Multirobot information gathering in adversarial environments, where enemies can destroy detected robots, presents unique challenges not addressed by existing algorithms designed for safe settings. The advent of multirobot systems enables collaborative risk-avoidance behavior, exemplified in pursuit-evasion scenarios, where concentrated robot groups enhance their ability to evade and overcome pursuing enemies. However, current multirobot information gathering algorithms have not yet integrated this collaborative risk-avoidance model, potentially leading to robot damage and reduced efficiency. This study adopts a decomposition-and-grafting mechanism to separate the problem into two weakly coupled subproblems: task execution and task allocation. For task execution, we propose an exact algorithm based on the branch-and-pricing method. Our task execution algorithms are seamlessly integrated with a novel task map composition algorithm designed to identify high-utility solutions with minimal computational overhead, addressing the task allocation problem. Extensive simulations demonstrate that our algorithms significantly outperform benchmarks by increasing the number of collaborative risk-avoidance activities conducted by robots during information gathering tasks in adversarial environments. This research advances multirobot information gathering by incorporating collaborative risk-avoidance, enhancing robot survivability and efficiency in hazardous settings.

With the high degree of integration of production capacity in the industrial field, the original form of single, linear, and vertical cooperation between different industrial chains has been broken, and a multiplex networked industrial chain has been formed. Traditional time series forecasting methods are often prone to fall into the trap of computational volume caused by long historical information and the problem of dimensional explosion caused by the mixing of redundant information in the face of multiple networked industrial chain capacity forecasting with large data volume and high information dimensionality. In this paper, we first propose an information decoupling technique based on the principle of time series decomposition to provide more accurate cyclical forecasting results for capacity forecasting. Secondly, this paper introduces a multi-scale dynamic aggregation network technique. This technique dynamically aggregates and predicts variables at different time scales. The combination of these two approaches is adept at capturing a wider range of local and global trends, thereby greatly improving the accuracy and robustness of forecasting models. In this paper, experiments are conducted to compare with the current mainstream time series prediction algorithms. The results show that in multivariate long time series, the error of our algorithm is reduced by 27.8%.

Multirobot information gathering in adversarial environments, where enemies can destroy detected robots, presents unique challenges not addressed by existing algorithms designed for safe settings. The advent of multirobot systems enables collaborative risk-avoidance behavior, exemplified in pursuit-evasion scenarios, where concentrated robot groups enhance their ability to evade and overcome pursuing enemies. However, current multirobot information gathering algorithms have not yet integrated this collaborative risk-avoidance model, potentially leading to robot damage and reduced efficiency. This study adopts a decomposition-andgrafting mechanism to separate the problem into two weakly coupled subproblems: task execution and task allocation. For task execution, we propose an exact algorithm based on the branch-and-pricing method. Our task execution algorithms are seamlessly integrated with a novel task map composition algorithm designed to identify high-utility solutions with minimal computational overhead, addressing the task allocation problem. Extensive simulations demonstrate that our algorithms significantly outperform benchmarks by increasing the number of collaborative risk-avoidance activities conducted by robots during information gathering tasks in adversarial environments. This research advances multirobot information gathering by incorporating collaborative risk-avoidance, enhancing robot survivability and efficiency in hazardous settings.