A mathematical model to determine the optimal production lot size for a deteriorating production system under an extended product inspection policy is developed. The last-K product inspection policy is considered so that the nonconforming items can be reduced, under which the last K products in a production lot are inspected and the nonconforming items from those inspected are reworked. Consider that the products produced towards the end of a production lot are more likely to be nonconforming, is proposed an extended product inspection policy for a deteriorating production system. That is, in a production lot, product inspections are performed among the middle K1 items and after inspections, all of the last K2 products are directly reworked without inspections. Our objective here is the joint optimization of the production lot size and the corresponding extended inspection policy such that the expected total cost per unit time is minimized. Since there is no closed form expression for our optimal policy, the existence for the optimal production inspection policy and an upper bound for the optimal lot size are obtained. Furthermore, an efficient solution procedure is provided to search for the optimal policy. Finally, numerical examples are given to illustrate the proposed model and indicate that the expected total cost per unit time of our product inspection model is less than that of the last-K inspection policy.

In order to solve the problem of coherent signal subspace method (CSSM) depending on the estimated accuracy of signal subspace, a new direction of arrival (DOA) estimation method of wideband source, which is based on iterative adaptive spectral reconstruction, is proposed. Firstly, the wideband signals are divided into several narrowband signals of different frequency bins by discrete Fourier transformation (DFT). Then, the signal matched power spectrum in referenced frequency bins is computed, which can form the initial covariance matrix. Finally, the linear restrained minimum variance spectral (Capon spectral) of signals in other frequency bins are reconstructed using sequential iterative means, so the DOA can be estimated by the locations of spectral peaks. Theoretical analysis and simulation results show the proposed method based on the iterative spectral reconstruction for the covariance matrices of all sub-bands can avoid the problem of determining the signal subspace accurately with the coherent signal subspace method under the conditions of small samples and low signal to noise ratio (SNR), and it can also realize full dimensional focusing of different sub-band data, which can be applied to coherent sources and can significantly improve the accuracy of DOA estimation. 

The earth observation satellites (EOSs) scheduling problem for emergency tasks often presents many challenges. For example, the scheduling calculation should be completed in seconds, the scheduled task rate is supposed to be as high as possible, the disturbance measure of the scheme should be as low as possible, which may lead to the loss of important observation opportunities and data transmission delays. Existing scheduling algorithms are not designed for these requirements. Consequently, we propose a rolling horizon strategy (RHS) based on event triggering as well as a heuristic algorithm based on direct insertion, shifting, backtracking, deletion, and reinsertion (ISBDR). In the RHS, the driven scheduling mode based on the emergency task arrival and control station time window events are designed to transform the long-term, large-scale problem into a short-term, small-scale problem, which can improve the schedulability of the original scheduling scheme and emergency response sensiti-vity. In the ISBDR algorithm, the shifting rule with breadth search capability and backtracking rule with depth search capability are established to realize the rapid adjustment of the original plan and improve the overall benefit of the plan and early completion of emergency tasks. Simultaneously, two heuristic factors, namely the emergency task urgency degree and task conflict degree, are constructed to improve the emergency task scheduling guidance and algorithm efficiency. Finally, we conduct extensive experiments by means of simulations to compare the algorithms based on ISBDR and direct insertion, shifting, deletion, and reinsertion (ISDR). The results demonstrate that the proposed algorithm can improve the timeliness of emergency tasks and scheduling performance, and decrease the disturbance measure of the scheme, therefore, it is more suitable for emergency task scheduling.

This paper investigates the distributed continuous-time aggregative optimization problem for second-order multi-agent systems, where the local cost function is not only related to its own decision variables, but also to the aggregation of the decision variables of all the agents. By using the gradient descent method, the distributed average tracking (DAT) technique and the time-base generator (TBG) technique, a distributed continuous-time aggregative optimization algorithm is proposed. Subsequently, the optimality of the system’s equilibrium point is analyzed, and the convergence of the closed-loop system is proved using the Lyapunov stability theory. Finally, the effectiveness of the proposed algorithm is validated through case studies on multirobot systems and power generation systems.

A novel multi-view 3D face registration method based on principal axis analysis and labeled regions orientation called local orientation registration is proposed. The pre-registration is achieved by transforming the multi-pose models to the standard frontal model’s reference frame using the principal axis analysis algorithm. Some significant feature regions, such as inner and outer canthus, nose tip vertices, are then located by using geometrical distribution characteristics. These regions are subsequently employed to compute the conversion parameters using the improved iterative closest point algorithm, and the optimal parameters are applied to complete the final registration. Experimental results implemented on the proper database demonstrate that the proposed method significantly outperforms others by achieving 1.249 and 1.910 mean root-mean-square measure with slight and large view variation models, respectively.

