Subset selection under budget constraints is critical in applications like multi-robot patrolling, crime deterrence, and targeted marketing, where multiple agents must jointly select targets and plan feasible routes. We formalize this challenge as Multi-Subset Selection with Budget-Constrained Routing (MSS-BCR), involving complex, non-additive cost structures that defy traditional methods. We propose GRIP, a graph-based framework integrating spatial reward fields and policy learning to enable coordinated, budget-aware target selection and routing. GRIP uses attention-based embeddings and constraint-triggered pruning with utility recovery to produce high-quality, feasible solutions. Experiments based on multiple synthetic and real-world datasets show GRIP outperforms baselines in reward efficiency and scalability across varied scenarios.

Modular methods, which decompose complex joint policies into function-specific sub-policies, have been widely adopted to enhance asymptotic performance in single-task cooperative multi-agent reinforcement learning (MARL). However, modular policies trained on source tasks often struggle to generalize to unseen scenarios due to variations across tasks, such as mismatched action spaces and divergent state dynamics. To address this challenge, we propose Mutual Information-Guided Subtask Selection(MIGSS), a novel framework that enhances zero-shot generalization in MARL through two key innovations: a Discriminative Group Trajectory Encoder and Global Attention-Driven Coordination. Specifically, the Discriminative Group Trajectory Encoder remaps agent trajectories by maximizing mutual information between agent trajectories and dynamically assigned groups. This optimizes cross-task consistent group trajectory with broader embedding distributions. This encourages agents in distinct states to select specialized subtasks, effectively promoting functional modularity. Meanwhile, the Global Attention-Driven Coordination employs a global attention mechanism to integrate state information, coordinating group trajectories for expressive credit assignment. Extensive experiments in StarCraft II cooperative scenarios demonstrate that MIGSS significantly outperforms superior zero-shot generalization baselines in both single-task and multi-task settings.Visualization analyses confirm that the learned group trajectories successfully disperse agent trajectories into a consistent and broader embedding space, thereby enhancing subtask modularization.

Existing video-based human pose estimation (HPE) methods commonly rely on large networks to localize body joints across all frames, achieving remarkable accuracy but imposing high memory and computational demands that limit their applications on resource-constrained devices. Moreover, most models lack the capability to accommodate dynamic changes in available resources, which can negatively impact the performance of parallel tasks. To address these issues, this article proposes a novel yet effective framework for efficient and adaptive HPE on resource-constrained devices. Specifically, the proposed approach adopts the knowledge distillation (KD) strategy to train a light-weight pose estimator network, which is capable of executing rapidly with low computational cost. To further increase the overall efficiency, it exploits the temporal coherence between successive video frames and explicitly propagates body joints from previous frames rather than naively extracting them using a pose estimator. Furthermore, a prediction-based mechanism is adopted to facilitate adaptive key-frame selection, dynamically determining the optimal number of keyframes, thus enhancing the overall efficiency and adaptability. Experiments on Penn Action, Sub-JHMDB, and real-world systems demonstrate that the proposed method achieves comparative accuracy, superior efficiency, and robust flexibility in dynamic scenarios.

Federated learning (FL) has emerged as a pivotal approach for edge-based distributed machine learning, yet it faces significant challenges due to the constrained capacities and heterogeneity of edge devices, including non-IID data distribution, communication constraints, and learning inefficiencies. Furthermore, a one-fits-all global model often fails to perform optimally across diverse participating devices. In this paper, we present NestFL, an efficient FL framework for edge computing that can jointly improve the training efficiency and achieve personalization. Specifically, NestFL innovates by incorporating distributed model pruning, creating a hierarchy of structured-sparse subnetworks tailored to the unique resource profiles of client devices. These subnetworks are integrated into a nested global model, ensuring parameter sharing without increasing the parameter space, thereby significantly reducing computational and communication burdens. Meanwhile, it implements a cross-training mechanism, allowing clients to train on a broader dataset and maintain consistent decision boundaries. Furthermore, a weighted aggregation mechanism is designed to improve training performance and maximally preserve personalization. Experimental results in different applications demonstrate the superiority of NestFL over the baseline approaches in terms of model accuracy, convergence speed, and personalization preservation.

