Fully Distributed and Attack-Immune Protocols for Prescribed-Time Consensus by Using Periodic Delayed Relative Output
针对只能通过传感器获取相对输出数据的一般线性多智能体系统，设计了基于周期性延迟输出测量的分布式观测器和线性时变控制协议，在预设时间内实现一致性，且无需网络直接数据交换，天然抗网络攻击。
This study investigates the problem of achieving consensus within a prescribed time for general linear multiagent systems (MASs) operating over directed communication graphs, particularly when agents can only access relative output data via their onboard sensors. Under the assumption of strong observability, we design a periodic delayed output measurements-based distributed observer to recover the relative state information. Leveraging the reconstructed states, a linear time-varying control protocol is developed to ensure consensus is attained within the desired time. In contrast to conventional approaches, our method brings several key benefits. Most importantly, it removes the requirement for direct data exchange over the network, making the system inherently robust against cyber-attacks. Furthermore, the protocol is entirely distributed, which enhances adaptability to dynamic communication structures. At last, since the proposed method utilizes linear state feedback, it avoids the need for real-time solutions of system-related differential equations, thus reducing computational overhead. Numerical simulations demonstrate the efficacy of the proposed strategy.