A key problem in multiagent multitask systems is optimizing conflict-free strategies, especially when task-assignment is coupled with path-planning. Incomplete information exacerbates this complexity, leading to frequent conflicts, such as redundant agents performing the same task. Different from the existing single-type game model, this article introduces a distributed mixed cooperative-noncooperative (DMCN) model that considers nondifferentiable constraints. In order to deal with nondifferentiable task layer constraints, we use approximation operators and splitting schemes to transform the original optimization function into the primal-dual differentiable function. In order to obtain more stable solutions, a distributed approximate gradient descent optimization algorithm and conflict resolution mechanism are proposed, which enhances the convergence of our method. We use Lyapunov theory to verify the exponential convergence of the algorithm in the time range. Simulation and experiments demonstrate the superiority of this method and its applicability in engineering applications.

This paper addresses the complex challenge of ensuring simultaneous arrival of multiple agents at a dynamic target, a critical requirement for operations such as roundups and saturation attacks. Traditional guidance systems have faced significant hurdles due to inaccurate flight time estimates and difficulties adapting to high-speed maneuvers. To overcome these limitations, we introduce a novel framework that utilizes Proximal Policy Optimization (PPO) and expert rules. This approach leverages distributed computing to enable autonomous decision-making among agents, thereby simplifying the deep reinforcement learning model and reducing computational overhead, which enhances scalability and adaptability. Additionally, we incorporate an angular velocity reward into the reward function, improving the predictability and effectiveness of maneuvers, particularly for targets with high-speed and irregular trajectories. The proposed methods have been rigorously tested through numerous simulations and high-fidelity scenarios, confirming their robustness and superior performance over traditional and enhanced proportional guidance systems.

BACKGROUND: To explore the value of multiparametric MRI markers for preoperative prediction of Ki-67 expression among patients with rectal cancer. METHODS: Data from 259 patients with postoperative pathological confirmation of rectal adenocarcinoma who had received enhanced MRI and Ki-67 detection was divided into 4 cohorts: training (139 cases), internal validation (in-valid, 60 cases), and external validation (ex-valid, 60 cases) cohorts. The patients were divided into low and high Ki-67 expression groups. In the training cohort, DWI, T2WI, and contrast enhancement T1WI (CE-T1) sequence radiomics features were extracted from MRI images. Radiomics marker scores and regression coefficient were then calculated for data fitting to construct a radscore model. Subsequently, clinical features with statistical significance were selected to construct a combined model for preoperative individualized prediction of rectal cancer Ki-67 expression. The models were internally and externally validated, and the AUC of each model was calculated. Calibration and decision curves were used to evaluate the clinical practicality of nomograms. RESULTS: Three models for predicting rectal cancer Ki-67 expression were constructed. The AUC and Delong test results revealed that the combined model had better prediction performance than other models in three chohrts. A decision curve analysis revealed that the nomogram based on the combined model had relatively good clinical performance, which can be an intuitive prediction tool for clinicians. CONCLUSION: The multiparametric MRI radiomics model can provide a noninvasive and accurate auxiliary tool for preoperative evaluation of Ki-67 expression in patients with rectal cancer and can support clinical decision-making.

Flocking control has been studied extensively along with the wide applications of multivehicle systems. In this article, the distributed flocking control strategy is studied for a network of autonomous vehicles with limited communication range. The main difference from the existing methods lies in that collision avoidance is considered a necessary condition while the vehicles are driven to follow a common desired trajectory under the proximity network. The sufficient conditions for system feasibility and stability are given by the proposed strategy. First, a centralized standard model predictive control (MPC) scheme is adopted to formulate the multivehicle flocking control problem by setting collision avoidance as an optimization constraint under the proximity network. Further, an equivalent distributed MPC (DMPC) is developed based on the consensus of local controllers under the existing framework of the alternating direction method of multiplier (ADMM). However, it may require infinite time to achieve consensus for all vehicles and, thus, the local controllers resulting in a limited number of ADMM iterations may not satisfy the given constraints. The constraints for each local controller are then modified so that the collision between vehicles is avoided all of the time. The feasibility and stability of the proposed method are analyzed under practical conditions. Simulation and experimental results show that the flocking of vehicles can track the common desired trajectory stably with no collisions by the proposed method.

