This article investigates the finite-horizon $H_{\infty } $ tracking control problem for discrete-time (DT) linear systems with partial observation and unknown dynamics from a game-theoretic perspective. Unlike existing reinforcement learning (RL) approaches that primarily address infinite-horizon, time-invariant systems with full state information, our setting requires solving time-varying Riccati equations and developing model-free methods that rely solely on input-output data. To tackle these challenges, we reconstruct the system state from historical input-output trajectories, driving to a data-driven system representation, and we define an input-output-based time-varying $Q$ -function. We then propose two minimax $Q$ -learning algorithms that do not require an initially admissible policy and avoid the use of a discount factor, thereby removing a long-standing obstacle to stability guarantees. Moreover, the framework readily extends to both infinite-horizon and time-varying systems without structural modifications. Convergence is proved theoretically, and the effectiveness of the algorithms is validated through simulations.

Gait recognition enables contact-free, long-range person identification that is robust to clothing variations and non-cooperative scenarios. While existing methods perform well in controlled environments, they struggle with cross-vertical view scenarios where elevation changes induce severe perspective distortions and self-occlusions. Our analysis reveals conventional CNN-based approaches relying on single-scale receptive fields fail to capture hierarchical frequency features, while standard self-attention mechanisms tend to over-smooth critical high-frequency edge patterns. To tackle this challenge, we propose Cross-Vertical-View Network(CVVNet), a frequency aggregation architecture specifically designed for robust cross-vertical-view gait recognition. CVVNet employs a Multi-Scale Attention Gated Aggregation (MSAGA) module which consists of a High-Low Frequency Extraction module (HLFE) and a Dynamic Gated Aggregation (DGA) mechanism. Specifically, HLFE adopts parallel multi-scale convolution/max-pooling path and self-attention path as high- and low-frequency mixers for effective multi-frequency feature extraction from input silhouettes, while DGA is introduced to adaptively adjust the fusion ratio of frequency and spatial features. The integration of HLFE and DGA enables CVVNet to effectively handle distortions from view changes, significantly improving the recognition robustness across different vertical views. Experimental results show that our CVVNet achieves state-of-the-art performance on both datasets, delivering an 8.6% improvement on DroneGait while retaining the leading position on Gait3D.

Human activity recognition (HAR) is an important task in the field of human-computer interaction. Given the penetration of WiFi devices in our daily lives, HAR using WiFi channel state information (CSI) is a more cost-efficient and comfortable approach. However, most existing approaches ignore the correlation between CSI sub-carriers, which makes their models inefficient and need to rely on deeper and more complex networks to further improve performance. To solve these problems, we propose a reconstructed WiFi CSI phase based HAR approach (WiPhase), which contains a two-stream model to fuse both temporal features and sub-carrier correlation features of reconstructed CSI phase. Specifically, a gated pseudo-Siamese network (GPSiam) is designed to capture the temporal features of the reconstructed sparse CSI phase integration representation (CSI-PIR), and a dynamic resolution based graph attention network (DRGAT) is designed to capture the nonlinear correlation between CSI sub-carriers by the reconstructed CSI phase graph. Furthermore, dendrite network (DD) makes the final decision by combining the features output from GPSiam and DRGAT. Experimental results show that WiPhase outperforms the existing state-of-the-art approaches.

This paper studies the motion control problem of an aerial manipulator that consists of a quad copter base and a robotic arm. We propose a novel control method that consists of a lightweight dynamic model and an MPC-based trajectory converter to perform accurate tracking control for the end-effector. The proposed method is verified by a step response experiment on the GAZEBO dynamics simulation platform. The experiment results show that the angular velocity disturbance of the end-effector is suppressed by the proposed method.

