Optimal signal control using adaptive dynamic programming

Chang Ouk Kim, Yunsun Park, Jun Geol Baek

Research output: Contribution to journalConference article

4 Citations (Scopus)

Abstract

This paper develops an adaptive, optimal planning algorithm for signal control at a single intersection using an efficient dynamic programming technique. It is called ADPAS (Adaptive Dynamic Programming Algorithm for Signaling). The objective of ADPAS is to minimize the total delay experienced by vehicles passing through an intersection. ADPAS can generate any sequence of green phases to optimize signal control without restriction to fixed cycles of green phases. The algorithm employs reaching as the method to solve the forward DP functional equation, which does not require any prior knowledge of the states of the DP network. The efficiency of the algorithm results from two acceleration techniques that adaptively eliminate inferior states as the algorithm progresses. We verify computational efficiency of ADPAS with several test cases.

Original languageEnglish
Pages (from-to)148-160
Number of pages13
JournalLecture Notes in Computer Science
Volume3483
Issue numberIV
Publication statusPublished - 2005 Sep 26

Fingerprint

Adaptive Dynamics
Signal Control
Dynamic programming
Dynamic Programming
Optimal Control
Intersection
Computational efficiency
Prior Knowledge
Computational Efficiency
Functional equation
Eliminate
Optimise
Planning
Verify
Restriction
Minimise
Cycle

All Science Journal Classification (ASJC) codes

  • Theoretical Computer Science
  • Computer Science(all)

Cite this

Kim, Chang Ouk ; Park, Yunsun ; Baek, Jun Geol. / Optimal signal control using adaptive dynamic programming. In: Lecture Notes in Computer Science. 2005 ; Vol. 3483, No. IV. pp. 148-160.
@article{ea7d1017570d49228b800d8a6ce04eff,
title = "Optimal signal control using adaptive dynamic programming",
abstract = "This paper develops an adaptive, optimal planning algorithm for signal control at a single intersection using an efficient dynamic programming technique. It is called ADPAS (Adaptive Dynamic Programming Algorithm for Signaling). The objective of ADPAS is to minimize the total delay experienced by vehicles passing through an intersection. ADPAS can generate any sequence of green phases to optimize signal control without restriction to fixed cycles of green phases. The algorithm employs reaching as the method to solve the forward DP functional equation, which does not require any prior knowledge of the states of the DP network. The efficiency of the algorithm results from two acceleration techniques that adaptively eliminate inferior states as the algorithm progresses. We verify computational efficiency of ADPAS with several test cases.",
author = "Kim, {Chang Ouk} and Yunsun Park and Baek, {Jun Geol}",
year = "2005",
month = "9",
day = "26",
language = "English",
volume = "3483",
pages = "148--160",
journal = "Lecture Notes in Computer Science",
issn = "0302-9743",
publisher = "Springer Verlag",
number = "IV",

}

Optimal signal control using adaptive dynamic programming. / Kim, Chang Ouk; Park, Yunsun; Baek, Jun Geol.

In: Lecture Notes in Computer Science, Vol. 3483, No. IV, 26.09.2005, p. 148-160.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Optimal signal control using adaptive dynamic programming

AU - Kim, Chang Ouk

AU - Park, Yunsun

AU - Baek, Jun Geol

PY - 2005/9/26

Y1 - 2005/9/26

N2 - This paper develops an adaptive, optimal planning algorithm for signal control at a single intersection using an efficient dynamic programming technique. It is called ADPAS (Adaptive Dynamic Programming Algorithm for Signaling). The objective of ADPAS is to minimize the total delay experienced by vehicles passing through an intersection. ADPAS can generate any sequence of green phases to optimize signal control without restriction to fixed cycles of green phases. The algorithm employs reaching as the method to solve the forward DP functional equation, which does not require any prior knowledge of the states of the DP network. The efficiency of the algorithm results from two acceleration techniques that adaptively eliminate inferior states as the algorithm progresses. We verify computational efficiency of ADPAS with several test cases.

AB - This paper develops an adaptive, optimal planning algorithm for signal control at a single intersection using an efficient dynamic programming technique. It is called ADPAS (Adaptive Dynamic Programming Algorithm for Signaling). The objective of ADPAS is to minimize the total delay experienced by vehicles passing through an intersection. ADPAS can generate any sequence of green phases to optimize signal control without restriction to fixed cycles of green phases. The algorithm employs reaching as the method to solve the forward DP functional equation, which does not require any prior knowledge of the states of the DP network. The efficiency of the algorithm results from two acceleration techniques that adaptively eliminate inferior states as the algorithm progresses. We verify computational efficiency of ADPAS with several test cases.

UR - http://www.scopus.com/inward/record.url?scp=24944580093&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=24944580093&partnerID=8YFLogxK

M3 - Conference article

VL - 3483

SP - 148

EP - 160

JO - Lecture Notes in Computer Science

JF - Lecture Notes in Computer Science

SN - 0302-9743

IS - IV

ER -