MAPPO-GAT: A Graph-Attention-Driven Multi-Agent Reinforcement Learning Framework for Entropy-Aware Autonomous Drone Swarm Coordination

无人机 群体行为 计算机科学 熵(时间箭头) 理论(学习稳定性) 光学(聚焦) 强化学习 任务(项目管理) 群机器人 避碰 图形 人工智能 碰撞 多智能体系统 电信网络 自主代理人 分布式计算 群体智能 订单(交换) 机器人 图论
作者
Komal Yadav,Durga Prasad Palaparthi,Gaurav Garg,Harshitha H B,Thella Preethi Priyanka,S. Kaliappan
出处
期刊: [Institute of Electrical and Electronics Engineers]
卷期号:: 1-8 被引量:3
标识
DOI:10.1109/icaft66710.2025.11452673
摘要

Managing autonomous swarms of drones in dynamic and uncertain conditions is a considerable challenge, especially in high-entropy conditions, where autonomous swarms form disordered formations and unequal spacing, and present a higher likelihood of collisions. To solve this issue, there is a need to have communication effective and uncertainty conscious multi-agent learning schemes that are able to create stability without compromising on scalability. In order to address these shortcomings, this paper presents a new framework called MAPPO-GAT, which is an entropy-sensitive swarm coordination model incorporating Multi-Agent Proximal Policy Optimization (MAPPO) and a Graph Attention Network (GAT)-based communication system. The suggested solution improves the information communication because it allows drones to focus on the most meaningful neighbors, and an entropy-driven reward system punishes disorder and encourages the formation control. The Drone-Swarm-Entropy Dataset, a subset of Kaggle, is used to conduct experiments, and it consists of different flight patterns with varying degrees of disturbance. Quantitative findings prove that MAPPO-GAT is much more successful than MAPPO, MADDPG, QMIX, and COMA, the mission success, coverage, entropy reduced and the rate of collision minimally lowered. Specifically, MAPPO-GAT has the highest success rate of 93%, collision rate of 11% and stable swarm formations than all the baselines. The framework is also highly energy efficient, by reducing the needless drone motions due to attention coordination. On the whole, this paper introduces the first MARL-GAT hybridized system that is tailored to the specific task of entropy-conscious swarm intelligence, creating a high-sized, resilient, and communication-efficient base of autonomous drone systems of the next generation.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
Salome完成签到 ,获得积分10
1秒前
康敏艳发布了新的文献求助20
1秒前
椰椰完成签到,获得积分20
1秒前
科研通AI2S的应助被sun采纳,获得10
2秒前
bai发布了新的文献求助10
2秒前
养火花发布了新的文献求助10
2秒前
2秒前
FAN发布了新的文献求助10
2秒前
kuailewuzhu发布了新的文献求助10
3秒前
3秒前
cz发布了新的文献求助10
3秒前
bkagyin的应助被老胖采纳,获得10
3秒前
3秒前
now完成签到,获得积分10
4秒前
4秒前
4秒前
微笑的冷之完成签到,获得积分10
4秒前
天天快乐的应助被孤独白拍采纳,获得10
5秒前
cpt完成签到,获得积分20
6秒前
幸运之星完成签到 ,获得积分10
6秒前
Dr_Seurin完成签到,获得积分10
6秒前
panda发布了新的文献求助10
7秒前
正在完成签到,获得积分10
7秒前
斯文若血发布了新的文献求助10
7秒前
steins发布了新的文献求助10
8秒前
hk发布了新的文献求助10
8秒前
直率的尔烟完成签到,获得积分10
8秒前
乐乐的应助被Mokwepa采纳,获得10
8秒前
9秒前
巨子鹭完成签到,获得积分10
9秒前
10秒前
11秒前
11秒前
12秒前
万能图书馆的应助被hk采纳,获得10
12秒前
CCC完成签到,获得积分10
13秒前
开朗的天佑完成签到,获得积分10
13秒前
雪山大地发布了新的文献求助10
13秒前
superworm1发布了新的文献求助10
13秒前
13秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
What Else Can I Tell You?: A Pragmatic Study of English Rhetorical Questions as Discursive and Argumentative Acts 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8163835
求助须知:如何正确求助?哪些是违规求助? 9557925
关于积分的说明 21742693
捐赠科研通 7754454
什么是DOI,文献DOI怎么找? 3428350
关于科研通互助平台的介绍 2553034
邀请新用户注册赠送积分活动 2472982