Neural Network-Based Finite-Time Distributed Formation-Containment Control of Two-Layer Quadrotor UAVs
将四旋翼无人机分为领导者和追随者两层，领导者接收跟踪信息，追随者通过图论通信网络获取信息，提出分布式编队包含控制方法，并用神经网络处理不确定性，实现有限时间稳定跟踪。
In this article, quadrotor unmanned aerial vehicles (QUAVs) are organized as a two-layer structure, where the first layer is leader QUAVs and the second layer is follower QUAVs. In this structure, only the leader QUAVs can receive the desired tracking information of position and attitude. Although the followers cannot obtain the given tracking information directly, they can obtain the corresponding information from leaders and other followers through the communication network based on the graph theory. In terms of this case, a distributed formation-containment (FC) control method is proposed to handle the related flight problems. We aim to develop a formation control for the leader QUAVs and a containment control for the follower QUAVs with the graph theory. Furthermore, a neural network (NN) technique is utilized to cope with the uncertainty of each QUAV. In order to guarantee good flight performance when tracking, the finite-time stability theorem is introduced into the control design to make each QUAV achieve satisfactory tacking performance in finite time. Finally, numerical simulations are conducted in the platform of two-layer 16 QUAVs to validate the feasibility and effectiveness of the proposed NN-based finite-time FC control.