Landscape-Aware Bandit Hyper-Heuristics for Online Operator Selection in UAV Inspection Routing
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911685555519488 |
|---|---|
| author | Wei, Junhao Li, Yanxiao Zhao, Yifu He, Qibin Li, Haochen Yao, Dexing Lu, Baili Peng, Zhenhong Wang, Yapeng Im, Sio-Kei Yang, Xu |
| author_facet | Wei, Junhao Li, Yanxiao Zhao, Yifu He, Qibin Li, Haochen Yao, Dexing Lu, Baili Peng, Zhenhong Wang, Yapeng Im, Sio-Kei Yang, Xu |
| contents | UAV multi-site inspection often reduces to choosing a high-quality visiting order after target sites have been extracted from a map. This paper develops LA-BHH, a landscape-aware bandit hyper-heuristic that learns an operator-selection policy online for this routing layer. LA-BHH treats 2-opt, swap, relocate, and Or-opt moves as low-level arms, builds context from static landscape descriptors and online search-state features, and updates a LinUCB controller from improvement rewards during the same run. Experimental results on 45 generated Euclidean TSP instances show that LA-BHH achieves the best mean final gap and convergence AUC, with 0.0223 and 0.0389 respectively. It reduces final gap by 17.6\% over UCB-HH, 22.6\% over Random-HH, and 68.2\% over nearest-neighbor construction. Ablation results further show that contextual credit assignment, 2-opt repair, and stagnation-aware state use are the main contributors. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_14620 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Landscape-Aware Bandit Hyper-Heuristics for Online Operator Selection in UAV Inspection Routing Wei, Junhao Li, Yanxiao Zhao, Yifu He, Qibin Li, Haochen Yao, Dexing Lu, Baili Peng, Zhenhong Wang, Yapeng Im, Sio-Kei Yang, Xu Computational Engineering, Finance, and Science UAV multi-site inspection often reduces to choosing a high-quality visiting order after target sites have been extracted from a map. This paper develops LA-BHH, a landscape-aware bandit hyper-heuristic that learns an operator-selection policy online for this routing layer. LA-BHH treats 2-opt, swap, relocate, and Or-opt moves as low-level arms, builds context from static landscape descriptors and online search-state features, and updates a LinUCB controller from improvement rewards during the same run. Experimental results on 45 generated Euclidean TSP instances show that LA-BHH achieves the best mean final gap and convergence AUC, with 0.0223 and 0.0389 respectively. It reduces final gap by 17.6\% over UCB-HH, 22.6\% over Random-HH, and 68.2\% over nearest-neighbor construction. Ablation results further show that contextual credit assignment, 2-opt repair, and stagnation-aware state use are the main contributors. |
| title | Landscape-Aware Bandit Hyper-Heuristics for Online Operator Selection in UAV Inspection Routing |
| topic | Computational Engineering, Finance, and Science |
| url | https://arxiv.org/abs/2605.14620 |