Network learning via multiagent inverse transportation problems

Susan Jia Xu, Mehdi Nourinejad, Xuebo Lai, Joseph Ying Jun Chow

Research output: Contribution to journalArticle

Abstract

Despite the ubiquity of transportation data, methods to infer the state parameters of a network either ignore sensitivity of route decisions, require route enumeration for parameterizing descriptive models of route selection, or require complex bilevel models of route assignment behavior. These limitations prevent modelers from fully exploiting ubiquitous data in monitoring transportation networks. Inverse optimization methods that capture network route choice behavior can address this gap, but they are designed to take observations of the same model to learn the parameters of that model, which is statistically inefficient (e.g., requires estimating population route and link flows). New inverse optimization models and supporting algorithms are proposed to learn the parameters of heterogeneous travelers’ route behavior to infer shared network state parameters (e.g., link capacity dual prices). The inferred values are consistent with observations of each agent’s optimization behavior. We prove that the method can obtain unique dual prices for a network shared by these agents in polynomial time. Four experiments are conducted. The first one, conducted on a four-node network, verifies the methodology to obtain heterogeneous link cost parameters even when multinomial or mixed logit models would not be meaningfully estimated. The second is a parameter recovery test on the Nguyen–Dupuis network that shows that unique latent link capacity dual prices can be inferred using the proposed method. The third test on the same network demonstrates how a monitoring system in an online learning environment can be designed using this method. The last test demonstrates this learning on real data obtained from a freeway network in Queens, New York, using only real-time Google Maps queries.

Original languageEnglish (US)
Pages (from-to)1347-1364
Number of pages18
JournalTransportation Science
Volume52
Issue number6
DOIs
StatePublished - Nov 1 2018

Fingerprint

learning
Monitoring
freeway network
Highway systems
monitoring
optimization model
Polynomials
search engine
Recovery
learning environment
Costs
experiment
methodology
costs
Experiments
Values
time

Keywords

  • Inverse optimization
  • Learning
  • Multiagent system
  • Network analysis
  • Route choice

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Transportation

Cite this

Network learning via multiagent inverse transportation problems. / Xu, Susan Jia; Nourinejad, Mehdi; Lai, Xuebo; Chow, Joseph Ying Jun.

In: Transportation Science, Vol. 52, No. 6, 01.11.2018, p. 1347-1364.

Research output: Contribution to journalArticle

Xu, Susan Jia ; Nourinejad, Mehdi ; Lai, Xuebo ; Chow, Joseph Ying Jun. / Network learning via multiagent inverse transportation problems. In: Transportation Science. 2018 ; Vol. 52, No. 6. pp. 1347-1364.
@article{2df481c8c5664cebb9fc6853219ae3cc,
title = "Network learning via multiagent inverse transportation problems",
abstract = "Despite the ubiquity of transportation data, methods to infer the state parameters of a network either ignore sensitivity of route decisions, require route enumeration for parameterizing descriptive models of route selection, or require complex bilevel models of route assignment behavior. These limitations prevent modelers from fully exploiting ubiquitous data in monitoring transportation networks. Inverse optimization methods that capture network route choice behavior can address this gap, but they are designed to take observations of the same model to learn the parameters of that model, which is statistically inefficient (e.g., requires estimating population route and link flows). New inverse optimization models and supporting algorithms are proposed to learn the parameters of heterogeneous travelers’ route behavior to infer shared network state parameters (e.g., link capacity dual prices). The inferred values are consistent with observations of each agent’s optimization behavior. We prove that the method can obtain unique dual prices for a network shared by these agents in polynomial time. Four experiments are conducted. The first one, conducted on a four-node network, verifies the methodology to obtain heterogeneous link cost parameters even when multinomial or mixed logit models would not be meaningfully estimated. The second is a parameter recovery test on the Nguyen–Dupuis network that shows that unique latent link capacity dual prices can be inferred using the proposed method. The third test on the same network demonstrates how a monitoring system in an online learning environment can be designed using this method. The last test demonstrates this learning on real data obtained from a freeway network in Queens, New York, using only real-time Google Maps queries.",
keywords = "Inverse optimization, Learning, Multiagent system, Network analysis, Route choice",
author = "Xu, {Susan Jia} and Mehdi Nourinejad and Xuebo Lai and Chow, {Joseph Ying Jun}",
year = "2018",
month = "11",
day = "1",
doi = "10.1287/trsc.2017.0805",
language = "English (US)",
volume = "52",
pages = "1347--1364",
journal = "Transportation Science",
issn = "0041-1655",
publisher = "INFORMS Inst.for Operations Res.and the Management Sciences",
number = "6",

