Multi-view clustering (MVC), as an important machine learning task, aims to group data into distinct groups by leveraging complementary and consistent information across multiple views. During the last two decades, it has been widely studied, and many methods have been proposed, which has brought incredible development to this field. However, few works comprehensively summarize existing methods and point out the potential challenges in this field for the next decades. To this end, our survey thoroughly reviews existing MVC methods according to three taxonomies, i.e., techniques, fusion strategies, and scenarios. Specifically, seven typical techniques, four fusion strategies, and five typical scenarios are included. Besides, we also collect the commonly used datasets and analyze the performance of typical MVC methods. Moreover, we summarize six application scenarios of existing MVC methods ranging from computer vision, and information retrieval tasks to medical diagnosis and bio-informatics. In particular, we point out seven interesting future directions in this field, which will definitely enlighten the readers.

The Artificial Internet of Things (AIoT) is growing into a new frontier field with broad development prospects, which essence is the collaborative enhancement of networked heterogeneous agent swarms. The market-based approach is an effective way for the cooperative scheduling of agent swarm, where networked agents need to distributedly select and arrange tasks meeting the spatio-temporal constraints. This paper proposes a new asynchronous consensus method aimed at substantially mitigating the communication traffic and decreasing the message transmission requirements associated with the market-based approach, ultimately leading to a reduction in scheduling time. Firstly, the method innovatively introduces timestamps of agent information updates, which are more informative, thereby reducing inter-agent communication volume to$ n/m$of that in the original protocol (where$ n$represents the number of agents and$ m$denotes the number of tasks, with$ m\gt n$). Secondly, agent-centric asynchronous consensus protocols are designed based on the new timestamps, which can resolve inter-agent task conflicts more rapidly and efficiently. Additionally, a mechanism for avoiding message flooding is proposed to prevent endless broadcasts caused by communication issues such as packet loss, link disruptions, and node withdrawals. Finally, through a self-developed ad-hoc network simulation system, the swarm scheduling under real networking conditions is simulated. The validation results demonstrate that the algorithm can significantly reduce communication traffic and scheduling time.

For formation control systems based on wireless communications, the communication interactions and control performance are highly coupled, while traditional methods do not take this coupling into account. To fill this gap, we study the formation control problem of second-order multiagent systems (MASs) with uncertain dynamics (affected by unknown but bounded (UBB) process noises) and commonly used time division multiple access (TDMA) communications. First, we establish the communication topology among agents as a periodically switching topology governed by precise switching mechanisms, which characterizes the effects of the TDMA mechanism, agent dynamics, and the physical layer of communications. Based on the communication model, we propose a control-communication codesign for MASs, where the delay-based formation controller and the distributed transmit power control algorithm are developed, to guarantee the bounded formation stability of control systems and reliable connections of the desired communication links simultaneously. The codesign framework systematically integrates formation control and communication transmission under physical layer constraints and provides a paradigm to better characterize the coupling relationship between communication interactions and control performance. Finally, experiments using realistic communication characteristics are conducted to validate the effectiveness of our codesign method.

To enhance the autonomous maneuverability of aircraft, it is urgent to develop high angle-of-attack (AOA) maneuvering flight methods suitable for fixed-wing autonomous aerial vehicles (AAVs). Addressing the issue that most existing methods neglect the nonlinearity of the flow field under high AOA conditions, this article considers the hysteresis loop phenomenon that represents the unsteady aerodynamics due to stall. Inspired by the correlation between aerodynamic coefficients and the change rate of the AOA, a time-varying aerodynamic model is established. It utilizes time-varying parameter equations to describe the aerodynamic coefficients and combines them with the fixed-wing aircraft’s longitudinal dynamics model. To address the uncertainties arising from the established model, a Lyapunov-based adaptive maneuvering controller is developed for the nonlinear time-varying system. With the prior knowledge that aerodynamic coefficients are bounded, a projection operator based on convex set theory is designed to achieve real-time bounded estimation of the unknown time-varying parameters. Additionally, the designed switching cascaded control strategy enables the aircraft to restore steady flight autonomously. The comparing simulations under parameter perturbation demonstrate that the proposed controller can effectively enhance the AAV’s tracking performance for high AOA maneuver commands.

