Abstract

Modern traffic lights use information from induction loops and to some extend radar information. Recent developments in radar technology has made it possible to obtain more detailed information relevant to the control mechanism of the traffic light. Unfortunately much of the current controllers do not profit from this additional information. Using this information could minimize waiting times and energy waste.
Uppaal Stratego is a tool that combines machine learning and model checking techniques to synthesize near optimal control strategies. The tool has been applied successfully to several case studies e.g. battery optimization in satellites, safe and optimal cruise control and optimal floor heating controlling.
In this work we use Uppaal Stratego as an on-line controller for a signalised intersection. Our controller reads the current data from the radar sensors and effectively uses it to learn a near optimal controller at each control step. Our experiments report considerable reduction in the waiting times.
Original languageEnglish
Title of host publication12th ITS European Congress : Strasbourg, France, 19-22 June 2017
Number of pages10
PublisherERTICO - ITS Europe
Publication date2017
Article numberSP0878
Publication statusPublished - 2017
Event12th ITS European Congress: ITS Beyond Borders - Strasbourg, France
Duration: 19 Jun 201722 Jun 2017
Conference number: 12

Conference

Conference12th ITS European Congress
Number12
CountryFrance
CityStrasbourg
Period19/06/201722/06/2017

Fingerprint

Telecommunication traffic
Controllers
Radar
Cruise control
Information use
Model checking
Learning systems
Profitability
Satellites
Heating
Sensors
Experiments

Keywords

  • Traffic lights
  • Model checking
  • Machine learning
  • Optimization

Cite this

Eriksen, A. B., Huang, C., Kildebogaard, J., Lahrmann, H. S., Larsen, K. G., Muniz, M., & Taankvist, J. H. (2017). Uppaal Stratego for Intelligent Traffic Lights. In 12th ITS European Congress: Strasbourg, France, 19-22 June 2017 [SP0878] ERTICO - ITS Europe.
Eriksen, Andreas Berre ; Huang, Chao ; Kildebogaard, Jan ; Lahrmann, Harry Spaabæk ; Larsen, Kim Guldstrand ; Muniz, Marco ; Taankvist, Jakob Haahr. / Uppaal Stratego for Intelligent Traffic Lights. 12th ITS European Congress: Strasbourg, France, 19-22 June 2017. ERTICO - ITS Europe, 2017.
@inproceedings{c2593a261742420f9a163890be3d8fb7,
title = "Uppaal Stratego for Intelligent Traffic Lights",
abstract = "Modern traffic lights use information from induction loops and to some extend radar information. Recent developments in radar technology has made it possible to obtain more detailed information relevant to the control mechanism of the traffic light. Unfortunately much of the current controllers do not profit from this additional information. Using this information could minimize waiting times and energy waste.Uppaal Stratego is a tool that combines machine learning and model checking techniques to synthesize near optimal control strategies. The tool has been applied successfully to several case studies e.g. battery optimization in satellites, safe and optimal cruise control and optimal floor heating controlling.In this work we use Uppaal Stratego as an on-line controller for a signalised intersection. Our controller reads the current data from the radar sensors and effectively uses it to learn a near optimal controller at each control step. Our experiments report considerable reduction in the waiting times.",
keywords = "Traffic lights, Model checking, Machine learning, Optimization, Traffic lights, Model checking, Machine learning, Optimization",
author = "Eriksen, {Andreas Berre} and Chao Huang and Jan Kildebogaard and Lahrmann, {Harry Spaab{\ae}k} and Larsen, {Kim Guldstrand} and Marco Muniz and Taankvist, {Jakob Haahr}",
year = "2017",
language = "English",
booktitle = "12th ITS European Congress",
publisher = "ERTICO - ITS Europe",

}

Eriksen, AB, Huang, C, Kildebogaard, J, Lahrmann, HS, Larsen, KG, Muniz, M & Taankvist, JH 2017, Uppaal Stratego for Intelligent Traffic Lights. in 12th ITS European Congress: Strasbourg, France, 19-22 June 2017., SP0878, ERTICO - ITS Europe, 12th ITS European Congress, Strasbourg, France, 19/06/2017.

Uppaal Stratego for Intelligent Traffic Lights. / Eriksen, Andreas Berre; Huang, Chao; Kildebogaard, Jan; Lahrmann, Harry Spaabæk; Larsen, Kim Guldstrand; Muniz, Marco; Taankvist, Jakob Haahr.

12th ITS European Congress: Strasbourg, France, 19-22 June 2017. ERTICO - ITS Europe, 2017. SP0878.

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - Uppaal Stratego for Intelligent Traffic Lights

AU - Eriksen, Andreas Berre

AU - Huang, Chao

AU - Kildebogaard, Jan

AU - Lahrmann, Harry Spaabæk

AU - Larsen, Kim Guldstrand

AU - Muniz, Marco

AU - Taankvist, Jakob Haahr

PY - 2017

Y1 - 2017

N2 - Modern traffic lights use information from induction loops and to some extend radar information. Recent developments in radar technology has made it possible to obtain more detailed information relevant to the control mechanism of the traffic light. Unfortunately much of the current controllers do not profit from this additional information. Using this information could minimize waiting times and energy waste.Uppaal Stratego is a tool that combines machine learning and model checking techniques to synthesize near optimal control strategies. The tool has been applied successfully to several case studies e.g. battery optimization in satellites, safe and optimal cruise control and optimal floor heating controlling.In this work we use Uppaal Stratego as an on-line controller for a signalised intersection. Our controller reads the current data from the radar sensors and effectively uses it to learn a near optimal controller at each control step. Our experiments report considerable reduction in the waiting times.

AB - Modern traffic lights use information from induction loops and to some extend radar information. Recent developments in radar technology has made it possible to obtain more detailed information relevant to the control mechanism of the traffic light. Unfortunately much of the current controllers do not profit from this additional information. Using this information could minimize waiting times and energy waste.Uppaal Stratego is a tool that combines machine learning and model checking techniques to synthesize near optimal control strategies. The tool has been applied successfully to several case studies e.g. battery optimization in satellites, safe and optimal cruise control and optimal floor heating controlling.In this work we use Uppaal Stratego as an on-line controller for a signalised intersection. Our controller reads the current data from the radar sensors and effectively uses it to learn a near optimal controller at each control step. Our experiments report considerable reduction in the waiting times.

KW - Traffic lights

KW - Model checking

KW - Machine learning

KW - Optimization

KW - Traffic lights

KW - Model checking

KW - Machine learning

KW - Optimization

M3 - Article in proceeding

BT - 12th ITS European Congress

PB - ERTICO - ITS Europe

ER -

Eriksen AB, Huang C, Kildebogaard J, Lahrmann HS, Larsen KG, Muniz M et al. Uppaal Stratego for Intelligent Traffic Lights. In 12th ITS European Congress: Strasbourg, France, 19-22 June 2017. ERTICO - ITS Europe. 2017. SP0878