Landscape-Aware Bandit Hyper-Heuristics for Online Operator Selection in UAV Inspection Routing

TL;DR

This paper introduces LA-BHH, a landscape-aware bandit hyper-heuristic that learns online operator selection for UAV inspection routing, significantly improving solution quality over existing methods.

Contribution

It develops a novel online learning approach combining landscape descriptors and search features for operator selection in UAV routing.

Findings

LA-BHH achieves the best mean final gap and convergence AUC on Euclidean TSP instances.

LA-BHH reduces final gap by 17.6% over UCB-HH and 68.2% over nearest-neighbor construction.

Ablation shows the importance of contextual credit assignment, 2-opt repair, and stagnation-aware state.

Abstract

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.