Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Traffic Signal Cycle Control with Centralized Critic and Decentralized Actors under Varying Intervention Frequencies

Maonan Wang, Yirong Chen, Yuheng Kan, Chengcheng Xu, Michael Lepech, Man-On Pun, Xi Xiong

TL;DR

An innovative joint phase traffic signal cycle control method that operates effectively with varying control intervals, enabling simultaneous phase changes within the signal cycle, which fosters both immediate stability and sustained TSC effectiveness, especially at lower frequencies.

Abstract

Traffic congestion in urban areas is a significant problem, leading to prolonged travel times, reduced efficiency, and increased environmental concerns. Effective traffic signal control (TSC) is a key strategy for reducing congestion. Unlike most TSC systems that rely on high-frequency control, this study introduces an innovative joint phase traffic signal cycle control method that operates effectively with varying control intervals. Our method features an adjust all phases action design, enabling simultaneous phase changes within the signal cycle, which fosters both immediate stability and sustained TSC effectiveness, especially at lower frequencies. The approach also integrates decentralized actors to handle the complexity of the action space, with a centralized critic to ensure coordinated phase adjusting. Extensive testing on both synthetic and real-world data across different intersection types and signal setups shows that our method significantly outperforms other popular techniques, particularly at high control intervals. Case studies of policies derived from traffic data further illustrate the robustness and reliability of our proposed method.

Traffic Signal Cycle Control with Centralized Critic and Decentralized Actors under Varying Intervention Frequencies

TL;DR

An innovative joint phase traffic signal cycle control method that operates effectively with varying control intervals, enabling simultaneous phase changes within the signal cycle, which fosters both immediate stability and sustained TSC effectiveness, especially at lower frequencies.

Abstract

Traffic congestion in urban areas is a significant problem, leading to prolonged travel times, reduced efficiency, and increased environmental concerns. Effective traffic signal control (TSC) is a key strategy for reducing congestion. Unlike most TSC systems that rely on high-frequency control, this study introduces an innovative joint phase traffic signal cycle control method that operates effectively with varying control intervals. Our method features an adjust all phases action design, enabling simultaneous phase changes within the signal cycle, which fosters both immediate stability and sustained TSC effectiveness, especially at lower frequencies. The approach also integrates decentralized actors to handle the complexity of the action space, with a centralized critic to ensure coordinated phase adjusting. Extensive testing on both synthetic and real-world data across different intersection types and signal setups shows that our method significantly outperforms other popular techniques, particularly at high control intervals. Case studies of policies derived from traffic data further illustrate the robustness and reliability of our proposed method.
Paper Structure (29 sections, 18 equations, 17 figures, 8 tables, 1 algorithm)

This paper contains 29 sections, 18 equations, 17 figures, 8 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related work
  3. Conventional Traffic Signal Control
  4. RL-based Traffic Signal Control
  5. Preliminaries
  6. Traffic Movement, Signal Phase, and Cycle
  7. Intervention frequency in TSC
  8. Methodology
  9. Framework for Joint Phase Control
  10. Agent Configuration for Phase Adjustment
  11. CCDA Framework for Traffic Signal Optimization
  12. Centralized vs. Decentralized Actors
  13. Policy Optimization for Decentralized Actors
  14. Centralized Critic for Cooperative Traffic Phase Management
  15. Model Structure for AAP (CCDA)
  16. ...and 14 more sections

Figures (17)

  • Figure 1: Four commonly used action designs in the RL-based TSC problem. (a) Choose next phase. (b) Next or not. (c) Set current phase duration. (d) Adjust single phase.
  • Figure 2: A standard 4-way intersection with its movements, phases, and cycle. (a) Topology of the intersection; (b) Relationship between the four traffic phases and the cycle.
  • Figure 3: An example of applying the intervention frequency based on cycle-based control action design in a four-phase traffic signal system.
  • Figure 4: The framework of AAP (CCDA) with the intervention frequency.
  • Figure 5: An example of adjust all phases in a four phases traffic signal system.
  • ...and 12 more figures