the constructed controller. Finally, a simulation example is provided to demonstrate the effectiveness of the proposed RPOC controller.

A safe time-varying formation (TVF) control framework is proposed in this article for heterogeneous multiagent systems under the constraints of denial of service (DoS) attacks, noncooperative dynamic obstacles, and input saturation. The framework integrates both the cyber-layer and physical-layer components to address the challenges posed by these adverse conditions. In the cyber-layer, a distributed resilient observer is provided based on a control Lyapunov function (CLF)-quadratic program (QP). This observer estimates a reference exosystem, effectively decoupling heterogeneous dynamics from unsafe networks and optimizing the system resilience against DoS attacks. At the physical-layer, for the first time, a collision-free TVF controller is presented based on the CLF-exponential control barrier function-QP. The controller guarantees high-order heterogeneous agents' operation safety under noncooperative obstacles and input saturation. The effectiveness and advantages of the proposed algorithms are verified through the comparative simulations and experiments conducted on a physical system comprising unmanned aerial vehicles and unmanned ground vehicles.

This article presents a novel event and learning-based resilient formation control strategy for heterogeneous multiagent systems subjected to denial-of-service (DoS) attacks and uncertainties. It involves a decoupled cyber-layer and physical system layer design that enables a distributed and model-free approach. In the cyber-layer, the design is an event-triggered resilient observer for a reference exosystem estimation under DoS attacks using dual adaptive laws and an optimal algorithm. This approach eliminates the need for global information of the communication topology and enhances system resilience under attacks. In the physical system layer, the design is a model-free formation output controller for heterogeneous agents based on off-policy reinforcement learning. The incorporation of a new rank condition improves the convergence performance. Experiments using unmanned ground vehicles are conducted for scanning a physical area to verify the effectiveness and resilience of the proposed control strategy.

In this paper, we propose a reinforcement learning-based safe control strategy for uncertain heterogeneous multi-agent systems. The objective is to achieve collision-free time-varying formations under switching topologies and with limited network resources. Without requiring global communication information, an event-triggered observer is designed to decouple the heterogeneous dynamics from switching networks and reduce data transmission frequency. A data-driven off-policy reinforcement learning algorithm is developed for addressing the robust safe formation control problem. The algorithm is capable of solving non-quadratic optimization problems without requiring model information. The proposed strategy is applied to a multi-unmanned ground vehicle (UGV) system for a patrolling mission, and the experimental results verified the effectiveness of the proposed strategy.

Cloud computing attracts increasing attention in processing dynamic computing tasks and automating the software development and operation pipeline. In many cases, the computing tasks have strict deadlines. The cloud resource manager (e.g., orchestrator) effectively manages the resources and provides tasks Quality of Service (QoS). Cloud task scheduling is tricky due to the dynamic nature of task workload and resource availability. Reinforcement Learning (RL) has attracted lots of research attention in scheduling. However, those RL-based approaches suffer from low scheduling performance robustness when the task workload and resource availability change, particularly when handling time-critical tasks. This paper focuses on both challenges of robustness and deadline guarantee among such RL, specifically Deep RL (DRL)-based scheduling approaches. We quantify the robustness measurements as the retraining time and investigate how to improve both robustness and deadline guarantee of DRL-based scheduling. We propose MLR-TC-DRLS, a practical, robust Meta Deep Reinforcement Learning-based scheduling solution to provide time-critical tasks deadline guarantee and fast adaptation under highly dynamic situations. We comprehensively evaluate MLR-TC-DRLS performance against RL-based and RL advanced variants-based scheduling approaches using real-world and synthetic data. The evaluations validate that our proposed approach improves the scheduling performance robustness of typical DRL variants scheduling approaches with 97%–98.5% deadline guarantees and 200%–500% faster adaptation.

In this article, a distributed adaptive event-triggered formation control strategy is proposed for unified nonlinear heterogeneous multiagent systems under uncertainties and disturbances to achieve time-varying formations. To reduce the frequency of data transmission, a distributed dual adaptive observer with an event-triggered strategy is developed to estimate the states of a reference exosystem. Without incurring prior global information about a communication graph, a novel robust formation controller, with dynamic distributed compensators for uncertainties and disturbances, is designed based on an observer result and a nonlinear internal control principle. Finally, both simulation and experiment are conducted for tracking and patrolling formation to verify the effectiveness of the proposed formation control strategy and its robustness. Note to Practitioners—This article addresses the collaborative formation problem of multiagent systems that has potential applications in transportation and disaster relief. The design of robust and energy-saving coordination strategies is challenging in heterogeneous multivehicle systems. The proposed distributed method is suitable for large-scale uncertain heterogeneous systems, and the use of the dual adaptive event-triggered strategy reduces the data transmission rate.

In practice, the dual constraints of limited interaction capabilities and system uncertainties make it difficult for large-scale multiagent systems (MASs) to achieve intelligent collaboration with incomplete local relative information. In this article, a review is conducted on the recent development of MASs intended for intelligent control, including consensus problem, formation control, and flocking control. Based on the limitations of the interaction level and the constraints of the individual system level, the published results on intelligent control are categorized into limited sensing-based control, event-based control, pinning-based control, resilient control, and collaborative control under system constraints. Also, the applications of intelligent control for MASs are presented, especially for robotics, complex networks, and transportation. Finally, a discussion is given about the challenges and future directions of research in this field.

Safety ranks the first in Air Traffic Management (ATM). Accurate trajectory prediction can help ATM to forecast potential dangers and effectively provide instructions for safely traveling. Most trajectory prediction algorithms work for land traffic, which rely on points of interest (POIs) and are only suitable for stationary road condition. Compared with land traffic prediction, flight trajectory prediction is very difficult because way-points are sparse and the flight envelopes are heavily affected by external factors. In this paper, we propose a flight trajectory prediction model based on a Long Short-Term Memory (LSTM) network. The four interacting layers of a repeating module in an LSTM enables it to connect the long-term dependencies to present predicting task. Applying sliding windows in LSTM maintains the continuity and avoids compromising the dynamic dependencies of adjacent states in the long-term sequences, which helps to improve accuracy of trajectory prediction. Taking time dimension into consideration, both 3-D (time stamp, latitude and longitude) and 4-D (time stamp, latitude, longitude and altitude) trajectories are predicted to prove the efficiency of our approach. The dataset we use was collected by ADS-B ground stations. We evaluate our model by widely used measurements, such as the mean absolute error (MAE), the mean relative error (MRE), the root mean square error (RMSE) and the dynamic warping time (DWT) methods. As Markov Model is the most popular in time series processing, comparisons among Markov Model (MM), weighted Markov Model (wMM) and our model are presented. Our model outperforms the existing models (MM and wMM) and provides a strong basis for abnormal detection and decision-making.