NECTAR-An Agent-Based Dynamic Task Allocation Algorithm in the UAV Swarm

Abstract

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.

An Improved Intelligent Auction Mechanism for Emergency Material Delivery

“…The algorithm is based on pre-authorization to ensure the system capability performance, and based on sequential auctions to effectively improve the system resilience performance and avoid the frequent occurrence of interference that causes the system performance degradation by reallocation or adjustment of the assignment results. It should be noted that since the published task is executed in the future time and has no effect on the current execution process, the UAV can participate in the auction during the execution of the task [27], but it can only obtain the pre-authorization of the task instead of the authorization.…”

“…The algorithm involves internal system interaction and inevitably has communication problems. On the one hand, in the disaster area environment, ground communication base stations are damaged, and it is necessary to restore communication, and UAVs are mature and widely used as temporary communication relays [3]; on the other hand, the bidding process is performed by UAVs, which greatly reduces the state information interacted between CCSys and UAVs, and can be used in a limited bandwidth environment [27].…”

“…CBBA-PR ensures optimality in dynamic assignment and improves the fast response of the algorithm to dynamic situations, but the algorithm is not effective in some cases where real-time performance is required or the problem size is large. Chen et al [27] argued for the better applicability of online algorithms for the uncertain arrival of dynamic tasks and proposed that tasks should be assigned one by one rather than in batches to ensure the efficiency of UAV execution. Farinelli et al [28] converted multi-robot patrol into a task assignment problem, considered online decision making techniques, proposed the DTAP algorithm based on sequential single auction, and verified the performance of the algorithm on a real robot platform.…”

Digital-Twin-Assisted Task Assignment in Multi-UAV Systems: A Deep Reinforcement Learning Approach

“…Moreover, to solve the problem of information coupling between task assignment and path planning of UAVs, a strategy based on the distributed architecture is proposed to improve the efficiency of UAV and re-evaluate the assigned tasks in [15]. Furthermore, in [16], an improved auction mechanism algorithm with the constraints of communication and endurance time is proposed to assign tasks. In [17], the authors propose a new multi-task cooperated UAVs network framework and an AggreGate Flow based scheduler in which ML is used to precisely estimate the task urgency-level, and improve efficiently the multi-task completion rate.…”