arXiv：cs.LG· Gyeongjun Kim, Yeseul Kang, Keemin Sohn·· 4 小时前AI 评分27
基于决策聚焦学习的个性化车辆路径复现神经优化框架
A Decision-Focused Neural Optimization Framework for Personalized Route Reproduction from Vehicle Trajectories
AI 导读
研究将个体路径复现建模为基于驾驶员特定隐式路段成本的最短路径问题，提出融合感知模型与约束优化层的神经管线，并用决策聚焦学习实现端到端训练。该方法采用隐式最大似然估计近似处理不可微的约束优化层，并引入正则项将隐式成本分布锚定到实际路段行程时间尺度。实验表明该框架在路径复现上优于基线路径选择模型。
正文
Abstract:This study formulates individual route reproduction as a shortest-path problem over learned driver-specific latent link costs. The central idea is that, once such latent costs are inferred from contextual information, observed routes can be reproduced without enumerating alternative route sets. We propose a neural pipeline that includes a perception model that embeds context covariates, which comprises individual characteristics, trip-specific attributes, and network-level traffic states, into the personalized link costs. A constrained optimization (CO) layer, which determines the shortest path (SP) based on these estimated costs, follows the perception encoder. To enable end-to-end training, we employ decision-focused learning to align the predicted shortest paths with observed routes. The implicit maximum likelihood estimation (iMLE) provides an approximate gradient of the loss function that contains the non-differentiable CO layer. Furthermore, a regularization term anchors the latent cost distribution to the empirical scale of observed link travel times, mitigating the scale ambiguity inherent in shortest-path supervision. Empirical evaluations demonstrate that the proposed framework outperforms baseline route choice models in path reproduction. The learned latent costs, interpreted as proxies for perceived travel costs, provide plausible explanations for heterogeneous route choices.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.07857 [cs.LG] |
| (or arXiv:2610.07857v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.07857 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Keemin Sohn [view email]
[v1]
Tue, 6 Oct 2026 07:00:49 UTC (2,436 KB)
来源：arXiv：cs.LG · arxiv.org