The Ocean 4A scatterometer, expected to be launched in 2024, is poised to be the world’s first spaceborne microwave scatterometer utilizing a digital beamforming system. To ensure high-precision measurements and performance stability across diverse environments, stringent requirements are placed on the dynamic range of its receiving system. This paper provides a detailed exposition of a field-programmable gate array (FPGA)-based automatic gain control (AGC) design for the spaceborne scatterometer. Implemented on an FPGA, the algorithm harnesses its parallel processing capabilities and high-speed performance to monitor the received echo signals in real time. Employing an adaptive AGC algorithm, the system generates gain control codes applicable to the intermediate frequency variable attenuator, enabling rapid and stable adjustment of signal amplitudes from the intermediate frequency amplifier to an optimal range. By adopting a purely digital processing approach, experimental results demonstrate that the AGC algorithm exhibits several advantages, including fast convergence, strong flexibility, high precision, and outstanding stability. This innovative design lays a solid foundation for the high-precision measurements of the Ocean 4A scatterometer, with potential implications for the future of spaceborne microwave scatterometers.

Total variation (TV) is widely applied in image processing. The assumption of TV is that an image consists of piecewise constants, however, it suffers from the so-called staircase effect. In order to reduce the staircase effect and preserve the edges when textures of image are extracted, a new image decomposition model is proposed in this paper. The proposed model is based on the total generalized variation method which involves and balances the higher order of the structure. We also derive a numerical algorithm based on a primal-dual formulation that can be effectively implemented. Numerical experiments show that the proposed method
can achieve a better trade-off between noise removal and texture extraction, while avoiding the staircase effect efficiently.

Complex systems widely exist in nature and human society. There are complex interactions between system elements in a complex system, and systems show complex features at the macro level, such as emergence, self-organization, uncertainty, and dynamics. These complex features make it difficult to understand the internal operation mechanism of complex systems. Networked modeling of complex systems is a favorable means of understanding complex systems. It not only represents complex interactions but also reflects essential attributes of complex systems. This paper summarizes the research progress of complex systems modeling and analysis from the perspective of network science, including networked modeling, vital node analysis, network invulnerability analysis, network disintegration analysis, resilience analysis, complex network link prediction, and the attacker-defender game in complex networks. In addition, this paper presents some points of view on the trend and focus of future research on network analysis of complex systems.

Traditional inverse synthetic aperture radar (ISAR) imaging methods for maneuvering targets have low resolution and poor capability of noise suppression. An ISAR imaging method of maneuvering targets based on phase retrieval is proposed, which can provide a high-resolution and focused map of the spatial distribution of scatterers on the target. According to theoretical derivation, the modulus of raw data from the maneuvering target is not affected by radial motion components for ISAR imaging system, so the phase retrieval algorithm can be used for ISAR imaging problems. However, the traditional phase retrieval algorithm will be not applicable to ISAR imaging under the condition of random noise. To solve this problem, an algorithm is put forward based on the range Doppler (RD) algorithm and oversampling smoothness (OSS) phase retrieval algorithm. The algorithm captures the target information in order to reduce the influence of the random phase on ISAR echoes, and then applies OSS for focusing imaging based on prior information of the RD algorithm. The simulated results demonstrate the validity of this algorithm, which cannot only obtain high resolution imaging for high speed maneuvering targets under the condition of random noise, but also substantially improve the success rate of the phase retrieval algorithm.

The theory of compressed sensing (CS) provides a new chance to reduce the data acquisition time and improve the data usage factor of the stepped frequency radar system. In light of the sparsity of radar target reflectivity, two imaging methods based on CS, termed the CS-based 2D joint imaging algorithm and the CS-based 2D decoupled imaging algorithm, are proposed. These methods incorporate the coherent mixing operation into the sparse dictionary, and take random measurements in both range and azimuth directions to get high resolution radar images, thus can remarkably reduce the data rate and simplify the hardware design of the radar system while maintaining imaging quality. Experimentsfrom both simulated data and measured data in the anechoic chamber show that the proposed imaging methods can get more focused images than the traditional fast Fourier transform method. Wherein the joint algorithm has stronger robustness and can provide clearer inverse synthetic aperture radar images, while the decoupled algorithm is computationally more efficient but has slightly degraded imaging quality, which can be improved by increasing measurements or using a robuster recovery algorithm nevertheless

