A hybrid algorithm with learning-based crossover, multi-penalty search, and GPU tensor acceleration solves large-scale multi-depot vehicle routing problems competitively with state-of-the-art methods.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A GPU-Accelerated Hybrid Method for a Class of Multi-Depot Vehicle Routing Problems
A hybrid algorithm with learning-based crossover, multi-penalty search, and GPU tensor acceleration solves large-scale multi-depot vehicle routing problems competitively with state-of-the-art methods.