This paper addresses the problem of formation control for a quadrotor swarm (QS) system with directed graph topology under external environmental disturbances and unreliable internal state acquisition. The proposed distributed robust control framework, based on a gemetric controller, incorporates${\mathcal {L}}_{1}$adaptive controllers and differentiator systems. First, the geometric formation controller is designed to implement the formation control of the nominal system. Then,${\mathcal {L}}_{1}$adaptive controllers are designed separately for each quadrotor’s position loop and attitude loop subsystems to address the effects of uncertainties such as external time-varying disturbances (matched and unmatched disturbances) and different mass variations of quadrotors. Furthermore, the differentiator system is devised to accurately estimate the higher-order derivatives of the non-directly-measurable velocity information and the virtual translation control signal, which enhances system accuracy while reducing computational complexity. The Lyapunov stability theory is employed to analyze the stability of the closed-loop system. Finally, the effectiveness and exceptional performance of this approach in QS formation control were validated through numerical simulation and experimental results. Note to Practitioners—The inspiration for this article comes from the issue of formation control in a cluster of quadrotor drones, which is also applicable to formation control in other types of drones. In this paper, a formation control algorithm based on${\mathcal {L}}_{1}$adaptive control strategy and arbitrary-order differentiation is designed. This algorithm can address not only the issue of time-varying wind disturbances frequently encountered during quadrotor drone flights but also the effects of unpredictable velocities and inconsistent masses of quadrotor drones. The disturbance rejection capability of this scheme enables quadrotor drones to be applied more safely and reliably in complex environments for search and rescue missions and surveillance tasks. Eliminating the need for linear velocity measurements reduces sensor costs and enhances system reliability and stability. The proposed formation control scheme allows the QS system to have different masses for each UAV, which can be applied to tasks such as collaboration logistics transportation, material delivery and crop spraying. Preliminary physical experiments have validated the feasibility of the proposed scheme, although it has not been applied in practical scenarios yet. In future research, we intend to equip each drone in the QS system with objects of different masses to achieve collaboration material transportation and delivery in complex environments.

This paper investigates a two-layer distributed control protocol for multiple unmanned aerial vehicles (UAVs) to fence a moving target cooperatively, using relative measurements. The multi-UAVs are divided into two layers: one is equipped with target detection sensors that can acquire relative bearing information; the other is equipped with relative distance sensors that can only acquire relative positions of neighbors. First, a bearing-based controller is presented for the leader layer to eliminate the singularity problem of observability of a moving target. Then, a distance-based controller is developed to fence the moving target within a convex hull at every moment for the follower layer. The relative spacing within the formation does not need to be given in advance, and the rotation and scaling of the formation can be quickly adjusted according to the design parameters. Third, we prove sufficient conditions for the design of the formation configuration, together with the selection of the fencing scale. The fencing protocol can be directly extended to 3-D space, and the form of the controller for 3-D scenarios is given as well. Finally, two numerical simulations and a hardware-in-loop (HIL) experiment verify the effectiveness of the proposed protocol. Note to Practitioners—This paper was motivated by the problem of cooperative moving target fencing control for multiple fixed-wing UAVs. In many practical missions, for instance, multiple UAVs protect a critical target or entrap an intruder target, it is typical that multiple fixed-wing UAVs encircle a moving target. Additionally, it may occur with communication limitations and the absence of global information in some complex environments, and the moving target may be non-cooperative. This would lead to existing fencing methods failing to be applied, which require communication to share information about the target and UAVs. A two-layer control frame is presented to address this problem. We use onboard sensors (target detection sensors for the leader layer and relative distance sensors for the follower layer) to obtain relative measurements of the moving target and other UAVs, removing communication and global information constraints. Then, a scale factor is introduced to make the proposed protocol widely applicable in narrow areas or places with obstructed views, driving the formation translating, rotating, and scaling with the movement of the target. The proposed protocol guarantees that the moving target is encircled by the convex hull formed by multiple UAVs, and it can be extended to 3-D space directly. In future research, we will perform the proposed protocol in practice.

