A Level-Based Distributed Recursive Self-Healing Algorithm of Unmanned Aerial Vehicle Swarm

In adversarial environments, unmanned aerial vehicle (UAV) swarms often face challenges such as node failures, battle damage, and strong electromagnetic interference, which may result in network failures and disruptions to physical formation. To address the issue of node failures, this paper proposes a distributed self-healing algorithm to recover corrupted swarm configurations. First, a distributed flocking method is employed to achieve self-organized formation and velocity alignment within the UAV swarm. Next, a concept named “level” is introduced, along with a level generation and diffusion mechanism to establish a stable level distribution across the swarm. This mechanism enables the evaluation of the importance of each UAV in the swarm. Based on the level distribution, a distributed recursive self-healing strategy is developed to construct healing paths that repair the damage caused by failed nodes. Finally, a series of simulations are conducted to demonstrate the effectiveness of the proposed algorithm.