This article studies the stability issue of networked switched systems (NSSs) under denial-of-service (DoS) attacks. To address this issue, the derived limitations imposed on both the frequency of DoS attacks on each subsystem and the upper limit of attack duration that each subsystem can tolerate are mode-dependent, which is more efficient and flexible than the current results for NSSs. Moreover, we reveal the relationship between the upper bound of the average maximum tolerable attack duration associated with the corresponding subsystem and the actual mode-dependent average dwell time. Furthermore, we identify that the total tolerable DoS attack duration as a percentage of the system runtime in this article can be higher than existing results. Finally, an example is given to demonstrate the effectiveness of our work.

In this work, we investigate the unknown moving-target circumnavigation problem in GPS-denied environments. A minimum of two tasking agents is excepted to circumnavigate the target cooperatively and symmetrically without prior knowledge of its position and velocity in order to achieve optimal sensor coverage persistently for the target. To achieve this goal, we develop a novel adaptive neural anti-synchronization (AS) controller. Based on relative distance-only measurements between the target and two tasking agents, a neural network is used to approximate the displacement of the target such that the position of the target can be estimated accurately and in real time. On this basis, a target position estimator is designed by considering whether all agents are in the same coordinate system. Furthermore, an exponential forgetting factor and a new information utilization factor are introduced to improve the accuracy of the aforementioned estimator. Rigorous convergence analysis of position estimation errors and AS error shows that the closed-loop system is globally exponentially bounded by the designed estimator and controller. Both numerical and simulation experiments are conducted to demonstrate the correctness and effectiveness of the proposed method.

This article investigates the problem of multiagent formation control for obstacle traversing mission with the support of distance and displacement measurements in GPS-denied environments. A key challenge in solving this problem is simultaneous estimation of the obstacle's position, determining the relative positions of multiple agents and their formation transition. In this work, we propose to solve the problem by integrating an embedded position estimation system with bounded control inputs into event-triggered formation traverse (ETFT) controller. The convergence analysis of estimation error on location estimation has been provided. Moreover, the ETFT controller for the formation transition has been proved that the multiagent can traverse easily through obstacles based on relative-distance only measurements. Simulations and real-world experiments have both been conducted to demonstrate the effectiveness of the proposed methods.

This work presents an approach for realizing the formation control of a second-order multiagent system using stochastic noises. The system is modeled as a virtual structure tracking control system with unicycle-type robots under a star-topology. A method for controlling the linear and rotational acceleration by stochastic feedback is proposed. Unlike traditional control methods, this approach does not require negative feedback, which allows for wider ranges of control gains. In addition, compared with the stochastic control problem of the first-order system, it provides a smoother stochastic trajectory of motion, which reduces the burden on the actuators. The stochastic motion also has the attached benefit of providing robot formations with a strategic advantage in some cases. The position, velocity, and angle errors are analyzed through the Itô’s formula, basic inequalities, and the Lyapunov method. Finally, the system and controller are tested through both numerical and physical simulations.

To meet the growing demand of electrical dispatch, accurate prediction of a dynamic thermal rating (DTR) for transmission lines is crucial. However, the uncertainty of DTR caused by weather data imbalance constraints poses a risk to secure grid operation. To this end, a secure probabilistic interval prediction model is developed to tap potential DTR using bootstrap plus-guided time-series generative adversarial networks (TimeGAN) and spatiotemporal graph network (STGN), called BP-G2NN. The TimeGAN is used to augment the data to solve the weather data imbalance problem. And the STGN model is developed to dynamically strengthen the weight of the model to the key potential feature. In addition, the designed BP strategy restricts the frequency of maximum DTR exceeding the upper bound of prediction intervals and solves the inherent problem of quantile crossings. The simulation experiments using real data verify the validity of the model for DTR decisions.

