Guardado en:
Detalles Bibliográficos
Autores principales: Zhi, Jianing, Li, Xinghua, Chen, Zidong
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2507.10636
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918091293720576
author Zhi, Jianing
Li, Xinghua
Chen, Zidong
author_facet Zhi, Jianing
Li, Xinghua
Chen, Zidong
contents The rapid development of urban low-altitude unmanned aerial vehicle (UAV) economy poses new challenges for dynamic site selection of UAV landing points and supply stations. Traditional deep reinforcement learning methods face computational complexity bottlenecks, particularly with standard attention mechanisms, when handling large-scale urban-level location problems. This paper proposes GeoHopNet, a Hopfield-augmented sparse spatial attention network specifically designed for dynamic UAV site location problems. Our approach introduces four core innovations: (1) distance-biased multi-head attention mechanism that explicitly encodes spatial geometric information; (2) K-nearest neighbor sparse attention that reduces computational complexity from $O(N^2)$ to $O(NK)$; (3) a modern Hopfield external memory module; and (4) a memory regularization strategy. Experimental results demonstrate that GeoHopNet extends the boundary of solvable problem sizes. For large-scale instances with 1,000 nodes, where standard attention models become prohibitively slow (over 3 seconds per instance) and traditional solvers fail, GeoHopNet finds high-quality solutions (0.22\% optimality gap) in under 0.1 seconds. Compared to the state-of-the-art ADNet baseline on 100-node instances, our method improves solution quality by 22.2\% and is 1.8$\times$ faster.
format Preprint
id arxiv_https___arxiv_org_abs_2507_10636
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GeoHopNet: Hopfield-Augmented Sparse Spatial Attention for Dynamic UAV Site Location Problem
Zhi, Jianing
Li, Xinghua
Chen, Zidong
Machine Learning
Artificial Intelligence
Neural and Evolutionary Computing
Robotics
90B06
I.2.8
The rapid development of urban low-altitude unmanned aerial vehicle (UAV) economy poses new challenges for dynamic site selection of UAV landing points and supply stations. Traditional deep reinforcement learning methods face computational complexity bottlenecks, particularly with standard attention mechanisms, when handling large-scale urban-level location problems. This paper proposes GeoHopNet, a Hopfield-augmented sparse spatial attention network specifically designed for dynamic UAV site location problems. Our approach introduces four core innovations: (1) distance-biased multi-head attention mechanism that explicitly encodes spatial geometric information; (2) K-nearest neighbor sparse attention that reduces computational complexity from $O(N^2)$ to $O(NK)$; (3) a modern Hopfield external memory module; and (4) a memory regularization strategy. Experimental results demonstrate that GeoHopNet extends the boundary of solvable problem sizes. For large-scale instances with 1,000 nodes, where standard attention models become prohibitively slow (over 3 seconds per instance) and traditional solvers fail, GeoHopNet finds high-quality solutions (0.22\% optimality gap) in under 0.1 seconds. Compared to the state-of-the-art ADNet baseline on 100-node instances, our method improves solution quality by 22.2\% and is 1.8$\times$ faster.
title GeoHopNet: Hopfield-Augmented Sparse Spatial Attention for Dynamic UAV Site Location Problem
topic Machine Learning
Artificial Intelligence
Neural and Evolutionary Computing
Robotics
90B06
I.2.8
url https://arxiv.org/abs/2507.10636