Abstract

For the first time, a fully neural approach has been proposed, capable of solving the optimization problem of routes of extremely large dimensions (~5000 points) with real-world constraints such as cargo capacity, time windows, and delivery sequencing. The proposed solution allows for rapid suboptimal problem solving for small and medium dimensions (<1000 points). Meanwhile, it outperforms heuristic approaches for tasks of extremely large dimensions (>1000 points), thereby representing a state-of-the-art (SotA) solution in the field of route optimization with real-world constraints and extremely large dimensions.

中文翻译：

---

使用网络和纯网络解决大规模路由优化问题

摘要

首次提出了一种全神经方法，能够解决具有现实世界约束（例如货运能力、时间窗口和交付顺序）的超大尺寸（约 5000 个点）的路线优化问题。所提出的解决方案允许快速解决中小尺寸（<1000 点）的次优问题。同时，对于超大维度（>1000点）的任务，它的性能优于启发式方法，从而代表了具有现实世界约束和超大维度的路径优化领域最先进的（SotA）解决方案。