This article proposes a distributed optimal attitude synchronization control strategy for multiple quadrotor unmanned aerial vehicles (QUAVs) through the adaptive dynamic programming (ADP) algorithm. The attitude systems of QUAVs are modeled as affine nominal systems subject to parameter uncertainties and external disturbances. Considering attitude constraints in complex flying environments, a one-to-one mapping technique is utilized to transform the constrained systems into equivalent unconstrained systems. An improved nonquadratic cost function is constructed for each QUAV, which reflects the requirements of robustness and the constraints of control input simultaneously. To overcome the issue that the persistence of excitation (PE) condition is difficult to meet, a novel tuning rule of critic neural network (NN) weights is developed via the concurrent learning (CL) technique. In terms of the Lyapunov stability theorem, the stability of the closed-loop system and the convergence of critic NN weights are proved. Finally, simulation results on multiple QUAVs show the effectiveness of the proposed control strategy.

Human activity recognition (HAR) is an important task due to its far-reaching applications, such as surveillance, healthcare systems, and human-computer interaction. Recently, Channel State Information (CSI)-based HAR has attracted increasing attention in the research community due to its ubiquitous availability, good user privacy, and fewer constraints on working conditions. Most of the existing methods for CSI-based HAR use various deep learning models, such as Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), and Transformers, to distinguish activities based on their temporal patterns. Despite their remarkable effectiveness, these methods solely focus on temporal patterns while ignoring the correlations among sub-carriers. This limitation prevents them from achieving further performance improvement. Moreover, recent works often involve advanced yet massive and inefficient neural architectures, like Transformers, to obtain satisfactory recognition accuracy. The performance gain is traded off with a steep increase in model complexity, which leads to low efficacy and high training/inference costs outsides the small time window. To address these issues, we propose a lightweight CSI-based HAR model. Our model makes the first effort to explore the graphical correlations of CSI sub-carriers, working in conjunction with a temporal causal convolution module. The high efficacy design enables our model to be highly effective without requiring excessive model complexity. Extensive experiments conducted on four real-world datasets demonstrate that our model outperforms state-of-the-art methods, including a strong Transformer-based baseline. It achieves an average improvement of 8 percentage points in recognition accuracy, with only 10% of the parameters compared to the Transformer-based method (4.95M vs. 49.24M). Additionally, our model is significantly faster, with empirical training and execution times at least 2.07 times faster than the baseline.

This paper investigates the stochastic moving target encirclement problem in a realistic setting. In contrast to typical assumptions in related works, the target in our work is non-cooperative and capable of escaping the circle containment by boosting its speed to maximum for a short duration. In extreme conditions, where GPS signals are not available, weight restrictions are present, and ground guidance is absent, the agents can rely solely on their onboard single-modality perception tools to measure the distances to the target. The distance measurement allows for creating a position estimator by providing a target position-dependent variable. Furthermore, the construction of the unique distributed anti-synchronization controller (DASC) can guarantee that the two agents track and encircle the target swiftly. The convergence of the estimator and controller is rigorously evaluated using the Lyapunov technique. A real-world UAV-based experiment is conducted to illustrate the performance of the proposed methodology in addition to a simulated Matlab numerical sample. Our video demonstration can be found in the URL https://youtu.be/EDVLvP-bk8M.

This work is concerned with the anti-synchronization (A-S) of drive-response (D-R) memristive neural networks (MNNs) based on fuzzy rules. A novel impulsive sampled-data communication mechanism is proposed by considering information security of the MNNs, in which the random response delay of sensors caused by the impulse signal is also investigated. As the state of MNNs cannot be outputted accurately and transmitted persistently, the state observers of the D-R MNNs are established, which is beneficial to design the A-S controller. By analyzing the stability of the augmented error system (AES) based on the fuzzy-based Lyapunov-Krasovskii functional (FLKF), sufficient conditions of the A-S between D-R MNNs are derived. An illustrative example is given to verify the effectiveness of the proposed A-S strategies.

The bounded antisynchronization (AS) problem of multiple discrete-time neural networks (NNs) based on the fuzzy model is studied, in consideration of the differences in quantity and communication among different NN groups, the variabilities of dynamics, and communication topological affected by environments. To reduce the energy consumption of communication, a cluster pinning communication mechanism is proposed, and an impulsive observer is designed to estimate the state of target NN. Then, a multilevel hybrid controller based on the impulsive observer is built including the AS controller and the bounded synchronization (BS) controller. Sufficient conditions for bounded AS are obtained by analyzing the stability of the BS augmented error (BSAE) and the AS augmented error (ASAE) based on the fuzzy-based Lyapunov functional (FBLF). Finally, a numerical example and an application example are given to verify the validity of the obtained results.

