In multi-agent systems, the decision of an agent will be affected by the behaviors of others. Therefore, from the perspective of an agent, the situation is uncertain and random. Inspired by the social behaviors in the biological world, a novel multi-agent coverage path planning algorithm is proposed. Based on the positions of agents, the problem is decoupled, which can effectively reduce the dimension of the decision space. The behavior-guide-point is introduced to guide agents in making decisions, and a new motion mode is presented. To avoid falling into the local optimum, a cooperation mechanism is designed, which can improve the adaptability of the system. Through proximity interaction, the prediction results obtained via the model predictive control (MPC) technology are fused, evaluated, and sorted within the neighborhood, based on which decisions are gained. The proposed algorithm can handle emergencies in unknown environments such as body damage and moving obstacles, and can also be applied to heterogeneous systems. Simulation shows that compared with other algorithms, it has advantages in terms of the makespan and the coverage repetition rate.

In command of modern intelligent operations, in addition to solving the problem of multi-unit coordinated task assignment, it is also necessary to obtain a suitable plan according to the needs of decision makers. Based on these requirements, we established a multi-stage bi-objective weapon-target assignment model, and designed a new algorithm with niche and region self-adaptive aggregation (named MOEA/ D-NRSA) based on the decomposition-based multi-objective evolutionary algorithm (MOEA/D) to obtain richer solutions that meet the preferences of different decision makers. Compared with MOEA/D, MOEA/ D-NRSA has advantages in improving the convergence and maintaining the distribution of the solution. On the one hand, it contains a population evolution method based on niche technology to obtain better offspring; on the other hand, it has a new neighborhood selection and update strategy. This strategy first clusters the individuals in the objective space to divide into different regions, in which the subproblems can independently select the appropriate aggregation mode according to the clustering density of the region and update its neighborhood. This strategy can improve the uneven distribution of individuals and maintain the diversity and distribution of the population. Numerical experiments selected state-of-the-art algorithms for comparison, which proved the superiority of MOEA/D-NRSA.

Human error can be regarded as a significant factor contributing to high-speed railway accidents. Cognitive Reliability and Error Analysis Method (CREAM) is well-known approach applied to determine Human Error Probability (HEP). However, shortcomings are still disclosed and weaken the applicability of such approach. These include the lack of sufficient failure data, lack of valid description of Common Performance Condition (CPC) and does not consider the CPCs weights. In addition, Basic CREAM does not provide a method to calculate the concrete HEP. In this paper, a modified CREAM is proposed to assess HEP of high-speed railway dispatchers in dispatching tasks. The core of the modified method is to use 2-tuple linguistic term sets to describe CPCs evaluation, combine weighted CPCs by Evidential Reasoning (ER) approach, and adopt Multi-Attribute Group Decision-Making (MAGDM) method to calculate HEP. To make CPCs weights more accurate, dynamically adjusting weights is adopted in this paper. The rationality and validity of the modified CREAM approach are verified by two axioms and compared other models. Finally this modified CREAM approach is applied to human reliability analysis of high-speed railway dispatchers.