UAV Swarm Rounding Strategy Based on Deep Reinforcement Learning Goal Consistency with Multi-Head Soft Attention Algorithm

Aiming at the problem of target rounding by UAV swarms in complex environments, this paper proposes a goal consistency reinforcement learning approach based on multi-head soft attention (GCMSA). Firstly, in order to make the model closer to reality, the reward function when the target is at differen...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhaotian Wei, Ruixuan Wei
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Drones
Subjects:
Online Access:https://www.mdpi.com/2504-446X/8/12/731
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850059036555214848
author Zhaotian Wei
Ruixuan Wei
author_facet Zhaotian Wei
Ruixuan Wei
author_sort Zhaotian Wei
collection DOAJ
description Aiming at the problem of target rounding by UAV swarms in complex environments, this paper proposes a goal consistency reinforcement learning approach based on multi-head soft attention (GCMSA). Firstly, in order to make the model closer to reality, the reward function when the target is at different positions and the target escape strategy are set, respectively. Then, the Multi-head soft attention module is used to promote the information cognition of the target among the UAVs, so that the UAVs can complete the target roundup more smoothly. Finally, in the training phase, this paper introduces cognitive dissonance loss to improve the sample utilization. Simulation experiments show that GCMSA is able to obtain a higher task success rate and is significantly better than MADDPG in terms of algorithm performance.
format Article
id doaj-art-90fa65354a6d4a66aa1a3cd8576dfa5c
institution DOAJ
issn 2504-446X
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Drones
spelling doaj-art-90fa65354a6d4a66aa1a3cd8576dfa5c2025-08-20T02:50:59ZengMDPI AGDrones2504-446X2024-12-0181273110.3390/drones8120731UAV Swarm Rounding Strategy Based on Deep Reinforcement Learning Goal Consistency with Multi-Head Soft Attention AlgorithmZhaotian Wei0Ruixuan Wei1Graduate School, Air Force Engineering University, Xi’an 710051, ChinaAviation Engineering School, Air Force Engineering University, Xi’an 710038, ChinaAiming at the problem of target rounding by UAV swarms in complex environments, this paper proposes a goal consistency reinforcement learning approach based on multi-head soft attention (GCMSA). Firstly, in order to make the model closer to reality, the reward function when the target is at different positions and the target escape strategy are set, respectively. Then, the Multi-head soft attention module is used to promote the information cognition of the target among the UAVs, so that the UAVs can complete the target roundup more smoothly. Finally, in the training phase, this paper introduces cognitive dissonance loss to improve the sample utilization. Simulation experiments show that GCMSA is able to obtain a higher task success rate and is significantly better than MADDPG in terms of algorithm performance.https://www.mdpi.com/2504-446X/8/12/731UAV swarmsroundup strategydeep reinforcement learningGCMSA
spellingShingle Zhaotian Wei
Ruixuan Wei
UAV Swarm Rounding Strategy Based on Deep Reinforcement Learning Goal Consistency with Multi-Head Soft Attention Algorithm
Drones
UAV swarms
roundup strategy
deep reinforcement learning
GCMSA
title UAV Swarm Rounding Strategy Based on Deep Reinforcement Learning Goal Consistency with Multi-Head Soft Attention Algorithm
title_full UAV Swarm Rounding Strategy Based on Deep Reinforcement Learning Goal Consistency with Multi-Head Soft Attention Algorithm
title_fullStr UAV Swarm Rounding Strategy Based on Deep Reinforcement Learning Goal Consistency with Multi-Head Soft Attention Algorithm
title_full_unstemmed UAV Swarm Rounding Strategy Based on Deep Reinforcement Learning Goal Consistency with Multi-Head Soft Attention Algorithm
title_short UAV Swarm Rounding Strategy Based on Deep Reinforcement Learning Goal Consistency with Multi-Head Soft Attention Algorithm
title_sort uav swarm rounding strategy based on deep reinforcement learning goal consistency with multi head soft attention algorithm
topic UAV swarms
roundup strategy
deep reinforcement learning
GCMSA
url https://www.mdpi.com/2504-446X/8/12/731
work_keys_str_mv AT zhaotianwei uavswarmroundingstrategybasedondeepreinforcementlearninggoalconsistencywithmultiheadsoftattentionalgorithm
AT ruixuanwei uavswarmroundingstrategybasedondeepreinforcementlearninggoalconsistencywithmultiheadsoftattentionalgorithm