Cooperative Multi-Task Assignment of Unmanned Autonomous Helicopters Based on Hybrid Enhanced Learning ABC Algorithm
Zengliang Han, Mou Chen, Shuyi Shao, Haojie Zhu, Qingxian Wu
Abstract
Aiming at the problem of cooperative combat problem for multiple unmanned autonomous helicopters (UAHs) in complex battlefield environments, a hybrid enhanced artificial bee colony (ABC) algorithm-based cooperative multi-task assignment method is proposed in this article. Firstly, by analyzing the battlefield requirements of UAH clusters in multi-target scenarios, a complex constrained task assignment optimization model considering practical application scenarios is established. Furthermore, a hybrid enhanced ABC algorithm is proposed based on cognitive-psychological learning (CPL). The proposed CPL-ABC algorithm integrates swarm intelligence and human cognitive mechanisms to guide the evolutionary direction of the population by introducing individual expectation effects and personality differences. In addition, an introspection evolution mechanism based on individual variability is introduced to enhance the local optimal escape ability of the ABC algorithm. Through the reflection and learning of locally optimal individuals, the uncontrollable influence of direction caused by random evolution is reduced. Finally, the simulation and experiment results verify the effectiveness and feasibility of the proposed cooperative multi-task assignment method.