scholarly journals Double Deep Q-Network with a Dual-Agent for Traffic Signal Control

2020 ◽  
Vol 10 (5) ◽  
pp. 1622 ◽  
Author(s):  
Jianfeng Gu ◽  
Yong Fang ◽  
Zhichao Sheng ◽  
Peng Wen
Keyword(s):  
Traffic Control ◽  
Traffic Congestion ◽  
Control Process ◽  
Stable State ◽  
Control Policy ◽  
Traffic Signal ◽  
Signalized Intersection ◽  
Signal Control ◽  
Traffic Signal Control ◽  
Two Agents

Adaptive traffic signal control (ATSC) based on deep reinforcement learning (DRL) has shown promising prospects to reduce traffic congestion. Most existing methods keeping traffic signal phases fixed adopt two agent actions to match a four-phase suffering unstable performance and undesirable operation in a four-phase signalized intersection. In this paper, a Double Deep Q-Network (DDQN) with a dual-agent algorithm is proposed to obtain a stable traffic signal control policy. Specifically, two agents are denoted by two different states and shift the control of green lights to make the phase sequence fixed and control process stable. State representations and reward functions are presented by improving the observability and reducing the leaning difficulty of two agents. To enhance the feasibility and reliability of two agents in the traffic control of the four-phase signalized intersection, a network structure incorporating DDQN is proposed to map states to rewards. Experiments under Simulation of Urban Mobility (SUMO) are carried out, and results show that the proposed traffic signal control algorithm is effective in improving traffic capacity.

scholarly journals Investigating the Applicability of Upstream Detection Strategy at Pedestrian Signalised Crossings

2017 ◽  
Vol 29 (5) ◽  
pp. 503-510 ◽  
Author(s):  
Sitti A Hassan ◽  
Nick B Hounsell ◽  
Birendra P Shrestha
Keyword(s):  
Traffic Control ◽  
Traffic Signal ◽  
Signal Control ◽  
Traffic Signal Control ◽  
Traffic Flows ◽  
Detection Strategy ◽  
Vehicle Delay ◽  
Simulation Results ◽  
The Uk ◽  
User Friendly

In the UK, the Puffin crossing has provision to extend pedestrian green time for those who take longer to cross. However, even at such a pedestrian friendly facility, the traffic signal control is usually designed to minimise vehicle delay while providing the crossing facility. This situation is rather contrary to the current policies to encourage walking. It is this inequity that has prompted the need to re-examine the traffic control of signalised crossings to provide more benefit to both pedestrians and vehicles. In this context, this paper explores the possibility of implementing an Upstream Detection strategy at a Puffin crossing to provide a user friendly crossing. The study has been carried out by simulating a mid-block Puffin crossing for various detector distances and a number of combinations of pedestrian and traffic flows. This paper presents the simulation results and recommends the situations at which Upstream Detection would be suitable.

scholarly journals Software-defined Architecture for Urban Regional Traffic Signal Control

2020 ◽  
Vol 32 (2) ◽  
pp. 229-236
Author(s):  
Songhang Chen ◽  
Dan Zhang ◽  
Fenghua Zhu
Keyword(s):  
Traffic Congestion ◽  
Traffic Signal ◽  
Urban Traffic ◽  
Signal Control ◽  
Traffic Signal Control ◽  
The Novel ◽  
Simulation Experiments ◽  
Microscopic Traffic Simulation ◽  
Control Devices ◽  
Innovation Platform

Regional Traffic Signal Control (RTSC) is believed to be a promising approach to alleviate urban traffic congestion. However, the current ecology of RTSC platforms is too closed to meet the needs of urban development, which has also seriously affected their own development. Therefore, the paper proposes virtualizing the traffic signal control devices to create software-defined RTSC systems, which can provide a better innovation platform for coordinated control of urban transportation. The novel architecture for RTSC is presented in detail, and microscopic traffic simulation experiments are designed and conducted to verify the feasibility.

Analysis of Trends in Data on Transit Bus Dwell Times

2017 ◽  
Vol 2619 (1) ◽  
pp. 64-74 ◽  
Author(s):  
Isaac K. Isukapati ◽  
Hana Rudová ◽  
Gregory J. Barlow ◽  
Stephen F. Smith
Keyword(s):  
Traffic Congestion ◽  
Urban Areas ◽  
Traffic Signal ◽  
Urban Traffic ◽  
Distribution Model ◽  
Signal Control ◽  
Traffic Signal Control ◽  
Real Time Control ◽  
Arrival Times ◽  
On The Road

Transit vehicles create special challenges for urban traffic signal control. Signal timing plans are typically designed for the flow of passenger vehicles, but transit vehicles—with frequent stops and uncertain dwell times—may have different flow patterns that fail to match those plans. Transit vehicles stopping on urban streets can also restrict or block other traffic on the road. This situation results in increased overall wait times and delays throughout the system for transit vehicles and other traffic. Transit signal priority (TSP) systems are often used to mitigate some of these issues, primarily by addressing delay to the transit vehicles. However, existing TSP strategies give unconditional priority to transit vehicles, exacerbating quality of service for other modes. In networks for which transit vehicles have significant effects on traffic congestion, particularly urban areas, the use of more-realistic models of transit behavior in adaptive traffic signal control could reduce delay for all modes. Estimating the arrival time of a transit vehicle at an intersection requires an accurate model of dwell times at transit stops. As a first step toward developing a model for predicting bus arrival times, this paper analyzes trends in automatic vehicle location data collected over 2 years and allows several inferences to be drawn about the statistical nature of dwell times, particularly for use in real-time control and TSP. On the basis of this trend analysis, the authors argue that an effective predictive dwell time distribution model must treat independent variables as random or stochastic regressors.