This article investigates the adaptive consensus control problem for a group of multirotor unmanned aerial vehicles (MUAVs) subject to dynamic state constraints and unmatched external disturbances. An adaptive inner–outer loop controller is devised based on the backstepping method, where the issue of “explosion of complexity” is solved via a first-order sliding-mode differentiator. By introducing a barrier function-based state transformation technique into the outer loop controller design, the dynamic constraints covering different types of time-varying state constraints can be addressed without reconfiguring the controller structure. Meanwhile, a neural-network-based disturbance observer is constructed to estimate the external disturbances. Consequently, the applicability and robustness of controller are improved, such that the position tracking control can be implemented in severe environments. Moreover, the inner loop controller is established by virtue of a distributed sliding-mode estimator so as the consensus control for attitude systems of multiple MUAVs can be realized rapidly. Finally, a simulation example is presented to demonstrate the validity and superiority of the proposed control strategy.

The remote control of Unmanned Aerial Vehicles (UAVs) in emergency rescues, large-scale search, e-commerce and other fields is still a hot topic. The majority of current remote human-computer interaction techniques, such as joy-sticks, monitoring interfaces, or gesture control, lack flexibility, have weak immersion, and have poor interaction. The study proposes the development of a novel system for controlling multiple UAVs using virtual reality (VR). A virtual system and a physical system make up the control system. A VR application uses a head-mounted display (HMD) to show the user a digital twin environment of a drone and a faraway location. The operators pilot the quadcopters with a set of virtual reality handles. Control data is translated directly from VR to the real UAV in realtime. The experimental results showed a stable and convenient method of manipulation by the VR scene. With the support of the proposed system, ultra-remote control is possible, and immersive maneuvering makes controlling multiple drones easier.

Available parking slot detection is the first step for autonomous parking systems. In this paper, we propose a novel parking slot detection method that uses the center information regression and the occupancy classification of the parking slot. We design a self-calibrated convolutions network (SCCN) to obtain the position, length, occupancy and direction, which can also infer the parking slot type according to the prediction results. The method divides an around view monitor (AVM) image into the 16 × 16 grid cells and performs a SCCN detector for feature extraction. Subsequently, the whole parking slot can be easily inferred via prior geometric information and detection results. We adopt the heatmap, MultiBins, and midline to detect the center keypoint, direction and occupancy, respectively. And we quantitatively evaluate the performance of the proposed method on the public PS2.0 datasets. The experimental results show the outperformance by a precision rate of 99.35%, a recall rate of 99.17%, an occupancy classification accuracy of 99.12% and all correctly inferred types of parking slots on the datasets.

Gesture recognition is an essential part in the field of human–computer interaction (HCI) and Internet of Things system. Compared with the existing technologies based on wearable sensors and dedicated devices, approaches using WiFi channel state information (CSI) signals are more desirable for passive and fine-grained gesture recognition. However, the existing CSI-based gesture recognition systems usually suffer from high model complexity and low accuracy caused by environmental dynamics. To address these issues, we propose a robust gesture recognition system (WiHGR) in this article. The WiHGR starts with a sparse recovery method to find the dominant paths from the multipath effect introduced by the orthogonal frequency division multiplexing (OFDM) technology, i.e., the main propagation paths disturbed by a human gesture. Then, the phase difference matrix is constructed according to the phase differences between two adjacent receiving antennas from the dominant paths. We propose a modified attention-based bi-directional gate recurrent unit (ABGRU) network to learn and extract discriminative features automatically from the phase difference matrix. The proposed attention mechanism assigns higher weights to the more important features, thus achieving a better recognition performance. The experimental results show that the WiHGR not only has a high accuracy for gesture recognition in the training environment, but also has a remarkable performance in new environment settings without retraining.

