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

页码：1898 / 1905

页数：7

共 22 条

[11]

LI P, DUAN H B., A flocking model base on selective attention mechanism, Scientia Sinica Technologica, 49, 9, pp. 1040-1050, (2019)

[12]

CHEN Z F, LIAO H M, CHU T G., Clustering in multi-agent swarms via medium-range interaction, Europhysics Letters, 96, 4, (2011)

[13]

YANG P P, LIU M Y, LEI X K, Et al., Progress in modeling and control of fission behavior for flocking system, Control and Decision, 31, 2, pp. 193-206, (2016)

[14]

LEI X K., From Grouping to Grouping: Theoretical Modeling and Analysis of Self-organizing Group Movement, (2015)

[15]

LIU Y Y, SLOTINE J J, BARABASI A L., Controllability of complex networks, Nature, 473, 7346, pp. 167-173, (2011)

[16]

LI C F, ZHANG Y W, SHAO J Q, Et al., Progress on fission behavior for multi-agent flocking system, Electronics Optics & Control, 29, 6, pp. 62-67, (2022)

[17]

LEI X K, LIU M Y, YANG P P., Fission control algorithm for swarm based on local following interaction, Control and Decision, 28, 5, pp. 741-745, (2013)

[18]

LIU M Y, LEI X K, YANG P P, Et al., Information coupling degree based approach for self-organized fission behavior in flocking system, Control and Decision, 30, 2, pp. 271-276, (2015)

[19]

YANG P P, LIU M Y, LEI X K, Et al., A novel fission control method for swarm robots based on self-organized pairwise interaction behavior, Northwestern Polytechnical University, 33, 1, pp. 147-152, (2015)

[20]

GAO Z L, DING Y, HE J., Multi-agent movement control combining attention-following mechanism with IAP method, Electronics Optics & Control, 27, 3, pp. 58-64, (2020)

← 1 2 3 →