This article studies an efficient nonlinear model-predictive control (NMPC) scheme for trajectory tracking control of a quadrotor unmanned aerial vehicle (UAV). By augmenting the desired trajectory to a reference dynamical system, we can make the tracking task fit into the standard NMPC framework. In order to alleviate the heavy computational burden caused by solving the corresponding NMPC optimization problem online, we develop an improved continuation/generalized minimal residual ( [Formula: see text]/GMRES) algorithm. Compared with the standard C/GMRES method, the inequality constraint is relaxed by imposing the penalty term on the cost function. To guarantee the closed-loop system stability, we introduce a contraction constraint. Based on the proposed numerical algorithm and the stability constraint, we develop a novel efficient-NMPC algorithm to achieve acceptable control performance with reduced computational complexity. The numerical convergence of [Formula: see text]/GMRES solutions and the closed-loop stability of efficient-NMPC are theoretically analyzed in the presence of the input constraint. Finally, the numerical simulations, software-in-the-loop (SIL) simulations, and the real-time experiment are given to demonstrate the effectiveness of the proposed [Formula: see text]/GMRES algorithm and efficient-NMPC scheme.

With the development of sensor fusion technologies, there has been a lot of research on intelligent ground vehicles, where obstacle detection is one of the key aspects of vehicle driving. Obstacle detection is a complicated task, which involves the diversity of obstacles, sensor characteristics, and environmental conditions. While the on-road driver assistance system or autonomous driving system has been well researched, the methods developed for the structured road of city scenes may fail in an off-road environment because of its uncertainty and diversity. A single type of sensor finds it hard to satisfy the needs of obstacle detection because of the sensing limitations in range, signal features, and working conditions of detection, and this motivates researchers and engineers to develop multi–sensor fusion and system integration methodology. This survey aims at summarizing the main considerations for the onboard multi-sensor configuration of intelligent ground vehicles in the off-road environments and providing users with a guideline for selecting sensors based on their performance requirements and application environments. State-of-the-art multi-sensor fusion methods and system prototypes are reviewed and associated to the corresponding heterogeneous sensor configurations. Finally, emerging technologies and challenges are discussed for future study.

A key problem in the formation control of homogeneous multiagent systems is the collision-free convergence of the agent positions into a desired formation. It is a typical NP-hard problem by considering the problem as optimizing the assignment of multiple destinations to the same number of agents deployed in an open space. It becomes even harder if the collision avoidance is required during the motion of agents, and thus, a suboptimal but efficient solution is adequate. The traditional methods make it by accurate preplanning of the motion trajectory of each single agent, or simply letting them reach an equilibrium as a tradeoff between the collision avoidance and the desired formation. In this article, a distributed control algorithm embedded with an assignment switch scheme is proposed to guarantee that the asymptotic convergence to the desired formation is achieved with no collisions between agents. By the proposed algorithm, the agents keep moving in straight lines toward their respective destinations until they are going to collide if they do not stop, at which moment the agents will communicate their information locally to switch their destination assignments so that they will continue to move in different directions and avoid potential collisions. Distributed control rules are also defined to confine the motion space of each agent for collision avoidance. It has been rigorously proven that the positions of all agents converge to the desired formation with no collision under random initial deployment. In addition, a detailed parameter design procedure is provided for both setting and controlling of the formation. Finally, Monte Carlo simulations and actual experiments in the outdoor environment are implemented and the results verify the effectiveness of the proposed algorithm.

In this paper, a novel nonlinear filter method named linear Gaussian regression filter (LG RF) is proposed. The LG RF utilizes the Variational Bayes (VB) to indirectly approximate the posterior probability density function (PDF) for state estimation. The core of the LG RF is to use a linear Gaussian distribution with a set of compensating parameters (CPs) to characterize the likelihood probability (LP) for maximizing the lower bound. Through iteratively and alternatively achieving the state estimation and CPs identification, the estimation accuracy can be improved gradually. In addition, compared with point-based filters, there is no decomposition of the covariance matrix in the LG RF so that the inborn defect of numerical instability is avoided. The superior performance of the LGRF is demonstrated in the simulation of maneuvering target tracking.