This paper presents AdaHPE, an innovative and efficient framework for human pose estimation (HPE) designed specifically for edge computing devices with constrained and fluctuating resources. AdaHPE redefines the conventional HPE workflow by converting the resource-demanding pose regression into a sequence of computationally feasible pose propagation tasks. The framework incorporates a memory-augmented LSTM network with a global memory repository, allowing AdaHPE to adaptively choose keyframes based on real-time data and the device’s resource status, thereby optimizing the trade-off between accuracy and computational efficiency. A reinforcement learning component is further integrated to intelligently adjust the ratio of keyframes used, enhancing the framework’s adaptability. Utilizing policy gradient algorithms, AdaHPE is optimized to maximize a reward function that encourages both accurate and resource-efficient pose estimations, while respecting a given keyframe constraint. Extensive experiments on benchmarks including Penn Action, Sub-JHMDB, NTU RGB+D 120, and real-world datasets demonstrate that AdaHPE can significantly reduce computational overhead compared to per-frame HPE models while preserving high accuracy and robustness under varying resource limitations. Moreover, the seamless compatibility of our approach with various off-the-shelf HPE models highlights its versatility and potential for broad applications.

The increasing network integration of industrial control systems amplifies the risk of cyberattacks on Programmable Logic Controllers (PLCs). In particular, the weak authentication of industrial communication protocols makes PLC program variables vulnerable to manipulation. Current defensive methods cannot reliably identify manipulated variables, even after PLC program manipulations have been detected. To bridge this gap, we presentADIS, a cross-domain Attack Detection and Identification System designed to detect and identify manipulated PLC program variables. Building on a novel state-aware graph representation of the PLC program,ADISdetects variable manipulations by comparing SCADA monitoring data with the control logic defined by the PLC program.ADISfurther identifies suspiciously manipulated program variables by excluding cascading failures from the detected anomalies and tracking suspicious variables based on the edges of the state-aware dependency graph. We have implemented and evaluatedADISon two platforms. The results demonstrate thatADISdetects attacks with a true positive rate exceeding 99% and a false positive rate of less than$0.04{\unicode {0x2030}}$. Furthermore, it successfully identifies manipulated program variables with up to a 71.3% reduction in suspicious variables compared to a baseline method.

Due to their high flexibility and strong maneuverability, unmanned aerial vehicles (UAVs) have attracted lots of attention and are widely employed in many fields. Especially in target encirclement applications, UAVs have shown great advantages in adaptability and reliability, and can efficiently fly to and evenly surround the targets in complex and dynamic environments. In this paper, we concentrate on the cooperative target encirclement problem of heterogeneous UAVs and try to propose a multi-agent reinforcement learning approach to solve the problem. First, with the models of heterogeneous UAVs and obstacles, we analyze the collision avoidance, motion continuity, and energy consumption constraints of UAVs, and formulate the cooperative target encirclement problem as a multi-constraint combinatorial optimization one. Then, inspired by the humans’ learning experience that curiosity provides a powerful motivator for humans to explore, discover, and acquire new knowledge, we propose an extrinsic-and-intrinsic reward-based multi-agent reinforcement learning approach to cooperatively control the behaviors of UAVs and achieve the target encirclement missions. Simulation experiments with randomly generated environments are conducted to evaluate the performance of our approach, and the results show that our approach has a significant advantage in terms of average reward, encirclement success rate, encirclement time, and encirclement energy consumption.

Unmanned Aerial Vehicles (UAVs) are emerging as a pivotal component in the field of intelligent transportation systems. Leveraging virtual-physical interactions, digital twin technology significantly enhances the adaptability of UAVs in complex traffic environments. However, current approaches still pose three major challenges: contextual adaptability, timely responsiveness, and effective multi-UAV coordination. In this paper, we introduce EnFlexiTwin, a digital twin enhancement assistance platform seamlessly integrated with AdaSor, a lightweight adaptive data selector. EnFlexiTwin automates the construction of incremental learning datasets, enabling real-time enhancements that allow digital twins to adapt to new time series data while preserving historical knowledge. We test EnFlexiTwin on a real-world dataset from low-altitude small-parcel delivery. The results show improved performance and adaptability of digital twins. Furthermore, time-varying simulations on real-world dataset and experiments on a practical air-ground cooperative UAV swarm application highlight that EnFlexiTwin achieves superior enhancements under varying real-time requirements and swarm scale compared to baseline approaches.

Multiagent routing problems, arising from practical applications, such as logistics, transportation, and emergency response, face challenges due to the exponential growth of the search space with increasing problem scales. This article proposes RouteMaker to address the often-overlooked multiagent routing problems involving dedicated multiple depots. RouteMaker leverages role-interaction-based graph neural network (RIGNN) to realize effective locations assignments and integrates an advanced planner to plan travel path for each agent. RouteMaker is trained on small-scale problems and can produce comparable or superior approximate optimal solutions compared with the best heuristic baselines. Notably, the learned RouteMaker generalizes seamlessly to large-scale problems and real-world problems without the need for fine-tuning, delivering significantly higher quality solutions in relatively less time. For scenarios involving 40 agents and 1000 locations, RouteMaker achieves over $600\times $ speed improvement and more than 88% cost reduction, compared with the representative classical heuristic solver (ORTools).