Flocking with multiple unmanned aerial vehicles (UAVs) offers significant potential for diverse applications due to its enhanced maneuverability, improved efficiency, and increased robustness. Collision avoidance is a critical and challenging issue for distributed flocking control with a UAV fleet, especially in dynamic environments with varying numbers of non-cooperative intruders. However, existing reinforcement learning based methods mainly focus on flocking with collision avoidance tasks with static obstacles and a fixed number of UAVs. In this article, we propose a scalable multi-agent reinforcement learning based method to solve the distributed flocking with collision avoidance problem for a scalable fleet of fixed-wing UAVs in dynamic environments. Specifically, we cast this problem in a decentralized partially observable Markov decision process framework and propose a scalable multi-agent reinforcement learning algorithm called spatial-temporal attention multi-agent actor-critic (STAAC). In this algorithm, we design a spatial-temporal attention based population-invariant network architecture to facilitate the representation learning of dynamic dimensional observations. By integrating the local spatial attention and global temporal attention mechanisms, STAAC is able to adapt to the changes in the scale of UAV fleets and the number of intruders. Finally, we empirically demonstrate the effectiveness, scalability, and adaptability of the proposed approach in numerical simulations and hardware-in-the-loop experiments.

Distributed model predictive control (DMPC) is promising in achieving optimal cooperative control in multirobot systems (MRS). However, real-time DMPC implementation relies on numerical optimization tools to periodically calculate local control sequences online. This process is computationally demanding and lacks scalability for large-scale, nonlinear MRS. This article proposes a novel distributed learning-based predictive control framework for scalable multirobot control. Unlike conventional DMPC methods that calculate open-loop control sequences, our approach centers around a computationally fast and efficient distributed policy learning algorithm that generates explicit closed-loop DMPC policies for MRS without using numerical solvers. The policy learning is executed incrementally and forward in time in each prediction interval through an online distributed actor–critic implementation. The control policies are successively updated in a receding-horizon manner, enabling fast and efficient policy learning with the closed-loop stability guarantee. The learned control policies could be deployed online to MRS with varying robot scales, enhancing scalability and transferability for large-scale MRS. Furthermore, we extend our methodology to address the multirobot safe learning challenge through a force field-inspired policy learning approach. We validate our approach's effectiveness, scalability, and efficiency through extensive experiments on cooperative tasks of large-scale wheeled robots and multirotor drones. Our results demonstrate the rapid learning and deployment of DMPC policies for MRS with scales up to 10 000 units.

Multiagent scheduling has recently been reinvigorated by the burgeoning application of swarm, receiving significant attention due to its new characteristics. The market-based method is a fast distributed scheduling method that is naturally suitable for agent swarm, while its multiround communication is inevitably affected by the environment and the performance deteriorates. This article proposes an idea of computing-for-communication (CFC) with improving or even appropriately increasing computation to reduce communication rounds and improve the performance meanwhile, which does not add additional communication protocols and traffic but may moderately increase the amount of computation and storage. First, a new scoring function and a local optimization method are proposed to improve the agent’s schedule and resolve the conflict among agents in advance. Second, an agent location inference method and task-related agent selection strategy are presented for local optimization, which is expected to avoid the increase of communication in locations and the waste of computation on irrelevant agents. Third, some modifications for removing and adding tasks are proposed to further improve the performance of scheduling. Finally, extensive Monte Carlo experiments demonstrate the commendable performance of the proposed method in comparison with the representative consensus-based bundle algorithm (CBBA) and performance impact algorithm (PI).

This article provides a solution to time-varying formation (TVF) tracking control problems of nonholonomic mobile robots (NMRs) with asymmetric input constraints. Different from existing works, the configuration of the formation for NMRs is time-varying, which requires formation tracking errors to keep convergent even if the configuration of the desired formation changes over time. A novel sliding mode controller is proposed to handle this problem, and the closed-loop stabilities of NMRs under given control protocols are proven by Lyapunov theory. As special cases of TVF, the above control methods can be directly applied to flexible formation and fixed formation studied in existing works. It should be pointed out that if the desired formation is fixed, the angular velocity of the tracking target is not necessary when designing the corresponding control algorithm. In addition, there is no singularity in the methods provided in this article. By collaborative selection of parameters in these control protocols, the adjustment ranges of linear and angular velocities associated with the leader or virtual leader are almost the same as that of followers. Numerical simulations and hardware-in-the-loop (HiL) simulations further verify the theoretical results.

