Cooperative Fission Control Algorithm of UAV Swarm Based on Attention Mechanism

被引:0
作者
Ren S. [1 ]
Zhou J. [1 ]
Gao S. [1 ]
Chen C.-B. [1 ]
机构
[1] School of Electronics and Information Engineering, Xi’an Technological University, Shaanxi, Xi’an
来源
Tien Tzu Hsueh Pao/Acta Electronica Sinica | 2023年 / 51卷 / 07期
关键词
attention mechanism; dynamic weight; multiple stimuli; partial perception; state transition; UAV swarm;
D O I
10.12263/DZXB.20221378
中图分类号
学科分类号
摘要
Aiming at the problem that unmanned aerial vehicle (UAV) swarm based on separation, alignment and cohesion rules cannot respond to multiple stimuli caused by partial perception, a cooperative fission control algorithm of UAV swarm based on attention mechanism is proposed. In order to ensure the efficient selection of neighbor information by UAV, the perception rule is designed considering the sight occlusion factor, and then the attention mechanism is introduced to calculate the contribution of UAV to the orderliness of local group in interactive neighbors. To solve the problem of UAV decision conflict under multiple stimuli, a state transition model based on attention mechanism is designed. In particular, the sub-activation state is designed to calculate the dynamic weight of stimulus source, so as to improve the sensitivity of swarm response to multiple stimuli. To achieve continuous and accurate tracking of the target by UAV, the motion strategy is determined based on the motion state of UAV, and then the motion model is adjusted. The changes process of motion trajectory and movement direction of the swarm in response to multiple stimuli is analyzed by simulation, and the process of fission motion is analyzed by stress precision, subgroup order parameter and fission time. The simulation results show that the proposed algorithm enables the UAV swarm to complete the fission motion in about 5 s, and realize fast and accurate tracking of stimuli. © 2023 Chinese Institute of Electronics. All rights reserved.
引用
收藏
页码:1898 / 1905
页数:7
相关论文
共 22 条
[1]  
LI P J, MAO P J, GENG Q, Et al., Research status and trend of UAV swarm technology, Aero Weaponry, 27, 4, pp. 25-32, (2020)
[2]  
LIU Q, HE M, LIU J T, Et al., A mechanism for identifying and suppressing the emergent flocking behaviors of UAV swarms, Acta Electronica Sinica, 47, 2, pp. 374-381, (2019)
[3]  
QIU H X, DUAN H B., From collective flight in bird flocks to unmanned aerial vehicle autonomous swarm formation, Chinese Journal of Engineering, 39, 3, pp. 317-322, (2017)
[4]  
HUANG F, LI G X, WANG H C, Et al., Navigation for UAV pair-supported relaying in unknown IoT systems with deep reinforcement learning, Chinese Journal of Electronics, 31, 3, pp. 416-429, (2022)
[5]  
DUAN H B, LI P., Autonomous control for unmanned aerial vehicle swarms based on biological collective behaviors, Science & Technology Review, 35, 7, pp. 17-25, (2017)
[6]  
LUO Q N, DUAN H B., Distributed UAV flocking control based on homing pigeon hierarchical strategies, Aerospace Science and Technology, 70, pp. 257-264, (2017)
[7]  
CHEN M, DAI F, WANG H B, Et al., DFM: A distributed flocking model for UAV swarm networks, IEEE Access, 6, pp. 69141-69150, (2018)
[8]  
GAO Y, LI D S, LIU X., UAV swarm cooperative situation perception consensus evaluation, Acta Electronica Sinica, 47, 1, pp. 190-196, (2019)
[9]  
OLFATI-SABER R., Flocking for multi-agent dynamic systems: Algorithms and theory, IEEE Transactions on Automatic Control, 51, 3, pp. 401-420, (2006)
[10]  
DONG J G, HA S Y, JUNG J, Et al., On the stochastic flocking of the cucker: Smale flock with randomly switching topologies, SIAM Journal on Control and Optimization, 58, 4, pp. 2332-2353, (2020)