With the advantage of fast calculation and map resources on cloud control system (CCS), cloud-based predictive cruise control (CPCC) for heavy trucks has great potential to improve energy efficiency, which is significant to achieve the goal of national carbon neutrality. However, most investigations focus on the on-board predictive cruise control (PCC) system, lack of research on CPCC architecture under CCS. Besides, the current PCC algorithms have the problems of a single control target and high computational complexity, which hinders the improvement of the control effect. In this paper, a layered architecture based on CCS is proposed to effectively address the real-time computing of CPCC system and the deployment of its algorithm on vehicle-cloud. In addition, based on the dynamic programming principle and the proposed road point segmentation method (RPSM), a PCC algorithm is designed to optimize the speed and gear of heavy trucks with slope information. Simulation results show that the CPCC system can adaptively control vehicle driving through the slope prediction, with fuel-saving rate of 6.17% in comparison with the constant cruise control. Also, compared with other similar algorithms, the PCC algorithm can make the engine operate more in the efficient zone by cooperatively optimizing the gear and speed. Moreover, the RPSM algorithm can reconfigure the road in advance, with a 91% roadpoint reduction rate, significantly reducing algorithm complexity. Therefore, this study has essential research significance for the economic driving of heavy trucks and the promotion of the CPCC system.

Bird’s-eye-view (BEV) perception is a core technology for autonomous driving systems. However, existing solutions face the dilemma of high costs associated with multi-modal methods and limited performance of vision-only approaches. To address this issue, this paper proposes a framework named “a lightweight pure visual BEV perception method based on dual distillation of spatial-temporal knowledge”. This framework innovatively designs a lightweight vision-only student model based on ResNet, which leverages a dual distillation mechanism to learn from a powerful teacher model that integrates temporal information from both image and light detection and ranging (LiDAR) modalities. Specifically, we distill efficient multi-modal feature extraction and spatial fusion capabilities from the BEVFusion model, and distill advanced temporal information fusion and spatiotemporal attention mechanisms from the BEVFormer model. This dual distillation strategy enables the student model to achieve perception performance close to that of multi-modal models without relying on LiDAR. Experimental results on the nuScenes dataset demonstrate that the proposed model significantly outperforms classical vision-only algorithms, achieves comparable performance to current state-of-the-art vision-only methods on the nuScenes detection leaderboard in terms of both mean average precision (mAP) and the nuScenes detection score (NDS) metrics, and exhibits notable advantages in inference computational efficiency. Although the proposed dual-teacher paradigm incurs higher offline training costs compared to single-model approaches, it yields a streamlined and highly efficient student model suitable for resource-constrained real-time deployment. This provides an effective pathway toward low-cost, high-performance autonomous driving perception systems.

The problem of scheduling radar dwells in multifunction phased array radar systems is addressed. A novel dwell scheduling algorithm is proposed. The whole scheduling process is based on an online pulse interleaving technique. It takes the system timing and energy constraints into account. In order to adapt the dynamic task load, the algorithm considers both the priorities and deadlines of tasks.  The simulation results demonstrate that compared with the conventional adaptive dwell scheduling algorithm, the proposed one can improve the task drop rate and system resource utility effectively.

Lightweight convolutional neural networks (CNNs) have simple structures but struggle to comprehensively and accurately extract important semantic information from images. While attention mechanisms can enhance CNNs by learning distinctive representations, most existing spatial and hybrid attention methods focus on local regions with extensive parameters, making them unsuitable for lightweight CNNs. In this paper, we propose a self-attention mechanism tailored for lightweight networks, namely the brief self-attention module (BSAM). BSAM consists of the brief spatial attention (BSA) and advanced channel attention blocks. Unlike conventional self-attention methods with many parameters, our BSA block improves the performance of lightweight networks by effectively learning global semantic representations. Moreover, BSAM can be seamlessly integrated into lightweight CNNs for end-to-end training, maintaining the network’s lightweight and mobile characteristics. We validate the effectiveness of the proposed method on image classification tasks using the Food-101, Caltech-256, and Mini-ImageNet datasets.

