Building autonomous systems that achieve human level intelligence is one of the primary objectives in artificial intelligence (AI). It requires the study of a wide range of functions robustly across different phases of human cognition. This paper presents a review of agent cognitive architectures in the past 20 year's AI research. Different from software structures and simulation environments, most of the architectures concerned are established from mathematics and philosophy. They are categorized according to their knowledge processing patterns--symbolic, emergent or hybrid. All the relevant literature can be accessed publicly, particularly through the Internet. Available websites are also summarized for further reference.

In recent years, analysis and optimization algorithm based on image data is a research hotspot. Aircraft detection based on aerial images can provide data support for accurately attacking military targets. Although many efforts have been devoted, it is still challenging due to the poor environment, the vastness of the sky background, and so on. This paper proposes an aircraft detection method named TransEffiDet in aerial images based on the EfficientDet method and Transformer module. We improved the EfficientDet algorithm by combining it with the Transformer which models the long-range dependency for the feature maps. Specifically, we first employ EfficientDet as the backbone network, which can efficiently fuse the different scale feature maps. Then, deformable Transformer is used to analyze the long-range correlation for global feature extraction. Furthermore, we designed a fusion module to fuse the long-range and short-range features extracted by EfficientDet and deformable Transformer, respectively. Finally, object class is produced by feeding the feature map to the class prediction net and the bounding box predictions are generated by feeding these fused features to the box prediction net. The mean Average Precision (mAP) is 86.6%, which outperforms the EfficientDet by 5.8%. The experiment shows that TransEffiDet is more robust than other methods. Additionally, we have established a public aerial dataset for aircraft detection, which will be released along with this paper.

With the rapid growth of application demands and the real-time change of environmental situations, the defects of the UAV task network in adaptability, flexibility, and resilience are becoming more and more prominent. The current network architecture that the junction of points and lines is fixed cannot dynamically provide capacity requirements in real-time due to the failure nodes encountered in the Unmanned Aerial Vehicle (UAV) task scheduling process. To address this challenging issue, this paper proposes a flexible network architecture supporting dynamic fault-tolerant task scheduling model (DSM-FNA) for the UAV cluster. To be specific this paper resorts to super network theory, combining the management theory of flexible network and resilience network to carry out the organizational calculation on the model, and also draw upon linear transformation function to weight and stratify the capability value according to the ability requirement required by the task. Then, a flexible network architecture dynamic scheduling algorithm (FDSA) is proposed, and the substitution strategy is designed for the failure point, to realize the capability and dynamically adapt to the task. Finally, compared with the classical Max-Min algorithm and other algorithms, it is verified that the FDSA algorithm performs better dynamic adjustment for quick response in case of UAV cluster emergencies.

Affected by the rescue environment and the unmanned aerial vehicle (UAV) communication technology, communication among UAVs is greatly restricted. How to do rescue mission planning for UAV swarms under limited communication has become a difficult problem. This paper proposes a motif-based mission planning model which generates a mission planning strategy as a task priority execution order is inputted. The choice of mission planning strategy turns to be the choice of a task priority execution order which is a many-objective optimization problem. Permutation and combination of task priority execution order contribute to the generation of mass feasible task planning strategies. The increase in the number of tasks leads to the explosion of the amount of calculation. We enhance preference-inspired co-evolutionary algorithm with goal vectors (PICEA-g) by using K-means clustering method in the step of offspring selection to select out next generation goal vectors. The proposed algorithm, called k-PICEA-g is applied in the optimization process minimizing, simultaneously, the mission completion time (MCT), the total number of changed connections (TNOCC) and the average number of used UAVs (ANOUU) through changing the priority execution order of tasks. As an example of application, we apply the improved PICEA-g to optimize the execution order of a set of tasks, achieving a set of non-dominated solutions from which the decision maker can select the most adequate one. By experiments, the feasibility and effectiveness of this algorithm is validated.

Person-job fit, which aims to predict the matching degree between a resume and a job, has become an effective way to overcome information overload in the recruitment market. Existing studies on person-job fit usually focus on the representation learning of textual data in jobs and resumes. Person-job fit is a highly nonlinear complex problem that is affected by several fields of features. We assume that it would bring benefits to comprehensively consider the numerical features, categorical features, and textual features of resumes and jobs. To this end, we propose a novel model based on the self-attention mechanism, named MUlti-Field Features representation and INteraction (MUFFIN) learning for person-job fit. The key idea is to explore meaningful feature representations and interactions. Specifically, we group all the features of resumes and jobs into several fields. And a module is introduced to learn the hidden vectors of feature correlations in each feature field. Along this line, we propose a module with the multi-head self-attention mechanism and a residual connection to further model the feature field interactions. Moreover, we utilize a multi-layer perceptron (MLP) to measure the matching score between a resume and a job. Finally, the experimental results on a real-world dataset validate the effectiveness of MUFFIN for person-job fit.