scholarly journals Adaptive Optimization of Traffic Signal Timing via Deep Reinforcement Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Zibo Ma ◽  
Tongchao Cui ◽  
Wenxing Deng ◽  
Fengyao Jiang ◽  
Liguo Zhang
Keyword(s):  
Reinforcement Learning ◽  
Traffic Flow ◽  
Rapid Development ◽  
Flow State ◽  
Traffic Light ◽  
Adaptive Optimization ◽  
State Action ◽  
Traffic Lights ◽  
Traffic Signal Timing ◽  
Policy Optimization

With rapid development of the urbanization, how to improve the traffic lights efficiency has become an urgent issue. The traditional traffic light control is a method that calculates a series of corresponding timing parameters by optimizing the cycle length. However, fixing sequence and duration of traffic lights is inefficient for dynamic traffic flow regulation. In order to solve the above problem, this study proposes a traffic light timing optimization scheme based on deep reinforcement learning (DRL). In this scheme, the traffic lights can output an appropriate phase according to the traffic flow state of each direction at the intersection and dynamically adjust the phase length. Specifically, we first adopt Proximal Policy Optimization (PPO) to improve the convergence speed of the model. Then, we elaborate the design of state, action, and reward, with the vehicle state defined by Discrete Traffic State Encoding (DTSE) method. Finally, we conduct experiments on real traffic data via the traffic simulation platform SUMO. The results show that, compared to the traditional timing control, the proposed scheme can effectively reduce the waiting time of vehicles and queue length in various traffic flow modes.

scholarly journals Characteristics of Traffic Flows at Kuda Mati non-traffic light Intersection in Workhour and Holidays

2018 ◽  
Vol 73 ◽  
pp. 08030
Author(s):  
F. Betaubun Herbin
Keyword(s):  
Traffic Flow ◽  
Movement Pattern ◽  
Survey Method ◽  
Traffic Flows ◽  
Traffic Light ◽  
City Center ◽  
Work Time ◽  
Traffic Lights ◽  
Economic Support ◽  
The City

Characteristics of traffic flow needs to be revealed to describe the traffic flow that occurred at the research location. One of the patterns of traffic flow movement of Merauke Regency that is important enough to be observed is the movement pattern that occurs at Kuda Mati Non-traffic lights Intersection. This intersection is one of the access for economic support of Merauke Regency. The intersection connects the city center to the production centers and is used by the community to perform activities in meeting their needs such as working and meeting the needs of clothing, food and shelter. This fulfillment activity is usually differentiated according to work time and holiday time. The method used is survey method to describe the characteristics of traffic flow at the intersection. Data analysis applied MKJI 1997. The results show that peak hour traffic flow occurs at 17.00 - 18.00 on holiday 803 smp / hour, while for working time the traffic flow is evenly distributed with maximum vehicle volume occur at 12:00 to 13:00 which amounted to 471 smp / hour.

scholarly journals Optimization of Traffic Flow On KS Tubun Street using Greenberg Model

2019 ◽  
Vol 8 (2S7) ◽  
pp. 83-86
Keyword(s):  
Traffic Flow ◽  
Red Light ◽  
Green Light ◽  
Light Cycle ◽  
Traffic Light ◽  
Traffic Jam ◽  
Traffic Lights ◽  
The Road ◽  
Road Users ◽  
Time Parameters

KS Tubun Street is a street in Bogor, which has a fairly high vehicle volume and become one of a high-traffic jam area. This is caused by KS Tubun Street is the main road for road users from Jakarta and Bogor. Traffic jam problem that occurs due to the confluence interchange of traffic flow and traffic lights settings that are not proportional to the volume of vehicles across the road. Optimization of traffic flow at KS Tubun Street performed by the stages of forming a model of traffic flow, determining the density and velocity of the vehicle is based on the Greenberg model, and determining the length of the traffic lights to avoid a buildup of vehicles. The result is a traffic flow model with distance and time parameters. The density of vehicles that occurs on the streets of KS. Tubun street based on the Greenberg model between 180 to 240 unit car of passanger (ucp) with the average velocity of vehicles 15 to 19.5 km per hour. The density of vehicles on KS. Tubun street can be break down by increasing time. Traffic light cycle time can be reduced for 8 seconds with the red light glowing time is 80 seconds and the green light glowing time is 62 seconds.