Weakly supervised semantic segmentation (WSSS) is a tricky task, which only provides category information for segmentation prediction. Thus, the key stage of WSSS is to generate the pseudo labels. For convolutional neural network (CNN) based methods, in which class activation mapping (CAM) is proposed to obtain the pseudo labels, and only concentrates on the most discriminative parts. Recently, transformer-based methods utilize attention map from the multi-headed self-attention (MHSA) module to predict pseudo labels, which usually contain obvious background noise and incoherent object area. To solve the above problems, we use the Conformer as our backbone, which is a parallel network based on convolutional neural network (CNN) and Transformer. The two branches generate pseudo labels and refine them independently, and can effectively combine the advantages of CNN and Transformer. However, the parallel structure is not close enough in the information communication. Thus, parallel structure can result in poor details about pseudo labels, and the background noise still exists. To alleviate this problem, we propose enhancing convolution CAM (ECCAM) model, which have three improved modules based on enhancing convolution, including deeper stem (DStem), convolutional feed-forward network (CFFN) and feature coupling unit with convolution (FCUConv). The ECCAM could make Conformer have tighter interaction between CNN and Transformer branches. After experimental verification, the improved modules we propose can help the network perceive more local information from images, making the final segmentation results more refined. Compared with similar architecture, our modules greatly improve the semantic segmentation performance and achieve 70.2% mean intersection over union（mIoU） on the PASCAL VOC 2012 dataset.

Formation control of multiple spacecraft has attracted extensive research attention. However, achieving reliable performance under sensor failures remains a significant challenge. This paper develops an integrated framework that jointly designs distributed observers and local controllers to ensure robust formation control in the presence of external disturbances and sensor malfunctions. Treating the spacecraft formation as a single interconnected system, each spacecraft constructs a distributed observer that estimates the overall system state by incorporating both its own measurements and the predicted control information shared among the spacecraft. Based on the observer estimates, a local control law is synthesized to maintain the desired formation. Rigorous theoretical analysis and numerical simulations demonstrate that the proposed integrated approach effectively guarantees formation stability and resilience against sensor failures and disturbances.

Traditional multi-band frequency selective surface (FSS) approaches are hard to achieve a perfect resonance response in a wide band due to the limit of the onset grating lobe frequency determined by the array. To solve this problem, an approach of combining elements in different period to build a hybrid array is presented. The results of series of numerical simulation show that multi-periodicity combined element FSS, which are designed using this approach, usually have much weaker grating lobes than the traditional FSS. Furthermore, their frequency response can be well predicted through the properties of their member element FSS. A prediction method for estimating the degree of expected grating lobe energy loss in designing multi-band FSS using this approach is provided.

A proper weapon system is very important for a national defense system. Generally, it means selecting the optimal weapon system among many alternatives, which is a multipleattribute decision making (MADM) problem. This paper proposes a new mathematical model based on the response surface method (RSM) and the grey relational analysis (GRA). RSM is used to obtain the experimental points and analyze the factors that have a significant impact on the selection results. GRA is used to analyze the trend relationship between alternatives and reference series. And then an RSM model is obtained, which can be used to calculate all alternatives and obtain ranking results. A real world application is introduced to illustrate the utilization of the model for the weapon selection problem. The results show that this model can be used to help decision-makers to make a quick comparison of alternatives and select a proper weapon system from multiple alternatives, which is an effective and adaptable method for solving the weapon system selection problem.

A composited integrated guidance and control (IGC) algorithm is presented to tackle the problem of the IGC design in the dive phase for the bank-to-turn (BTT) vehicle with the inaccuracy information of the line-of-sight (LOS) rate. For the sake of theoretical derivation, an IGC model in the pitch plane is established. The high-order finite-time state observer (FTSO), with the LOS angle as the single input, is employed to reconstruct the states of the system online. Besides, a composited IGC algorithm is presented via the fusion of back-stepping and dynamic inverse. Compared with the traditional IGC algorithm, the proposed composited IGC method can attenuate effectively the design conservation of the flight control system, while the LOS rate is mixed with noise. Extensive experiments have been performed to demonstrate that the proposed approach is globally finite-time stable and strongly robust against parameter uncertainty.

Numerous works prove that existing neighbor-averaging graph neural networks (GNNs) cannot efficiently catch structure features, and many works show that injecting structure, distance, position, or spatial features can significantly improve the performance of GNNs, however, injecting high-level structure and distance into GNNs is an intuitive but untouched idea. This work sheds light on this issue and proposes a scheme to enhance graph attention networks (GATs) by encoding distance and hop-wise structure statistics. Firstly, the hop-wise structure and distributional distance information are extracted based on several hop-wise ego-nets of every target node. Secondly, the derived structure information, distance information, and intrinsic features are encoded into the same vector space and then added together to get initial embedding vectors. Thirdly, the derived embedding vectors are fed into GATs, such as GAT and adaptive graph diffusion network (AGDN) to get the soft labels. Fourthly, the soft labels are fed into correct and smooth (C&S) to conduct label propagation and get final predictions. Experiments show that the distance and hop-wise structures encoding enhanced graph attention networks (DHSEGATs) achieve a competitive result.