The problem of secure finite-horizon consensus control for discrete time-varying multiagent systems (MASs) with actuator saturation and cyber attacks is addressed in this article. A random attack model is first proposed to account for randomly occurring false data injection attacks and denial-of-service attacks, whose dynamics are governed by the random Markov process. The hybrid secure control scheme is developed to mitigate the influence of arbitrary cyber attacks on system performance. Specifically, this article proposes a hybrid control law containing multiple controllers, each of which is designed to counter different types of cyber attacks. By using the stochastic analysis approach, two sufficient criteria are provided to guarantee that the time-varying MASs satisfy the finite horizon$H_{\infty }$consensus performance. Then, the controller parameters are obtained by solving the recursive linear matrix inequality. The usefulness of the theoretic results presented is demonstrated via a numerical example that contains a performance comparison of different secure control schemes.

Fingerprinting based indoor positioning system is gaining more research interest under the umbrella of location-based services. However, existing works have certain limitations in addressing issues such as noisy measurements, high computational complexity, and poor generalization ability. In this work, a random vector functional link network based approach is introduced to address these issues. In the proposed system, a subset of informative features from many randomized noisy features is selected to both reduce the computational complexity and boost the generalization ability. Moreover, the feature selector and predictor are jointly learned iteratively in a single framework based on an augmented Lagrangian method. The proposed system is appealing as it can be naturally fit into parallel or distributed computing environment. Extensive real-world indoor localization experiments are conducted on users with smartphone devices and results demonstrate the superiority of the proposed method over the existing approaches.

In this paper, we will introduce our newly developed 3D simulation system for miniature unmanned aerial vehicles (UAVs) navigation and control in GPS-denied environments. As we know, simulation technologies can verify the algorithms and identify potential problems before the actual flight test and to make the physical implementation smoothly and successfully. To enhance the capability of state-of-the-art of research-oriented UAV simulation system, we develop a 3D simulator based on robot operation system (ROS) and a game engine, Unity3D. Unity3D has powerful graphics and can support high-fidelity 3D environments and sensor modeling which is important when we simulate sensing technologies in cluttered and harsh environments. On the other hand, ROS can provide clear software structure and simultaneous operation between hardware devices for actual UAVs. By developing data transmitting interface and necessary sensor modeling techniques, we have successfully glued ROS and Unity together. The integrated simulator can handle real-time multi-UAV navigation and control algorithms, including online processing of a large number of sensor data.

This letter is concerned with source localization based on time-difference-of-arrival (TDOA) measurements from spatially separated sensors in a wireless sensor network (WSN). Most of the existing works adopt a centralized sensor pairing strategy, where one sensor node is chosen as the common reference. However, due to the bandwidth and power constraints of multihop WSNs, it is well known that this kind of centralized methods is energy consuming due to the need of single and multihop transmissions of raw measurement data. In this letter, we propose a decentralized in-network sensor pairing method to acquire TDOA measurements for source localization. It is proved that the proposed decentralized in-network sensor pairing method can result in the same Cramer-Rao-Bound (CRB) as the centralized one at a far less communication cost.

Source localization is an important application of wireless sensor networks (WSNs). Many types of sensors can be used for source localization, e.g., range sensors, bearing sensors and time-difference-of-arrival (TDOA) based sensors, etc. It is well known that relative sensor-source geometry can significantly affect the performance of any particular localization algorithm. Existing works in the literature mainly deal with geometry analysis for homogeneous sensors. However, in real applications, different types of sensors may be utilized for source localization. Hence, in this paper, we consider the optimal sensor placement problem in heterogeneous sensor networks (HSNs), where two types of sensors are deployed for source localization. Relative optimal sensor-source configurations with the minimum number of sensors for source localization are identified under the Doptimality criterion with potential extensions to the general case. Explicit characterizations of optimal sensor-source geometries are given for hybrid range and bearing sensors, hybrid bearing and TDOA based sensors as well as co-located hybrid range and bearing sensors, respectively. The results of this work can be applied to the sensor path planning problem for optimal source localization.