Proposed Traffic Light Control Mechanism Based on Multi-Agent Coordination

2016 ◽  
Vol 20 (5) ◽  
pp. 803-812
Author(s):  
Satoshi Kurihara ◽  
◽  
Ryo Ogawa ◽  
Kosuke Shinoda ◽  
Hirohiko Suwa ◽  
...  
Keyword(s):  
Traffic Flow ◽  
Urban Areas ◽  
Transport Systems ◽  
Light Control ◽  
Traffic Light ◽  
Agent Based ◽  
Traffic Lights ◽  
Control Framework ◽  
Traffic Light Control ◽  
Multi Agent

Traffic congestion is a serious problem for people living in urban areas, causing social problems such as time loss, economical loss, and environmental pollution. Therefore, we propose a multi-agent-based traffic light control framework for intelligent transport systems. Achieving consistent traffic flow necessitates the real-time adaptive coordination of traffic lights; however, many conventional approaches are of the centralized control type and do not have this feature. Our multi-agent-based control framework combines both indirect and direct coordination. Reaction to dynamic traffic flow is attained by indirect coordination, whereas green-wave formation, which is a systematic traffic flow control strategy involving several traffic lights, is attained by direct coordination. We present the detailed mechanism of our framework and verify its effectiveness using simulation to carry out a comparative evaluation.

scholarly journals Metaheuristic Techniques in Optimizing Traffic Control Lights: A Systematic Review

2020 ◽  
Vol 14 ◽  
Keyword(s):  
Systematic Review ◽  
Traffic Control ◽  
Traffic Congestion ◽  
Traffic Monitoring ◽  
Optimization Techniques ◽  
Traffic Light ◽  
Traffic Lights ◽  
The Road ◽  
Traffic Signal Timing ◽  
Metaheuristic Techniques

Traffic congestion is a serious problem on every roadway and streets in many cities around the world. This systematic review is devoted to analyze research papers that deal with the optimization of traffic signal timing. The main objective of such optimization is maximizing the number of the vehicles leaving the network in a given period of time. This will lead to enhancing the performance of the road system. In this work, we researched the most recent metaheuristic optimized traffic light control techniques. It was shown that integrating optimization techniques in the field of traffic lights control had a great impact on the performance of traffic monitoring. During our research, we found that the most used method was the Genetic Algorithm (GA).

scholarly journals Device and Algorithm for Vehicle Detection and Traffic Intensity Analysis

2021 ◽  
Vol 17 (1) ◽  
pp. 83-92
Author(s):  
Mikhail Gorobetz ◽  
Andrey Potapov ◽  
Aleksandr Korneyev ◽  
Ivars Alps
Keyword(s):  
Traffic Flow ◽  
Internal Combustion Engines ◽  
Radio Channel ◽  
Vehicle Detection ◽  
Detection Methods ◽  
Traffic Intensity ◽  
Traffic Light ◽  
Traffic Lights ◽  
Advantages And Disadvantages ◽  
Sensor Module

Abstract To effectively manage the traffic flow in order to reduce traffic congestion, it is necessary to know the volumes and quantitative indicators of this flow. Various detection methods are known for detecting a vehicle in a lane, which, in turn, have their own advantages and disadvantages. To detect vehicles and analyse traffic intensity, the authors use a pulse coherent radar (PCR) sensor module. Testing of various modes of operation of the radar sensor was carried out to select the optimal mode for detecting vehicles. The paper describes a method for fixing vehicles of different sizes, filtering and separating the vehicle from the traffic flow. The developed vehicle detection device works in conjunction with signal traffic lights, through which traffic control takes place. The signal traffic lights, which have their own sensors and control units, communicate with each other via a radio channel; there is no need for cable laying. The system is designed to work on road maintenance sites. The paper describes the experimental data when testing on a separate section of the road. The experiment showed the advantage of traffic lights (cars passed the regulated traffic light faster) from the point of view of calculating the traffic flow over the normal traffic light operation. Reducing downtime in traffic jams, in turn, has a beneficial effect on the environmental situation, since at the moment internal combustion engines prevail in vehicles.