The Industrial Internet of Things (IIoT) has become a critical technology to accelerate the process of digital and intelligent transformation of industries. As the cooperative relationship between smart devices in IIoT becomes more complex, obtaining deterministic responses of IIoT periodic time-critical computing tasks becomes a crucial and nontrivial problem. However, few current works in cloud/edge/fog computing focus on this problem. This paper is a pioneer in exploring deterministic scheduling and network structural optimization problems for IIoT periodic time-critical computing tasks. We first formulate the two problems and derive theorems to help quickly identify computation and network resource sharing conflicts. Based on this, we propose a deterministic scheduling algorithm,IIoTBroker, which realizes a deterministic response for each IIoT task by optimizing the fine-grained computation and network resources, and a network optimization algorithm,IIoTDeployer, which provides a cost-effective structural upgrade solution for existing IIoT networks. Our methods are illustrated to be cost-friendly, scalable, and deterministic response guaranteed with low computation cost from our simulation results.

A neural processing unit (NPU) is a microprocessor which is specially designed for various types of neural network applications. Because of its high acceleration efficiency and lower power consumption, the airborne embedded system has widely deployed NPU to replace GPU as the new accelerator. Unfortunately, the inherent scheduler of NPU does not consider real-time scheduling. Therefore, it cannot meet real-time requirements of airborne embedded systems. At present, there is less research on the multi-task real-time scheduling of the NPU device. In this article, we first design an NPU resource management framework based on Kubernetes. Then, we propose WAMSPRES, a workload-aware NPU performance model based soft preemptive real-time scheduling method. The proposed workload-aware NPU performance model can accurately predict the remaining execution time of the task when it runs with other tasks concurrently. The soft preemptive real-time scheduling algorithm can provide approximate preemption capability by dynamically adjusting the NPU computing resources of tasks. Finally, we implement a prototype NPU scheduler of the airborne embedded system for the fixed-wing UAV. The proposed models and algorithms are validated on both the simulated and realistic task sets. Experimental results illustrate that WAMSPRES can achieve low prediction error and high scheduling success rate.

Electric vehicles (EVs), which have become one of the most important commuting vehicles in the world, heavily depend on the support of robust and efficient grids. Many researchers focus on optimizing the charging of EVs by the grid. However, they overlook the emergency charging when the large-scale grid fails. Inspired by the DC-2-DC technology, EVs can achieve vehicle-2-vehicle (V2V) energy sharing between each other, which inspires us to study leveraging the significant number of electric buses (e-buses) as effective and cost-efficient standby energy to charge low-power EVs when a large-scale grid outage occurs, whereas the feasibility, scheduling algorithm, and performance of e-bus-based V2V energy sharing remain open questions. With this in mind, we first reveal that it is feasible for e-buses to serve as effective standby power for low-power EVs, after careful analysis of real-world data. Then, we conduct a data-driven estimation of the energy consumption to determine the volume of the V2V shared energy for large-scale EVs. Accordingly, we formulate the e-bus-based V2V energy sharing problem, whose two objectives are to maximize the total number of the sufficiently charged EVs and to minimize the distance of these EVs moving to the e-bus for charging. The first objective is to charge more low-power EVs with the limited energy volume of the e-buses and the second objective is to reduce the range anxiety of the low-power EV drivers. Observing that existing algorithm is time-consuming or inefficient, which cannot be applied for the problem instance with a large number of e-buses and EVs, we design a low-complexity approximation algorithm for the problem. Both theoretical analysis and comprehensive data-driven evaluation demonstrate that the proposed algorithm, 1) significantly optimizes the optimization objectives by 23.6% and 15.8% on average, and up to 34.8% and 34.0% in extreme cases, compared with the existing approximation algorithm and 2) achieves over$100\times $execution speed improvement compared to the linear programming (LP)-based algorithm and evolutionary learning (EL) algorithms. The results demonstrate that the proposed algorithm achieves a better overall performance and makes it a promising solution for large-scale problem instances.

Unmanned Aerial Vehicles (UAVs) are widely applied in smart city applications such as urban sensing and delivery, due to the UAVs’ agility, low cost and not being restricted by ground road conditions. However, the limited battery capacity becomes one of the biggest obstacles to the application of UAVs. To address this issue, this paper investigates an emergency response application, in which UAVs generally ride crowdsourced buses to save energy and respond to a stochastic emergency event (such as a traffic accident) when the event occurs. For the bus-based UAV response paradigm, a single UAV response process with the constraint of the bus mobility is first modeled. Subsequently, a data-driven UAV path planning algorithm is designed. Then two emergency response cases by multi-UAV are investigated. One case is irregular emergency response, whose objective is to maximize the temporal-spatial coverage of the urban area. The other case is predictable emergency response, which optimizes the response performance to these emergencies. Thereafter, the bus-stimulating problems for the two cases are formulated and solved. Finally, utilizing a real-world bus trajectory dataset generated by a large-scale bus fleet and a traffic event dataset, the emergency response performance of the bus-based UAV response paradigm is comprehensively evaluated. The results show that (1) with only 30 UAVs, 90% of Shenzhen city can be covered in the irregular emergency response case; (2) with only 50 UAVs, the average response delay to the emergencies is shorter than 1.5 minutes, which is 56% shorter than baselines, in the predictable emergencies response case.