}

TY - JOUR

T1 - Network learning via multiagent inverse transportation problems

AU - Xu, Susan Jia

AU - Nourinejad, Mehdi

AU - Lai, Xuebo

AU - Chow, Joseph Ying Jun

PY - 2018/11/1

Y1 - 2018/11/1

N2 - Despite the ubiquity of transportation data, methods to infer the state parameters of a network either ignore sensitivity of route decisions, require route enumeration for parameterizing descriptive models of route selection, or require complex bilevel models of route assignment behavior. These limitations prevent modelers from fully exploiting ubiquitous data in monitoring transportation networks. Inverse optimization methods that capture network route choice behavior can address this gap, but they are designed to take observations of the same model to learn the parameters of that model, which is statistically inefficient (e.g., requires estimating population route and link flows). New inverse optimization models and supporting algorithms are proposed to learn the parameters of heterogeneous travelers’ route behavior to infer shared network state parameters (e.g., link capacity dual prices). The inferred values are consistent with observations of each agent’s optimization behavior. We prove that the method can obtain unique dual prices for a network shared by these agents in polynomial time. Four experiments are conducted. The first one, conducted on a four-node network, verifies the methodology to obtain heterogeneous link cost parameters even when multinomial or mixed logit models would not be meaningfully estimated. The second is a parameter recovery test on the Nguyen–Dupuis network that shows that unique latent link capacity dual prices can be inferred using the proposed method. The third test on the same network demonstrates how a monitoring system in an online learning environment can be designed using this method. The last test demonstrates this learning on real data obtained from a freeway network in Queens, New York, using only real-time Google Maps queries.

AB - Despite the ubiquity of transportation data, methods to infer the state parameters of a network either ignore sensitivity of route decisions, require route enumeration for parameterizing descriptive models of route selection, or require complex bilevel models of route assignment behavior. These limitations prevent modelers from fully exploiting ubiquitous data in monitoring transportation networks. Inverse optimization methods that capture network route choice behavior can address this gap, but they are designed to take observations of the same model to learn the parameters of that model, which is statistically inefficient (e.g., requires estimating population route and link flows). New inverse optimization models and supporting algorithms are proposed to learn the parameters of heterogeneous travelers’ route behavior to infer shared network state parameters (e.g., link capacity dual prices). The inferred values are consistent with observations of each agent’s optimization behavior. We prove that the method can obtain unique dual prices for a network shared by these agents in polynomial time. Four experiments are conducted. The first one, conducted on a four-node network, verifies the methodology to obtain heterogeneous link cost parameters even when multinomial or mixed logit models would not be meaningfully estimated. The second is a parameter recovery test on the Nguyen–Dupuis network that shows that unique latent link capacity dual prices can be inferred using the proposed method. The third test on the same network demonstrates how a monitoring system in an online learning environment can be designed using this method. The last test demonstrates this learning on real data obtained from a freeway network in Queens, New York, using only real-time Google Maps queries.

KW - Inverse optimization

KW - Learning

KW - Multiagent system

KW - Network analysis

KW - Route choice

UR - http://www.scopus.com/inward/record.url?scp=85052875411&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85052875411&partnerID=8YFLogxK

U2 - 10.1287/trsc.2017.0805

DO - 10.1287/trsc.2017.0805

M3 - Article

AN - SCOPUS:85052875411

VL - 52

SP - 1347

EP - 1364

JO - Transportation Science

JF - Transportation Science

SN - 0041-1655

IS - 6

ER -