01126645

Component

https://doi.org/10.3141/2128-22

http://scholar.google.com....+Li&publication_year=2009

Several protection algorithms strive to reduce the number of vehicles trapped in the dilemma zone. These algorithms use some arbitrary policies such as terminating the green when only one vehicle is present in the dilemma zone and the dilemma zone has not cleared after a certain period of time. The research proposes a control agent that is able to develop and adapt an optimal policy by learning from the environment. The agent incorporates a Markovian traffic state estimation into its learning process. A novel approach is presented for controlling traffic signals so that the number of vehicles trapped in the dilemma zone is reduced in an optimal fashion according to changes in traffic states. A comparison between the proposed optimal policy and the emerging detection-control system two-stage policy was conducted, and it was found that the policy based on reinforcement learning reduced the number of vehicles caught in the dilemma zone by up to 32%.

01147490

09-3734

English

pp 217-225

2009

Transportation Research Record: Journal of the Transportation Research Board

9780309142601

Print

Figures (10) ; References (19) ; Tables (1)

Dilemma zone; Green interval (Traffic signal cycle); Highway traffic control; Markov processes; Traffic estimation; Traffic signal control systems

Detection control system; Reinforcement learning

Highways; Operations and Traffic Management; I73: Traffic Control

TRIS, TRB, ATRI

Jan 30 2009 8:09PM

• Active and Passive Bus Priority Strategies in Mixed Traffic Arterials Controlled by SCOOT Adaptive Signal System: Assessment of Performance in Fortaleza, Brazil
• Assessment of Traffic Signal Maintenance and Operations Needs at Virginia Department of Transportation
• Bicyclist Intersection Crossing Times: Quantitative Measurements for Selecting Signal Timing (With Discussion and Closure)
• Comparison of Before–After Versus Off–On Adaptive Traffic Control Evaluations: Park City, Utah, Case Study
• Cycle-Length Performance Measures: Revisiting and Extending Fundamentals
• Determination of Significant Critical Movements to Generate Traffic Scenarios for Large Arterial Networks
• Distributed Ethernet Network of Advanced Pedestrian Signals
• Evaluation of Integrated Platoon-Priority and Advance Warning Flasher System at High-Speed Intersections
• Guidelines for Multicriterion Decision-Based Left-Turn Signal Control
• Local Synchronization Control Scheme for Congested Interchange Areas in Freeway Corridor
• Long Green Times and Cycles at Congested Traffic Signals
• Lost Time and Cycle Length for Actuated Traffic Signal
• Microscopic Modeling of Traffic Signal Operations: Comparative Evaluation of Hardware-in-the-Loop and Software-in-the-Loop Simulations
• Optimization of Coordinated–Actuated Traffic Signal System: Stochastic Optimization Method Based on Shuffled Frog-Leaping Algorithm
• Optimizing Signal Timings from the Field: VISGAOST and VISSIM-ASC/3 Software-in-the-Loop Simulation
• Optimizing Traffic Control to Reduce Fuel Consumption and Vehicular Emissions: Integrated Approach with VISSIM, CMEM, and VISGAOST
• Performance Measures for Railroad-Preempted Intersections
• Prediction of Red Light Running Based on Statistics of Discrete Point Sensors
• Proposed Concept for Specifying Vehicle Detection Performance
• Recommended Tolerances for Magnetometer Orientation and Field Calibration Procedure
• Safety Evaluation for Intergreen Intervals at Signalized Intersections Based on Probabilistic Method
• Three-Dimensional Mapping of Inductive Loop Detector Sensitivity with Field Measurement