This article proposes a prescribed-time distributed convex polygon entrapping control protocol based on relative measurements for leader-follower-constructed autonomous aerial vehicles (AAVs). A group of moving targets is considered as the entrapped target, whose dynamics are not predetermined in advance. First, a convex polygon formation is constructed to determine impact points of leaders through optimization, and the followers’ desired positions are derived from the relative positions of their neighbors. Then, a prescribed-time distributed entrapping controller is rigorously deduced, which can be applied to large-scale AAV swarms and guarantee the convergence of the system within a prescribed time set in advance. Finally, numerical simulations are performed for two targets with different dynamics to verify the effectiveness of the proposed method, which is capable of realizing the prescribed-time convex polygon entrapping.

Ground target tracking constitutes a crucial functionality for Unmanned Aerial Vehicles (UAVs), serving as the foundational element for missions including reconnaissance, search and rescue operations. This paper proposes a rapid and adaptive approach for fixed-wing UAVs to track a ground target by utilizing image-based visual servoing (IBVS). It is noted that a monocular camera is fixed on the UAV to observe the target. Initially, the feedback linearization coupled with the least squares method is employed to obtain the optimal control for the nonlinear underactuated system of the UAV. Subsequently, a "regulatory factor" is devised for the image Jacobian matrix to streamline the convergence of target position on the image and thereby expediting the approaching of the UAV to the target. Considering the necessity of target depth information in the image Jacobian matrix, an innovative strategy is conceived for the online, adaptive estimation of the depth. Simulation results validate the effectiveness of the proposed method.

This paper explores the optimal containment control problem for nonlinear and underactuated quadrotors with multiple team leaders governed by nonlinear dynamics, employing the reinforcement learning. A cascade controller is formulated, comprising a position control component to ensure containment achievement and an attitude control component to govern rotational channel. The proposed optimal control protocols derived from historical data collected from quadrotor systems without requirement for exact knowledge of vehicle dynamics. The simulation illustrates the effectiveness of the proposed controller in managing a quadrotor team with multiple leaders.

Fixed-wing unmanned aerial vehicles (UAVs) are highly mobile and play a crucial role in low-altitude remote sensing. Cooperative tracking of these UAVs is expected to significantly improve detection, tracking, and defense capabilities over large areas. In this study, we propose a new consensus protocol for multi-UAVs using nonlinear mapping. This protocol allows for advanced regulation of settling time and limits the trajectory within a desired performance range. Compared with the existing methods, the proposed controller exhibits a more moderate magnitude near the prescribed time. We validate the effectiveness of our approach through numerical simulations and hardware-in-loop experiments. For second-order multiagent systems (MASs), the proposed method has a more than 70% improvement in the convergence rate. The maximum control magnitude to converge high-order MASs reduces by 90% compared to existing methods.

Multiple unmanned aerial vehicles (UAVs) are able to efficiently accomplish a variety of tasks in complex scenarios. However, developing a collision-avoiding flocking policy for multiple fixed-wing UAVs is still challenging, especially in obstacle-cluttered environments. In this article, we propose a novel curriculum-based multiagent deep reinforcement learning (MADRL) approach called task-specific curriculum-based MADRL (TSCAL) to learn the decentralized flocking with obstacle avoidance policy for multiple fixed-wing UAVs. The core idea is to decompose the collision-avoiding flocking task into multiple subtasks and progressively increase the number of subtasks to be solved in a staged manner. Meanwhile, TSCAL iteratively alternates between the procedures of online learning and offline transfer. For online learning, we propose a hierarchical recurrent attention multiagent actor-critic (HRAMA) algorithm to learn the policies for the corresponding subtask(s) in each learning stage. For offline transfer, we develop two transfer mechanisms, i.e., model reload and buffer reuse, to transfer knowledge between two neighboring stages. A series of numerical simulations demonstrate the significant advantages of TSCAL in terms of policy optimality, sample efficiency, and learning stability. Finally, the high-fidelity hardware-in-the-loop (HITL) simulation is conducted to verify the adaptability of TSCAL. A video about the numerical and HITL simulations is available at https://youtu.be/R9yLJNYRIqY.

In this article, the problem of the fixed-wing UAV formation control in local frames is investigated, and a formation controller based on the distance constraints is designed. Without using the global position information, this article considers the GPS-denied environment, and the control of UAVs only depends on the relative range and relative angle information defined in local frames. Meanwhile, to simultaneously address the optimization and external disturbance issues of the system, an ADP-ISMC formation controller is designed in this article. Finally, the simulations are presented to illustrate the effectiveness of the proposed control method.

