The advancement of UAV technology makes the use of UAVs more and more widespread, and the swarm is the main mode of UAV applications owing to its robustness and adaptability. Meanwhile, task allocation plays an essential role in a swarm to obtain overall high performance and unleash the potential of each UAVs owing to the complexity of the large-scale swarm. In this paper, we pay attention to the real-time allocation problem of dynamic tasks. We design models for the task assigning problem to construct the constraints model and assigning objectives. In addition, we introduce a novel agent-based allocating mechanism based on the auction process, including the design for three kinds of agents and the cooperation mechanism among different agents. Moreover, we proposed a new algorithm to calculate the bidding values of UAVs, by which the messages passed between UAVs can be reduced. On the basis of the assigning mechanism, we put up with a novel agent-based real-time task allocation algorithm named NECTAR for dynamic tasks in the UAV swarm. Furthermore, we conduct extensive experiments to evaluate the performance of our NECTAR, and the results indicate that NECTAR is able to solve the real-time task allocation for dynamic tasks and achieve high performance of the UAV swarm.

中文翻译：

---

NECTAR-无人机群中基于代理的动态任务分配算法

无人飞行器技术的进步使无人飞行器的使用越来越广泛，由于其坚固性和适应性强，蜂群是无人飞行器应用的主要方式。同时，由于大型机群的复杂性，任务分配在机群中起着至关重要的作用，以获得总体高性能并释放每个无人机的潜力。在本文中，我们关注动态任务的实时分配问题。我们为任务分配问题设计模型，以构造约束模型和分配目标。此外，我们基于拍卖过程介绍了一种新颖的基于代理的分配机制，包括三种代理的设计以及不同代理之间的协作机制。此外，我们提出了一种新的算法来计算无人机的竞标价格，通过它可以减少无人机之间传递的消息。在分配机制的基础上，我们提出了一种新颖的基于代理的实时任务分配算法NECTAR，用于无人机群中的动态任务。此外，我们进行了广泛的实验来评估NECTAR的性能，结果表明NECTAR能够解决动态任务的实时任务分配并实现无人机群的高性能。