With the development of global position system (GPS), wireless technology and location aware services, it is possible to collect a large quantity of trajectory data. In the field of data mining for moving objects, the problem of anomaly detection is a hot topic. Based on the development of anomalous trajectory detection of moving objects, this paper introduces the classical trajectory outlier detection (TRAOD) algorithm, and then proposes a density-based trajectory outlier detection (DBTOD) algorithm, which compensates the disadvantages of the TRAOD algorithm that it is unable to detect anomalous defects when the trajectory is local and dense. The results of employing the proposed algorithm to Elk1993 and Deer1995 datasets are also presented, which show the effectiveness of the algorithm.

The concept of unmanned weapon system-of-systems (UWSoS) involves a collection of various unmanned systems to achieve or accomplish a specific goal or mission. The mission reliability of UWSoS is represented by its ability to finish a required mission above the baselines of a given mission. However, issues with heterogeneity, cooperation between systems, and the emergence of UWSoS cannot be effectively solved by traditional system reliability methods. This study proposes an effective operation-loop-based mission reliability evaluation method for UWSoS by analyzing dynamic reconfiguration. First, we present a new connotation of an effective operation loop by considering the allocation of operational entities and physical resource constraints. Then, we propose an effective operation-loop-based mission reliability model for a heterogeneous UWSoS according to the mission baseline. Moreover, a mission reliability evaluation algorithm is proposed under random external shocks and topology reconfiguration, revealing the evolution law of the effective operation loop and mission reliability. Finally, a typical 60-unmanned-aerial-vehicle-swarm is taken as an example to demonstrate the proposed models and methods. The mission reliability is achieved by considering external shocks, which can serve as a reference for evaluating and improving the effectiveness of UWSoS.

In wireless sensor networks, ensuring communication security via specific emitter identification (SEI) is crucial. However, existing SEI methods are limited to closed-set scenarios and lack the ability to detect unknown devices and perform class-incremental training. This study proposes a class-incremental open-set SEI approach. The open-set SEI model calculates radio-frequency fingerprints (RFFs) prototypes for known signals and employs a self-attention mechanism to enhance their discriminability. Detection thresholds are set through Gaussian fitting for each class. For class-incremental learning, the algorithm freezes the parameters of the previously trained model to initialize the new model. It designs specific losses: the RFFs extraction distribution difference loss and the prototype transformation distribution difference loss, which force the new model to retain old knowledge while learning new knowledge. The training loss enables learning of new class RFFs. Experimental results demonstrate that the open-set SEI model achieves state-of-the-art performance and strong noise robustness. Moreover, the class-incremental learning algorithm effectively enables the model to retain old device RFFs knowledge, acquire new device RFFs knowledge, and detect unknown devices simultaneously.

The realization of the parameter estimation of chirp signals using the fractional Fourier transform (FRFT) is based on the assumption that the sampling duration of practical observed signals would be equal to the time duration of chirp signals contained in the former. However, in many actual circumstances, this assumption seems unreasonable. On the basis of analyzing the practical signal form, this paper derives the estimation error of the existing parameter estimation method and then proposes a novel and universal parameter estimation algorithm. Furthermore, the proposed algorithm is developed which allows the estimation of the practical observed Gaussian windowed chirp signal. Simulation results show that the new algorithm works well.

In laser-guided bomb attacking process, the target indication from the laser target designator is the premise for the bomb to hit the target accurately. Considering the lack of quantitative study of the irradiation area of the laser target designator, this paper, based on the existing aircraft motion model and the laser transmission model, uses two aircraft as respectively the carrier of the laser-guided bomb and the carrier of the laser designator and proposes a method to calculate the global irradiation area of the airborne laser designator. By using the proposed algorithm, the global irradiation area when attacking a large flat target or a large spherical target is simulated respectively. Finally, according to the simulation results, the influences of different factors on the shapes of the irradiation area are discussed in detail.