In this paper, predefined-time tracking control of fixed-wing unmanned aerial vehicles (UAV) subject to external disturbance and unmodeled dynamics is studied. First, the nonlinear dynamics of the UAV are converted to the second-order system through feedback linearization. Then, a fixed-time observer is addressed to estimate the disturbance and uncertainty. Finally, a novel predefined-time controller is designed to drive the tracking error to zero within a predefined time. Numerical simulation and comparison demonstrate that the proposed algorithm has a faster convergence rate, and the control input is smoother near the settling time.

In this paper, aimed at improving the cooperative target tracking performance, the optimal cooperative circumnavigation control of multiple robots is studied. To solve the curse of dimensionality in the training process of the optimal cooperative control policy, this paper employs the idea of “Mean Field” and designs a fully distributed optimization algorithm based on the robust optimal control method, which greatly reduces the algorithm complexity and training time. The stability of the system under the designed control policy is analyzed rigorously and the theoretical results are validated by a numerical simulation.

Highly accurate and efficient map in unknown and complex environments is essential for robotics navigation. Traditionally, mobile robot platforms are often computationally constrained when using multiple sensors to process large amounts of input data. In previous works, some of them have been deployed to embedded platforms in real-time. However, how to balance accuracy and efficiency while reducing the computational resources and the memory footprint is still the bottleneck. Motivated by these challenges, we proposed a mapping framework called VDBblox to incrementally build Euclidean Signed Distance Fields (ESDFs) map from Truncated Signed Distance Fields (TSDFs) mapping. We use a novel weight function to update the non-projective TSDFs, thus improving the quality of the mesh reconstruction with higher accuracy than up-to-date methods. Meanwhile, the generated ESDFs map is maintained by the least recently used (LRU) cache to dynamically handle the obstacle changes with less runtime than state-of-the-art. We show VDBblox performance in terms of accuracy and efficiency by benchmark comparison on RGB-D and LiDAR public datasets. Moreover, we demonstrate that VDBblox can be integrated into a completed quadrotor system as a sub-module. Then we validate it through online obstacle avoidance and high-quality mesh reconstruction in real-world experiments. Finally, we release our method as open-source code to the community11Code - https://github.com/yinloonga/vdbblox.

Abstract As the scale of the system expands, processor failures are inevitable. Fault diagnosis has great significance in analyzing the reliability of multiprocessing systems. Probabilistic fault diagnosis is a method that attempts to diagnose nodes correctly with high probability. In this paper, we extend the threshold $t \leq 2$ to threshold $t=3$ for regular networks based on probabilistic diagnosis algorithm and determine the status of a cluster of nodes by analyzing the local performance. Moreover, we evaluate the global performance based on the Poisson distribution and the Binomial distribution and show that the achievement in terms of correctness demonstrates a good performance. Finally, we employ the probabilistic diagnosis scheme to explore some well-known networks, including complete cubic networks, dual cubes and hierarchical hypercubes as well.

In this article, a novel design scheme is introduced to solve the optimal control problem for nonlinear systems with unsymmetrical and state-dependent input constraints. By introducing an initial stabilizing control policy as the baseline of the constructed optimal control policy, we remove the assumption in the current study for the adaptive optimal control, that is, the internal dynamics should hold zero when the state of the system is in the origin. Particularly, nonlinear control systems with partially unknown dynamics are investigated and the procedure to acquire the corresponding optimal control policy is presented. The stability for the closed-loop dynamics and the optimality of the obtained control policy are both proved. Besides, we apply the proposed control design framework to solve the optimal circumnavigation problem based on the accumulative Fisher information for a fixed-wing unmanned aerial vehicle (UAV). The control performance of our algorithm is compared with that of the existing circumnavigation control policy in a numerical simulation.

The affine formation tracking problem for fixed-wing unmanned aerial vehicles (UAVs) is considered in this paper, where fixed-wing UAVs are modeled as unicycle-type agents with asymmetrical speed constraints. A group of UAVs are required to generate and track a time-varying target formation obtained by affinely transforming a nominal formation. To handle this problem, a distributed control law based on stress matrix is proposed under the leader-follower control scheme. It is proved, theoretically, that followers can converge to the desired positions and achieve affine transformations while tracking diverse trajectories. Furthermore, a saturated control strategy is proposed to meet the speed constraints of fixed-wing UAVs, and numerical simulations are executed to verify the effectiveness of our proposed affine formation tracking control strategy in improving maneuverability

In our paper[1], the last inequality of[1, eq. (20)]is not correct, which affects the proof of the converge of$z_{I}$. In the following, we will give a corrected proof.

