Enhanced route planning with calibrated uncertainty set

Lingxuan Tang; Rui Luo; Zhixin Zhou; Nicolo Colombo

doi:10.1007/s10994-024-06697-7

Enhanced route planning with calibrated uncertainty set

Lingxuan Tang
, Rui Luo^*
, Zhixin Zhou
, Nicolo Colombo

^*Corresponding author for this work

Department of Systems Engineering

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

12 Citations (Scopus)

103 Downloads (CityUHK Scholars)

Abstract

This paper investigates the application of probabilistic prediction methodologies in route planning within a road network context. Specifically, we introduce the Conformalized Quantile Regression for Graph Autoencoders (CQR-GAE), which leverages the conformal prediction technique to offer a coverage guarantee, thus improving the reliability and robustness of our predictions. By incorporating uncertainty sets derived from CQR-GAE, we substantially improve the decision-making process in route planning under a robust optimization framework. We demonstrate the effectiveness of our approach by applying the CQR-GAE model to a real-world traffic scenario. The results indicate that our model significantly outperforms baseline methods, offering a promising avenue for advancing intelligent transportation systems. © The Author(s) 2025.

Original language	English
Article number	129
Journal	Machine Learning
Volume	114
Issue number	5
Online published	26 Mar 2025
DOIs	https://doi.org/10.1007/s10994-024-06697-7
Publication status	Published - May 2025

Funding

Open access publishing enabled by City University of Hong Kong Library's agreement with Springer Nature.

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 11 Sustainable Cities and Communities

Research Keywords

Conformal prediction
Covariate information
Quantile regression
Robust optimization
Route planning

Publisher's Copyright Statement

This full text is made available under CC-BY 4.0. https://creativecommons.org/licenses/by/4.0/

Access Output

10.1007/s10994-024-06697-7

279300196.pdfFinal Published version, 2.15 MBLicence: CC BY

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{6506c720632a407f8fb63197a6278e62,

title = "Enhanced route planning with calibrated uncertainty set",

abstract = "This paper investigates the application of probabilistic prediction methodologies in route planning within a road network context. Specifically, we introduce the Conformalized Quantile Regression for Graph Autoencoders (CQR-GAE), which leverages the conformal prediction technique to offer a coverage guarantee, thus improving the reliability and robustness of our predictions. By incorporating uncertainty sets derived from CQR-GAE, we substantially improve the decision-making process in route planning under a robust optimization framework. We demonstrate the effectiveness of our approach by applying the CQR-GAE model to a real-world traffic scenario. The results indicate that our model significantly outperforms baseline methods, offering a promising avenue for advancing intelligent transportation systems. {\textcopyright} The Author(s) 2025.",

keywords = "Conformal prediction, Covariate information, Quantile regression, Robust optimization, Route planning",

author = "Lingxuan Tang and Rui Luo and Zhixin Zhou and Nicolo Colombo",

year = "2025",

month = may,

doi = "10.1007/s10994-024-06697-7",

language = "English",

volume = "114",

journal = "Machine Learning",

issn = "0885-6125",

publisher = "Springer New York",

number = "5",

}

TY - JOUR

T1 - Enhanced route planning with calibrated uncertainty set

AU - Tang, Lingxuan

AU - Luo, Rui

AU - Zhou, Zhixin

AU - Colombo, Nicolo

PY - 2025/5

Y1 - 2025/5

N2 - This paper investigates the application of probabilistic prediction methodologies in route planning within a road network context. Specifically, we introduce the Conformalized Quantile Regression for Graph Autoencoders (CQR-GAE), which leverages the conformal prediction technique to offer a coverage guarantee, thus improving the reliability and robustness of our predictions. By incorporating uncertainty sets derived from CQR-GAE, we substantially improve the decision-making process in route planning under a robust optimization framework. We demonstrate the effectiveness of our approach by applying the CQR-GAE model to a real-world traffic scenario. The results indicate that our model significantly outperforms baseline methods, offering a promising avenue for advancing intelligent transportation systems. © The Author(s) 2025.

AB - This paper investigates the application of probabilistic prediction methodologies in route planning within a road network context. Specifically, we introduce the Conformalized Quantile Regression for Graph Autoencoders (CQR-GAE), which leverages the conformal prediction technique to offer a coverage guarantee, thus improving the reliability and robustness of our predictions. By incorporating uncertainty sets derived from CQR-GAE, we substantially improve the decision-making process in route planning under a robust optimization framework. We demonstrate the effectiveness of our approach by applying the CQR-GAE model to a real-world traffic scenario. The results indicate that our model significantly outperforms baseline methods, offering a promising avenue for advancing intelligent transportation systems. © The Author(s) 2025.

KW - Conformal prediction

KW - Covariate information

KW - Quantile regression

KW - Robust optimization

KW - Route planning

UR - https://www.scopus.com/pages/publications/105001342680

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-105001342680&origin=recordpage

U2 - 10.1007/s10994-024-06697-7

DO - 10.1007/s10994-024-06697-7

M3 - RGC 21 - Publication in refereed journal

SN - 0885-6125

VL - 114

JO - Machine Learning

JF - Machine Learning

IS - 5

M1 - 129

ER -

Enhanced route planning with calibrated uncertainty set

Abstract

Funding

UN SDGs

Research Keywords

Publisher's Copyright Statement

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this