Dynamic collective routing using crowdsourcing data

Siyuan Liu, Qiang Qu

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

With the development of information technology, crowdsourcing data from a crowd of cooperative vehicles and online social platforms have been becoming available. The crowdsourcing data, reflecting real-time context of road segments in transportation systems, enable vehicles to be routed adaptively in uncertain and dynamic traffic environments. We consider the problem of adaptively routing a fleet of cooperative vehicles within a road network. To tackle this problem, we first propose a Crowdsourcing Dynamic Congestion Model. The model is based on topic-aware Gaussian Process considering the crowdsourced data collected from social platforms and probing vehicle traces that can effectively characterize both the dynamics and the uncertainty of road conditions. Our model is efficient and thus facilitates real-time adaptive routing in the face of uncertainty. Using this congestion model, we develop efficient algorithms for non-myopic adaptive routing to minimize the collective travel time of all vehicles in the entire transportation system. A key property of our approach is the ability to efficiently reason about the long-term value of exploration, which enables collectively balancing the exploration/exploitation trade-off for entire fleets of vehicles. Our approach is validated by real-life traffic and geo-tagged social network data from two large cities. Our congestion model is shown to be effective in modeling dynamic congestion conditions. Our routing algorithms also generate significantly faster routes compared to standard baselines, and approximate optimal performance compared to an omniscient routing algorithm. We also present the results from a preliminary field study, which showcases the efficacy of our approach.

Original languageEnglish (US)
Pages (from-to)450-469
Number of pages20
JournalTransportation Research Part B: Methodological
Volume93
DOIs
StatePublished - Nov 1 2016

Fingerprint

transportation system
Routing algorithms
uncertainty
road
traffic
road network
large city
Travel time
exploitation
social network
information technology
travel
Information technology
ability
performance
time
Uncertainty

All Science Journal Classification (ASJC) codes

  • Civil and Structural Engineering
  • Transportation

Cite this

@article{f3f6a3a152b147a59535a64e5c487b72,
title = "Dynamic collective routing using crowdsourcing data",
abstract = "With the development of information technology, crowdsourcing data from a crowd of cooperative vehicles and online social platforms have been becoming available. The crowdsourcing data, reflecting real-time context of road segments in transportation systems, enable vehicles to be routed adaptively in uncertain and dynamic traffic environments. We consider the problem of adaptively routing a fleet of cooperative vehicles within a road network. To tackle this problem, we first propose a Crowdsourcing Dynamic Congestion Model. The model is based on topic-aware Gaussian Process considering the crowdsourced data collected from social platforms and probing vehicle traces that can effectively characterize both the dynamics and the uncertainty of road conditions. Our model is efficient and thus facilitates real-time adaptive routing in the face of uncertainty. Using this congestion model, we develop efficient algorithms for non-myopic adaptive routing to minimize the collective travel time of all vehicles in the entire transportation system. A key property of our approach is the ability to efficiently reason about the long-term value of exploration, which enables collectively balancing the exploration/exploitation trade-off for entire fleets of vehicles. Our approach is validated by real-life traffic and geo-tagged social network data from two large cities. Our congestion model is shown to be effective in modeling dynamic congestion conditions. Our routing algorithms also generate significantly faster routes compared to standard baselines, and approximate optimal performance compared to an omniscient routing algorithm. We also present the results from a preliminary field study, which showcases the efficacy of our approach.",
author = "Siyuan Liu and Qiang Qu",
year = "2016",
month = "11",
day = "1",
doi = "10.1016/j.trb.2016.08.005",
language = "English (US)",
volume = "93",
pages = "450--469",
journal = "Transportation Research, Series B: Methodological",
issn = "0191-2615",
publisher = "Elsevier Limited",

}

Dynamic collective routing using crowdsourcing data. / Liu, Siyuan; Qu, Qiang.

In: Transportation Research Part B: Methodological, Vol. 93, 01.11.2016, p. 450-469.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Dynamic collective routing using crowdsourcing data

AU - Liu, Siyuan

AU - Qu, Qiang

PY - 2016/11/1

Y1 - 2016/11/1

N2 - With the development of information technology, crowdsourcing data from a crowd of cooperative vehicles and online social platforms have been becoming available. The crowdsourcing data, reflecting real-time context of road segments in transportation systems, enable vehicles to be routed adaptively in uncertain and dynamic traffic environments. We consider the problem of adaptively routing a fleet of cooperative vehicles within a road network. To tackle this problem, we first propose a Crowdsourcing Dynamic Congestion Model. The model is based on topic-aware Gaussian Process considering the crowdsourced data collected from social platforms and probing vehicle traces that can effectively characterize both the dynamics and the uncertainty of road conditions. Our model is efficient and thus facilitates real-time adaptive routing in the face of uncertainty. Using this congestion model, we develop efficient algorithms for non-myopic adaptive routing to minimize the collective travel time of all vehicles in the entire transportation system. A key property of our approach is the ability to efficiently reason about the long-term value of exploration, which enables collectively balancing the exploration/exploitation trade-off for entire fleets of vehicles. Our approach is validated by real-life traffic and geo-tagged social network data from two large cities. Our congestion model is shown to be effective in modeling dynamic congestion conditions. Our routing algorithms also generate significantly faster routes compared to standard baselines, and approximate optimal performance compared to an omniscient routing algorithm. We also present the results from a preliminary field study, which showcases the efficacy of our approach.

AB - With the development of information technology, crowdsourcing data from a crowd of cooperative vehicles and online social platforms have been becoming available. The crowdsourcing data, reflecting real-time context of road segments in transportation systems, enable vehicles to be routed adaptively in uncertain and dynamic traffic environments. We consider the problem of adaptively routing a fleet of cooperative vehicles within a road network. To tackle this problem, we first propose a Crowdsourcing Dynamic Congestion Model. The model is based on topic-aware Gaussian Process considering the crowdsourced data collected from social platforms and probing vehicle traces that can effectively characterize both the dynamics and the uncertainty of road conditions. Our model is efficient and thus facilitates real-time adaptive routing in the face of uncertainty. Using this congestion model, we develop efficient algorithms for non-myopic adaptive routing to minimize the collective travel time of all vehicles in the entire transportation system. A key property of our approach is the ability to efficiently reason about the long-term value of exploration, which enables collectively balancing the exploration/exploitation trade-off for entire fleets of vehicles. Our approach is validated by real-life traffic and geo-tagged social network data from two large cities. Our congestion model is shown to be effective in modeling dynamic congestion conditions. Our routing algorithms also generate significantly faster routes compared to standard baselines, and approximate optimal performance compared to an omniscient routing algorithm. We also present the results from a preliminary field study, which showcases the efficacy of our approach.

UR - http://www.scopus.com/inward/record.url?scp=84984605203&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84984605203&partnerID=8YFLogxK

U2 - 10.1016/j.trb.2016.08.005

DO - 10.1016/j.trb.2016.08.005

M3 - Article

AN - SCOPUS:84984605203

VL - 93

SP - 450

EP - 469

JO - Transportation Research, Series B: Methodological

JF - Transportation Research, Series B: Methodological

SN - 0191-2615

ER -