This article investigates the problem of coordinated path following for fixed-wing unmanned aerial vehicles (UAVs) with speed constraints in the two-dimensional plane. The objective is to steer a fleet of UAVs along the path(s) while achieving the desired sequenced inter-UAV arc distance. In contrast to the previous coordinated path-following studies, we are able through our proposed hybrid control law to deal with the forward speed and the angular speed constraints of fixed-wing UAVs. More specifically, the hybrid control law makes all the UAVs work at two different levels: 1) those UAVs whose path-following errors are within an invariant set (i.e., the designed coordination set) work at the coordination level and 2) the other UAVs work at the single-agent level. At the coordination level, we prove that even with speed constraints, the proposed control law can make sure the path-following errors reduce to zero, while the inter-UAV arc distances converge to the desired value. At the single-agent level, analysis for the path-following error entering the coordination set is provided. We develop a hardware-in-the-loop simulation testbed of the multi-UAV system by using actual autopilots and the X-Plane simulator. The effectiveness of the proposed approach is corroborated with both numerical simulation and the testbed.

In this article, a multilayered and distributed architecture for mission-oriented miniature fixed-wing UAV swarms is presented. Based on the concept of modularity, the proposed architecture divides the overall system into five layers: 1) low-level control layer; 2) high-level control layer; 3) coordination layer; 4) communication layer; and 5) human interaction layer, and many modules that can be viewed as black boxes with interfaces of inputs and outputs. In this way, not only the complexity of developing a large system can be reduced but also the versatility of supporting diversified missions can be ensured. Furthermore, the proposed architecture is fully distributed that each UAV performs the decision-making procedure autonomously so as to achieve better scalability. Moreover, different kinds of aerial platforms can be feasibly extended by using the control allocation matrices and the integrated hardware box. A prototype swarm system based on the proposed architecture is built and the proposed architecture is evaluated through field experiments with a scale of 21 fixed-wing UAVs. Particularly, to the best of our knowledge, this article is the first work which successfully demonstrates formation flight, target recognition, and tracking missions within an integrated architecture for fixed-wing UAV swarms through field experiments.

Feature extraction and feature selection have been regarded as two independent dimensionality reduction methods in most of the existing literature. In this paper, we propose to integrate both approaches into a unified framework and design an unsupervised linear feature selective projection (FSP) for feature extraction with low-rank embedding and dual Laplacian regularization, with the aim to exploit the intrinsic relationship among data and suppress the impact of noise. Specifically, a projection matrix with an l2,1-norm regularization is introduced to project original high dimensional data points into a new subspace with lower dimension, where the l2,1-norm regularization can endow the projection with good interpretability. We deploy a coefficient matrix with low rank constraint to reconstruct the data points and the l2,1-norm is imposed to regularize the data reconstruction errors in the low-dimensional subspace and make FSP robust to noise. Furthermore, a dual graph Laplacian regularization term is imposed on the low dimensional data and data reconstruction matrix for preserving the local manifold geometrical structure of data. Finally, an alternatively iterative algorithm is carefully designed for solving the proposed optimization model. Theoretical convergence and computational complexity analysis of the algorithm are also provided. Comprehensive experiments on various benchmark datasets have been carried out to evaluate the performance of the proposed FSP. As indicated, our algorithm significantly outperforms other state-of-the-art methods for feature extraction.

This paper is concerned with general coopetition networks with signed graphs, based on which both the bipartite consensus and tracking control problems for networked systems subject to nonidentical matching uncertainties are studied. For the case of undirected and connected communication graphs, we propose a distributed discontinuous nonlinear controller which can achieve the bipartite consensus. To cancel the chattering phenomenon of the discontinuous controller, a continuous one is designed by using the boundary layer technique, under which the bipartite consensus error is shown to be uniformly ultimately bounded and can exponentially converge to a small adjustable bounded set. Further, considering the case of a leader having a bounded control action, we present a continuous controller to guarantee the ultimate boundedness of the bipartite tracking error.

