Efficient macroscopic urban traffic models for reducing congestion

A PDDL+ planning approach

Mauro Vallati, Daniele Magazzeni, Bart De Schutter, Lukáš Chrpa, Thomas L. McCluskey

Research output: Chapter in Book/Report/Conference proceedingConference contribution

27 Citations (Scopus)

Abstract

The global growth in urbanisation increases the demand for services including road transport infrastructure, presenting challenges in terms of mobility. In this scenario, optimising the exploitation of urban road networks is a pivotal challenge. Existing urban traffic control approaches, based on complex mathematical models, can effectively deal with planned-Ahead events, but are not able to cope with unexpected situations -such as roads blocked due to car accidents or weather-related events- because of their huge computational requirements. Therefore, such unexpected situations are mainly dealt with manually, or by exploiting pre-computed policies. Our goal is to show the feasibility of using mixed discrete-continuous planning to deal with unexpected circumstances in urban traffic control. We present a PDDL+ formulation of urban traffic control, where continuous processes are used to model flows of cars, and show how planning can be used to efficiently reduce congestion of specified roads by controlling traffic light green phases. We present simulation results on two networks (one of them considers Manchester city centre) that demonstrate the effectiveness of the approach, compared with fixed-Time and reactive techniques.

Original languageEnglish
Title of host publication30th AAAI Conference on Artificial Intelligence, AAAI 2016
PublisherAAAI press
Pages3188-3194
Number of pages7
ISBN (Electronic)9781577357605
Publication statusPublished - 2016
Event30th Association for the Advancement of Artificial Intelligence Conference - Phoenix, United States
Duration: 12 Feb 201617 Feb 2016
Conference number: 30

Conference

Conference30th Association for the Advancement of Artificial Intelligence Conference
Abbreviated titleAAAI 2016
CountryUnited States
CityPhoenix
Period12/02/1617/02/16

Fingerprint

Traffic control
Planning
Railroad cars
Accidents
Mathematical models

Cite this

Vallati, M., Magazzeni, D., Schutter, B. D., Chrpa, L., & McCluskey, T. L. (2016). Efficient macroscopic urban traffic models for reducing congestion: A PDDL+ planning approach. In 30th AAAI Conference on Artificial Intelligence, AAAI 2016 (pp. 3188-3194). AAAI press.
Vallati, Mauro ; Magazzeni, Daniele ; Schutter, Bart De ; Chrpa, Lukáš ; McCluskey, Thomas L. / Efficient macroscopic urban traffic models for reducing congestion : A PDDL+ planning approach. 30th AAAI Conference on Artificial Intelligence, AAAI 2016. AAAI press, 2016. pp. 3188-3194
@inproceedings{5712f942f2a243c99bc0636ccc237393,
title = "Efficient macroscopic urban traffic models for reducing congestion: A PDDL+ planning approach",
abstract = "The global growth in urbanisation increases the demand for services including road transport infrastructure, presenting challenges in terms of mobility. In this scenario, optimising the exploitation of urban road networks is a pivotal challenge. Existing urban traffic control approaches, based on complex mathematical models, can effectively deal with planned-Ahead events, but are not able to cope with unexpected situations -such as roads blocked due to car accidents or weather-related events- because of their huge computational requirements. Therefore, such unexpected situations are mainly dealt with manually, or by exploiting pre-computed policies. Our goal is to show the feasibility of using mixed discrete-continuous planning to deal with unexpected circumstances in urban traffic control. We present a PDDL+ formulation of urban traffic control, where continuous processes are used to model flows of cars, and show how planning can be used to efficiently reduce congestion of specified roads by controlling traffic light green phases. We present simulation results on two networks (one of them considers Manchester city centre) that demonstrate the effectiveness of the approach, compared with fixed-Time and reactive techniques.",
author = "Mauro Vallati and Daniele Magazzeni and Schutter, {Bart De} and Luk{\'a}š Chrpa and McCluskey, {Thomas L.}",
year = "2016",
language = "English",
pages = "3188--3194",
booktitle = "30th AAAI Conference on Artificial Intelligence, AAAI 2016",
publisher = "AAAI press",

}

Vallati, M, Magazzeni, D, Schutter, BD, Chrpa, L & McCluskey, TL 2016, Efficient macroscopic urban traffic models for reducing congestion: A PDDL+ planning approach. in 30th AAAI Conference on Artificial Intelligence, AAAI 2016. AAAI press, pp. 3188-3194, 30th Association for the Advancement of Artificial Intelligence Conference, Phoenix, United States, 12/02/16.

Efficient macroscopic urban traffic models for reducing congestion : A PDDL+ planning approach. / Vallati, Mauro; Magazzeni, Daniele; Schutter, Bart De; Chrpa, Lukáš; McCluskey, Thomas L.

30th AAAI Conference on Artificial Intelligence, AAAI 2016. AAAI press, 2016. p. 3188-3194.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Efficient macroscopic urban traffic models for reducing congestion

T2 - A PDDL+ planning approach

AU - Vallati, Mauro

AU - Magazzeni, Daniele

AU - Schutter, Bart De

AU - Chrpa, Lukáš

AU - McCluskey, Thomas L.

PY - 2016

Y1 - 2016

N2 - The global growth in urbanisation increases the demand for services including road transport infrastructure, presenting challenges in terms of mobility. In this scenario, optimising the exploitation of urban road networks is a pivotal challenge. Existing urban traffic control approaches, based on complex mathematical models, can effectively deal with planned-Ahead events, but are not able to cope with unexpected situations -such as roads blocked due to car accidents or weather-related events- because of their huge computational requirements. Therefore, such unexpected situations are mainly dealt with manually, or by exploiting pre-computed policies. Our goal is to show the feasibility of using mixed discrete-continuous planning to deal with unexpected circumstances in urban traffic control. We present a PDDL+ formulation of urban traffic control, where continuous processes are used to model flows of cars, and show how planning can be used to efficiently reduce congestion of specified roads by controlling traffic light green phases. We present simulation results on two networks (one of them considers Manchester city centre) that demonstrate the effectiveness of the approach, compared with fixed-Time and reactive techniques.

AB - The global growth in urbanisation increases the demand for services including road transport infrastructure, presenting challenges in terms of mobility. In this scenario, optimising the exploitation of urban road networks is a pivotal challenge. Existing urban traffic control approaches, based on complex mathematical models, can effectively deal with planned-Ahead events, but are not able to cope with unexpected situations -such as roads blocked due to car accidents or weather-related events- because of their huge computational requirements. Therefore, such unexpected situations are mainly dealt with manually, or by exploiting pre-computed policies. Our goal is to show the feasibility of using mixed discrete-continuous planning to deal with unexpected circumstances in urban traffic control. We present a PDDL+ formulation of urban traffic control, where continuous processes are used to model flows of cars, and show how planning can be used to efficiently reduce congestion of specified roads by controlling traffic light green phases. We present simulation results on two networks (one of them considers Manchester city centre) that demonstrate the effectiveness of the approach, compared with fixed-Time and reactive techniques.

UR - http://www.scopus.com/inward/record.url?scp=85007196021&partnerID=8YFLogxK

UR - https://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/view/11985

M3 - Conference contribution

SP - 3188

EP - 3194

BT - 30th AAAI Conference on Artificial Intelligence, AAAI 2016

PB - AAAI press

ER -

Vallati M, Magazzeni D, Schutter BD, Chrpa L, McCluskey TL. Efficient macroscopic urban traffic models for reducing congestion: A PDDL+ planning approach. In 30th AAAI Conference on Artificial Intelligence, AAAI 2016. AAAI press. 2016. p. 3188-3194