Multiedge cooperative computing that combines constrained resources of multiple edges into a powerful resource pool has the potential to deliver great benefits, such as a tremendous computing power, improved response time, and more diversified services. However, the mass heterogeneous resources composition and lack of scheduling strategies make the modeling and cooperating of multiedge computing system particularly complicated. This article first proposes a system-level state evaluation model to shield the complex hardware configurations and redefine the different service capabilities at heterogeneous edges. Second, an integer linear programming model is designed to cater for optimally dispatching the distributed arriving requests. Finally, a learning-based lightweight real-time scheduler, CoRaiS is proposed. CoRaiS embeds the real-time states of the multiedge system and requests information, and combines the embeddings with a policy network to schedule the requests, so that the response time of all requests can be minimized. Evaluation results verify that the CoRaiS can make a high-quality scheduling decision in real-time, and can be generalized to other multiedge computing system, regardless of the system scales. Characteristic validation also demonstrates that the CoRaiS successfully learns to balance loads, perceive real-time state and recognize heterogeneity while scheduling.

The fiercely competitive business environment and increasingly personalized customization needs are driving the digital transformation and upgrading of the manufacturing industry. IIoT intelligence, which can provide innovative and efficient solutions for various aspects of the manufacturing value chain, illuminates the path of transformation for the manufacturing industry. It’s time to provide a systematic vision of IIoT intelligence. However, existing surveys often focus on specific areas of IIoT intelligence, leading researchers and readers to have biases in their understanding of IIoT intelligence, that is, believing that research in one direction is the most important for the development of IIoT intelligence, while ignoring contributions from other directions. Therefore, this paper provides a comprehensive overview of IIoT intelligence. We first conduct an in-depth analysis of the inevitability of manufacturing transformation and study the successful experiences from the practices of Chinese enterprises. Then we give our definition of IIoT intelligence and demonstrate the value of IIoT intelligence for industries in fucntions, operations, deployments, and application. Afterwards, we propose a hierarchical development architecture for IIoT intelligence, which consists of five layers. The practical values of technical upgrades at each layer are illustrated by a close look on lighthouse factories. Following that, we identify seven kinds of technologies that accelerate the transformation of manufacturing, and clarify their contributions. The ethical implications and environmental impacts of adopting IIoT intelligence in manufacturing are analyzed as well. Finally, we explore the open challenges and development trends from four aspects to inspire future researches.

New generation airborne embedded system has deployed Graphical Processing Units (GPUs) to raise processing capability to meet growing computational demands. Applications in the airborne embedded system have strict real-time constraints. Therefore, it is necessary to accurately predict timing behaviors of those applications. Many previous work propose GPU performance models to estimate the execution time of applications. However, most of those models do not consider the impact of co-execution on the GPU performance. In this paper, we propose a workload-aware GPU performance model to predict the execution time of applications executed concurrently on a single GPU. Experimental results illustrate that the proposed model can achieve a 5.1%-11.6% prediction error in a real airborne embedded hardware platform.

Vehicularad hocnetworks (VANETs) have far-reaching application potentials in the intelligent transportation system (ITS) such as traffic management, accident avoidance and in-car infotainment. However, security has always been a challenge to VANETs, which may cause severe harm to the ITS. Sybil attack is considered as a serious security threat to VANETs since the adversary can disseminate false messages with multiple forged identities to attack various applications in the ITS. RSSI-based Sybil nodes detection is an efficient scheme against Sybil attacks, which adopts position estimation, distribution verification or similarity comparison to identify Sybil nodes. However, when Sybil nodes conduct power control to deliberately change transmission powers, the received RSSI values would change correspondingly, which leads to inaccurate localization or different RSSI time series of these Sybil nodes. Thus, it is very difficult to differentiate Sybil nodes from normal nodes via conventional RSSI-based methods. This paper first discusses potential power control models (PCMs) for launching Sybil attacks in VANETs, then presents two simple Sybil attack models and three sophisticated Sybil attack ones with or without power control in detail, finally proposes a power control identification Sybil attack detection (PCISAD) scheme to find anomalous variations in RSSI time series, which are then used to identify Sybil nodes via a linear SVM classifier. Extensive simulations and real-world experiments prove that the proposed scheme can effectively deal with Sybil attacks with power control.