In the applications of joint control and robot movement, the joint torque estimation has been treated as an effective technique and widely used. Researches are made to analyze the kinematic and compliance model of the robot joint with harmonic drive to acquire high precision torque output. Through analyzing the structures of the harmonic drive and experiment apparatus, a scheme of the proposed joint torque estimation method based on both the dynamic characteristics and unscented Kalman filter (UKF) is designed and built. Based on research and scheme, torque estimation methods in view of only harmonic drive compliance model and compliance model with the Kalman filter are simulated as guidance and reference to promote the research on the torque estimation technique. Finally, a promoted torque estimation method depending on both harmonic drive compliance model and UKF is designed, and simulation results compared with the measurements of a commercial torque sensor, have verified the effectiveness of the proposed method.

Spacecraft require a large-angle manoeuvre when performing agile manoeuvring tasks, therefore a control moment gyroscope (CMG) is employed to provide a strong moment. However, the control of the CMG system easily falls into singularity, which renders the actuator unable to output the required moment. To solve the singularity problem of CMGs, the control law design of a CMG system based on a cooperative game is proposed. First, the cooperative game model is constructed according to the quadratic programming problem, and the cooperative strategy is constructed. When the strategy falls into singularity, the weighting coefficient is introduced to carry out the strategy game to achieve the optimal strategy. In theory, it is proven that the cooperative game manipulation law of the CMG system converges, the sum of the CMG frame angular velocities is minimized, the energy consumption is small, and there is no output torque error. Then, the CMG group system is simulated. When the CMG system is near the singular point, it can quickly escape the singularity. When the CMG system falls into the singularity, it can also escape the singularity. Considering the optimization of angular momentum and energy consumption, the feasibility of the CMG system steering law based on a cooperative game is proven.

In order to improve the autonomous ability of unmanned aerial vehicles (UAV) to implement air combat mission, many artificial intelligence-based autonomous air combat maneuver decision-making studies have been carried out, but these studies are often aimed at individual decision-making in 1v1 scenarios which rarely happen in actual air combat. Based on the research of the 1v1 autonomous air combat maneuver decision, this paper builds a multi-UAV cooperative air combat maneuver decision model based on multi-agent reinforcement learning. Firstly, a bidirectional recurrent neural network (BRNN) is used to achieve communication between UAV individuals, and the multi-UAV cooperative air combat maneuver decision model under the actor-critic architecture is established. Secondly, through combining with target allocation and air combat situation assessment, the tactical goal of the formation is merged with the reinforcement learning goal of every UAV, and a cooperative tactical maneuver policy is generated. The simulation results prove that the multi-UAV cooperative air combat maneuver decision model established in this paper can obtain the cooperative maneuver policy through reinforcement learning, the cooperative maneuver policy can guide UAVs to obtain the overall situational advantage and defeat the opponents under tactical cooperation.

To solve discrete optimization difficulty of the spectrum allocation problem, a membrane-inspired quantum shuffled frog leaping (MQSFL) algorithm is proposed. The proposed MQSFL algorithm applies the theory of membrane computing and quantum computing to the shuffled frog leaping algorithm, which is an effective discrete optimization algorithm. Then the proposed MQSFL algorithm is used to solve the spectrum allocation problem of cognitive radio systems. By hybridizing the quantum frog colony optimization and membrane computing, the quantum state and observation state of the quantum frogs can be well evolved within the membrane structure. The novel spectrum allocation algorithm can search the global optimal solution within a reasonable computation time. Simulation results for three utility functions of  a cognitive radio system are provided to show that the MQSFL spectrum allocation method is superior to some previous spectrum allocation algorithms based on intelligence computing.

For multi-agent reinforcement learning in Markov games, knowledge extraction and sharing are key research problems. State list extracting means to calculate the optimal shared state path from state trajectories with cycles. A state list extracting algorithm checks cyclic state lists of a current state in the state trajectory, condensing the optimal action set of the current state. By reinforcing the optimal action selected, the action policy of cyclic states is optimized gradually. The state list extracting is repeatedly learned and used as the experience knowledge which is shared by teams. Agents speed up the rate of convergence by experience sharing. Competition games of preys and predators are used for the experiments. The results of experiments prove that the proposed algorithms overcome the lack of experience in the initial stage, speed up learning and improve the performance.

The development processes and the application achievements of space-borne microwave sounder prelaunch calibration technologies in China are introduced briefly. Then, the general project plan for pre-launch calibration, the latest research achievements on the optimization and development of the microwave wide band calibration targets, emissivity measurement technologies and the system level uncertainty analysis of the laboratory, and the thermal/vacuum microwave sounder calibration system for “FY-3” meteorological satellite are reported, respectively. Finally, the key technological problems of the calibration technologies under researching are analyzed predictively.