Source localization is an important application of wireless sensor networks (WSNs). Many types of sensors can be used for source localization, e.g. range-only sensors, bearing-only sensors and time-of-arrival (TOA) sensors, etc. It is well known that the relative sensor-source geometry can significantly affect the performance of any particular localization algorithm. Existing works in the literature mainly deal with the geometry analysis for a single type of sensors. However, in real applications, different types of sensors may be utilized for source localization simultaneously. Hence, in this paper, we consider the optimal sensor placement problem in heterogeneous sensor networks, where two types of sensors are deployed for source localization. Relative optimal sensor-source configurations with the minimum number of sensors for source localization, are identified under the D-optimality criterion with potential extensions to a general case. Explicit characterizations of optimal sensor-source geometries are given for hybrid range-only and bearing-only sensors as well as hybrid bearing-only and TOA sensors, respectively.

Acoustic source localization based on time difference of arrival (TDOA) measurements from spatially separated sensors is an important problem in wireless sensor networks (WSNs). While extensive research works have been performed on algorithm development, limited attention has been paid in how to form the sensor pairs. In the literature, most of the works adopt a centralized sensor pairing strategy, where only one common sensor node is chosen as the reference. However, due to the multi-hop nature of WSNs, it is well known that this kind of centralized signal processing method is power consuming since raw measurement data is involved in the transmissions. To reduce the requirements for both network bandwidth and power consumptions, we propose an in-network sensor pairing method to collect the TDOA measurements while guaranteeing the quality of source localization. The solution involves finding a minimal sized dominating set (MSDS) for a graph of the muti-hop network. It has been proved that in-network sensor pairing can result in the same Cramer-Rao-Bound (CRB) as the centralized one but at a far more less communication cost. Furthermore, the structure of the proposed in-network sensor pairing coincides with the decentralized source localization, which is an important application of our method.

Indoor positioning has emerged as a widely used application of Wi-Fi wireless networks. Fingerprinting techniques can provide a low-cost and high-accuracy localization solution by utilizing in-building communication infrastructures. However, existing fingerprinting localization algorithms are not resistant to outliers, for example, the accidental environment changes, access point (AP) attacks. Another drawback is that traditional K nearest neighbor (KNN) algorithm in the literature may not select the candidate reference points (RPs) correctly. In this paper, we propose a novel environmentally robust and attack resistant probabilistic fingerprinting localization method. In the offline phase, the distribution estimation of the signal strength is performed using probabilistic histogram method. Then in the online phase, a three-step location sensing method is proposed. In the first step, a simple and efficient outlier detection method named non-iterative “RANdom SAmple Consensus” (RANSAC) is run to detect and eliminate part of APs from which the signals measured are severely distorted by unexpected environment effects. In the second step, a novel region-based RP selection method which works like a “family of probability” is proposed to improve the possibility of the correctness of selection of the nearest RPs. In the final step, the location is obtained using a weighted-mean method. In the experiment section, we demonstrate the proposed method in our lab and find that the proposed strategies are resistant to outliers and can improve the localization accuracy effectively compared with existing methods.

Multi-source localization is an open and challenging research problem in the energy-based wireless sensor network (WSN) of acoustic sensors. Classic maximum likelihood (ML) algorithm can not work well due to the high computation demand. An expectation maximization (EM) algorithm was proposed in our previous paper to approximate the optimal solution with lower computational complexity. However that algorithm is centralized in nature in which all the observed data from each sensor node must be sent to the fusion centre. It has several drawbacks including the relying on the centre which may be damaged or shut down, poor scalability with the increasing of network size, and the high communication overhead requirement when a sensor is far away from the centre. In this paper we propose a distributed EM algorithm for multi-source localization in energy-based WSN. It can achieve satisfactory localization accuracy with significantly low communication and computation cost.