发表机构
Alibaba Group（阿里巴巴集团）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有路线规划方法无法兼顾用户偏好和最优性的问题，提出一种联合优化成本函数与路线排序的深度架构，实现可微最短路径搜索，在真实数据集上显著提升路线质量与可定制性。
AI 中文摘要
随着在线导航和网约车服务的广泛使用，针对多样化用户偏好实现最优路线规划近来受到越来越多的关注。用于路径查找的经典图算法使用启发式成本函数来定义边权重，因此无法保证路线质量的最优性。先前将最优路线真实值等同于用户轨迹的数据驱动方法，受到导航服务的适度影响，存在反馈循环问题。为解决这些问题，我们提出了一种深度架构，能够针对任意路线偏好联合优化成本函数和路线排序模型。首先，我们离线运行多目标Dijkstra算法，收集帕累托最优路线集合，并将其视为完整候选集。利用该集合的性质，我们设计了一种神经网络结构，以端到端可微的方式模拟最短路径搜索和路线排序。其次，我们将路线偏好定义为路线属性的约束优化任务，并提出一种新颖的损失函数，该函数优化单一目标变量，同时其他变量严格受约束。我们在真实世界数据集上进行了大量实验。结果表明，我们的架构在路线质量和可定制性方面显著优于最先进的方法。
英文摘要
With the widespread use of online navigation and ride-hailing services, achieving optimal route planning for diverse user preferences has recently attracted increasing attention. Classic graph algorithms for pathfinding use heuristic cost functions to define edge weight, thus providing no optimality guarantee of route quality. Prior data-driven approaches equating ground truth of the optimal route with user trajectory, which is however moderately influenced by the navigation service, suffers from the feedback loop problem. To address these issues, we propose a deep architecture that is able to jointly optimize cost functions and route-ranking model towards any route preference. First, we run a multi-objective Dijkstra algorithm offline to collect the set of Pareto optimal routes, deeming it as the complete candidate set. Exploiting the property of such a set, we design a neural network structure that emulates shortest-path search and route ranking in an end-to-end differentiable manner. Second, we define route preference as a task of constrained optimization of route attributes, and propose a novel loss function that optimizes a single-objective variable, with other variables strictly under constraints. We conduct extensive experiments on real-world datasets. The results show that our architecture significantly outperforms state-of-the-art methods in route quality and customizability.