The problem of collaborative self-localization and target tracking method under challenge environment is studied in this paper. Specifically, the scenario with general nonlinear process and sensing model as well as sparse communication is considered by combining the distributed tracking (DT) and the collaborative localization (CL) techniques. To better characterize the statistics after nonlinear transformations, the unscented transformation (UT) approach is adopted. Simulations are extensively studied to show that the proposed method have better performance on both self-localization and target tracking than the solo CL or DT method.

For the purpose of monitoring the health conditions of electrical machines, a framework is proposed to establish the methods to provide an early warning to potential machine failures in data mining terminology. The framework consists of five stages including data segmentation, feature extraction/selection, multi-classifier ensemble, decision fusion and output, which is flexible and can be adapted for any known faults. The difference lies in the implementation choices of techniques and structures (e.g. number of classifiers) in the second to forth stage as well as the input requirements. As an example, the turn-to-turn short circuit fault of induction motor is used as the known fault in studies in this work. Simulation results show the effectiveness of the proposed techniques.

To meet the challenges of the big data age, an urgent requirement from diverse manufacturing industries is to develop a systematic time-variant methodology to make good use of the condition parameters to benefit more from the monitoring point of view. With condition-based Statistical Process Control (SPC), we develop a time-variant Exponentially Weighted Moving Average-Cumulative Sum (EWMA-CUSUM) anomaly detection mechanism which can monitor real-time multi-condition parameters, as well as multi-output quality characteristics simultaneously and efficiently. This technique enables the process user to conduct the visualization in real-time, thus, affording the representation of the information from huge volume of data. In order to demonstrate the implementation for the monitoring of a real manufacturing process, the Wire Electrochemical Tuning (WECT) process is adopted as a practical application. The proposed mechanism is superior to the conventional univariate charting mechanism by 18.75% in terms of detection accuracy and it has great potential to be employed in a large area of factorial applications.

Model regression is vitally important for performance prediction and quality control in the manufacturing industry. Since manufacturing machines always suffer from random disturbances and unobservable model shift/drift due to component failure and tool wear in the daily production, online model regression techniques are required by the manufacturers to help increase productivity and reduce quality defects by tracking the system variations promptly. Though many different types of online regression methods exist in current literatures, very few of them have considered the regression of time-varying systems. This paper addresses the online model regression for time-varying manufacturing systems with random unknown model variations during production. We first extend the standard Gaussian process regression (GPR) method for time-varying systems, which provides the optimal model estimate with the minimum mean square error (MSE). Then, an iterative form of the extended method is derived which is computation efficient but maintains the optimality of estimation with the minimum MSE. However, such optimality is obtained at the cost of storage for continuously updating the covariances between the estimated model values and the measurements. This would make the storage unaffordable when an output can take infinite number of values. Due to such a limitation, a suboptimal GPR method is further proposed to make both computation and storage inexpensive, but with worse estimation performance. Finally, the effectiveness of the two proposed methods is demonstrated by simulations.

This paper addresses vision-based cooperative search for multiple mobile ground targets by a group of unmanned aerial vehicles (UAVs) with limited sensing and communication capabilities. The airborne camera on each UAV has a limited field of view and its target discriminability varies as a function of altitude. First, a general target detection probability model is built based on the physical imaging process of a camera. By dividing the whole surveillance region into cells, a probability map can be formed for each UAV indicating the probability of target existence within each cell. Then, we propose a distributed probability map updating model which includes the fusion of measurement information, information sharing among neighboring agents, information decaying and transmission due to environmental changes such as the target movement. Furthermore, we formulate the target search problem by multiple agents as a cooperative coverage control problem by optimizing the collective coverage area and the detection performance. The proposed map updating model and the cooperative control scheme are distributed, i.e., assuming that each agent only communicates with its neighbors within its communication range. Finally, the effectiveness of the proposed algorithms is illustrated by simulation.