Developing Signal Warrants for Restricted Crossing U-Turn Intersections

2021 ◽  
pp. 036119812110469
Author(s):  
Justice Appiah
Keyword(s):  
Traffic Control ◽  
Simulation Analysis ◽  
Traffic Signals ◽  
Traffic Volume ◽  
Traffic Signal ◽  
Signal Control ◽  
Traffic Signal Control ◽  
Left Turn ◽  
Minor Road ◽  
Intersection Configuration

The restricted crossing U-turn (RCUT) intersection is a form of innovative intersection design that reroutes left-turn and through traffic from the minor road to U-turn crossovers on the major road. When implemented correctly, an RCUT intersection can provide significant safety and operational benefits over the conventional intersection configuration. The RCUT may be controlled by traffic signals, STOP control, merges and diverges, or a combination of these. There is currently no concrete guidance in relation to when the use of traffic signal control is warranted at an RCUT intersection. This study investigated traffic volume conditions that may warrant consideration of traffic signal control at an RCUT intersection. Simulation experiments including two geometric configurations and three traffic control schemes were designed and run in VISSIM to evaluate the effects of traffic conditions on intersection delay and queue lengths. Traffic was varied by changing the composition, approach volumes, and origin–destination flow patterns to reflect different conditions that may occur at the intersection on any given day. For the range of conditions studied, the results of the simulation analysis suggested that the RCUT intersection may operate better with traffic signals (at all junctions) when the minor roadway traffic volume is more than 450 vehicles per hour (vph) and the major roadway has two through lanes. The corresponding minor roadway volume threshold increases to 575 vph when the major roadway has four through lanes.

A New Design of Intelligent Traffic Signal Control

2013 ◽  
Vol 3 (3) ◽  
pp. 51-67
Author(s):  
Fatemeh Daneshfar ◽  
Javad RavanJamJah
Keyword(s):  
Knowledge Base ◽  
Traffic Control ◽  
Clustering Algorithm ◽  
Recursive Algorithm ◽  
Green Light ◽  
Traffic Signal ◽  
Signal Control ◽  
Traffic Signal Control ◽  
Fixed Sequence ◽  
Traffic Pattern

Dynamic traffic signal control in Intelligent Transportation System (ITS) recently has received increasing attention. This paper proposed an adaptive and cooperative multi-agentfuzzy system for a decentralized traffic signal control. The proposed model has three levels of control, the current intersection traffic situation, its neighboring intersections recommendations and a knowledge base, which provides the current intersection traffic pattern. The proposed architecture comprises a knowledge base, prediction module and a traffic observer that provide data to real traffic data preparation module, then a decision-making layer takes decision to how long should the intersection green light be extended. Also every intersection flow is predicted in two different ways: 1- through a recursive algorithm. 2- based on a two stage fuzzy clustering algorithm. The proposed solution is tested with traffic control of a large connected junction and the result obtained is promising in comparison to the conventional fixed sequence traffic signal and to the vehicle actuated traffic signal control strategies which are the most applicable strategies in this area. Also to simulate the proposed traffic control solutions, a Netlogo-based traffic simulator has been developed as the agents’ world which simulates the roads, traffic flow and intersections.

KNOWLEDGE BASED TRAFFIC SIGNAL CONTROL MODEL FOR SIGNALIZED INTERSECTION

Transport ◽  
2012 ◽  
Vol 27 (3) ◽  
pp. 263-267 ◽  
Author(s):  
Henrikas Pranevičius ◽  
Tadas Kraujalis
Keyword(s):  
Intelligent Transportation Systems ◽  
Control Method ◽  
Intelligent Transportation ◽  
Transportation Systems ◽  
Traffic Signal ◽  
Signalized Intersection ◽  
Signal Control ◽  
Traffic Signal Control ◽  
Signal Timing ◽  
Traffic Conditions

Intelligent transportation systems have received increasing attention in academy and industry. Being able to handle uncertainties and complexity, expert systems are applied in vast areas of real life including intelligent transportation systems. This paper presents a traffic signal control method based on expert knowledge for an isolated signalized intersection. The proposed method has the adaptive signal timing ability to adjust its signal timing in response to changing traffic conditions. Based on the traffic conditions, the system determines to extend or terminate the current green signal group. Using the information from its traffic detectors of isolated intersection, the proposed controller gives optimal signals to adapt the phase lengths to the traffic conditions. A comparative analysis between proposed control algorithm, fuzzy logic (FLC) and fixed-timed (pre-timed) controllers has been made in traffic flows control, with varying traffic volume levels, by using simulation software ‘Arena’. Simulation results show that the proposed traffic signal control method (EKC) has better performance over fuzzy logic and conventional pre-time controllers under light and heavy traffic conditions.

Sign in / Sign up

Export Citation Format

Share Document