In this paper, a curved path following scheme with the aid of the vector field (VF) and the notion of input-to-state stable (ISS) for a fixed-wing unmanned aerial vehicle (UAV) is developed. The VF strategy is a robust and valid guidance method and its stability is proved using ISS properties. Many existing path following algorithms for fixed-wing UAVs are only proposed for straight-lines and orbits. However, the path required to be followed is always in approximate curves rather than straight-lines and orbits in many high-level missions, such as obstacle avoidance, search, and surveillance. The nonlinear-theoretic notion of ISS is playing a central role in the control law design and stability analysis. The error kinematics are converted into two interconnected subsystems with proven ISS properties, which yield the overall system that is globally asymptotically stable, i.e., and the along-track error and the cross-track error asymptotically approach zeros from any initial position in the space. The followed path is defined in terms of the arc-length parameter, and it can be expanded according to the waypoint fitting without the need to obtain a global function representation. The singularity of multiple closest points on the path is eliminated by constructing a speed profile of a virtual point on the path. The scheme is validated with a semi-physical experiment combined by an actual autopilot, ground station and the X-Plane flight simulator. Flight tests using a small fixed-wing UAV show excellent tracking performance of the curved path following.

This paper investigates the distributed event-based consensus problem of switching networks satisfying the jointly connected condition. Both the state consensus of homogeneous linear networks and the output consensus of heterogeneous networks are studied. Two kinds of event-based protocols based on local sampled information are designed, without the need to solve any matrix equation or inequality. Theoretical analysis indicates that the proposed event-based protocols guarantee the achievement of consensus and the exclusion of Zeno behaviors for jointly connected undirected switching graphs. These protocols, relying on no global knowledge of the network topology and independent of switching rules, can be devised and utilized in a completely distributed manner. They are able to avoid continuous information exchanges for either controllers' updating or triggering functions' monitoring, which ensures the feasibility of the presented protocols.

An end-to-end deep learning (DL) control model is proposed to solve autonomous landing problem of the quadrotor in way of supervised learning. Traditional methods mainly focus on getting the relative position of the quadrotor through GPS signal which is not always reliable or position-based vision servo (PBVS) methods. In this paper, we have constructed a deep neural network based on convolutional neural network(CNN) whose input is raw image. A monocular camera is used as only sensor to capture down-looking image which contains landing area. To train our deep neural network, we have used our self-built image dataset. After training phase, the well-trained control model is tested and the results perform well. Light changes and background interferences have little influence on the model`s performance, which shows the robustness and adaptation of our deep learning model.

This paper presents a novel method-continuous-time Markov decision process (CTMDP)-to address the uncertainties in pursuit-evasion problem. The primary difference between the CTMDP and the Markov decision process (MDP) is that the former takes into account the influence of the transition time between the states. The policy iteration method-based potential performance for solving the CTMDP and its convergence are also presented. The results obtained by MDP-based method demonstrate that it is a special case of CTMDP-based method involving the identity transition rate matrix. To compare the methods, a well-known pursuit-evasion problem, involving two identical cars, is solved as a benchmark. The CTMDP-based method can provide a discretization solution that is close to the analytical solution obtained by the differential game method. Besides, it shows strong robustness against changes in the transition probability, as compared with the traditional MDP-based method. To the best of our knowledge, this is the first attempt to validate the influence of the transition time between the states in such a pursuit-evasion scenario, or in a similar application, solved by an MDP-related model. The CTMDP-based method offers a new approach to solving the pursuit-evasion problem and can be extended to similar optimization applications.

This paper focuses on finding a dual quaternion solution to attitude and position control for multiple rigid body coordination. Representing rigid bodies in 3-D space by unit dual quaternion kinematics, a distributed control strategy, together with a specified rooted-tree structure, are proposed to control the attitude and position of networked rigid bodies simultaneously with notion concision and nonsingularity. A property called pairwise asymptotic stability of the overall system is then analyzed and validated by an example of seven quad-rotor formation in the Urban Search And Rescue Simulation (USARSim) platform. As a separate but related issue, a maximum depth condition of the rooted tree is found with respect to error accumulation along each path using dual quaternion algebra, such that a given safety bound on attitude and position errors can be satisfied.