scholarly journals Extending the learning and communicating shout-ahead architecture with user-defined exception rules -- a case study for traffic light controls

2021 ◽  
Vol 2 (1) ◽  
pp. 46-67
Author(s):  
Christian Roatis ◽  
Jorg Denzinger
Keyword(s):  
Traffic Flow ◽  
Hybrid Learning ◽  
Learning Approach ◽  
Application Area ◽  
Agent Architecture ◽  
Traffic Light ◽  
Traffic Lights ◽  
Learning Time

We present an extension of the shout-ahead agent architecture that allows for adding human user-defined exception rules to the rules created by the hybrid learning approach for this architecture. The user-defined rules can be added after learning as reaction to weaknesses of the learned rules or learning can be performed with the user-defined rules already in place. We applied the extended shout-ahead architecture and the associated learning to a new application area, cooperating controllers for the traffic lights of intersections. In our experimental evaluations, adding user-defined exception rules to the learned rules for several traffic flow instances increased the efficiency of the resulting controllers substantially compared to just using the learned rules. Performing learning with user-defined exception rules already in place decreased the learning time substantially for all flows, but had mixed results with respect to efficiency. We also evaluated user-defined exception rules for a variant of the architecture that is not using communication and saw similar effects as for the variant with communication. For the communicating version, both variants of adding user-defined exception rules create controllers that are much more flexible than what using the original shout-ahead architecture with its learning is able to create as indicated by experiments with variations of flows.

scholarly journals Recent development of smart traffic lights

2021 ◽  
Vol 10 (1) ◽  
pp. 224
Author(s):  
A’isya Nur Aulia Yusuf ◽  
Ajib Setyo Arifin ◽  
Fitri Yuli Zulkifli
Keyword(s):  
Traffic Flow ◽  
Time Allocation ◽  
Traffic Density ◽  
Light Cycle ◽  
Traffic Light ◽  
Large Cities ◽  
Traffic Lights ◽  
Smart Traffic ◽  
Very High ◽  
Signal Time

<span id="docs-internal-guid-288f4dcc-7fff-1e8c-0350-5032593b6e4f"><span>Increased traffic flow causes congestion, especially in large cities. Even though congestion is not unusual, traffic jams still result in very high economic and social losses. Several factors cause congestion, one of which is traffic lights. Therefore, a mechanism is needed so that traffic lights can intelligently and adaptively manage signal time allocation according to traffic flow conditions. A traffic light with this type of mechanism is known as a smart traffic light. Smart traffic light cycle settings can be grouped based on the traffic density, scenarios for emergency vehicles, and the interests of pedestrians. This paper analyzes the methods and technologies used in the development of smart traffic light technology from the perspective of these three situations as well as the development of smart traffic light technology in the future.</span></span>

scholarly journals Traffic Light Optimization Based on Modified Webster Function

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Huizhen Zhang ◽  
Hongtao Yuan ◽  
Youqing Chen ◽  
Wenlong Yu ◽  
Cheng Wang ◽  
...  
Keyword(s):  
Genetic Algorithm ◽  
Road Traffic ◽  
Optimal Solution ◽  
Normal Operation ◽  
Signal Timing ◽  
Improved Genetic Algorithm ◽  
Traffic Light ◽  
Delay Function ◽  
Traffic Lights ◽  
Traffic Signal Timing

Intersection traffic lights are a basic means of ensuring the normal operation of road traffic. A good signal timing scheme is essential for improving traffic congestion. To obtain the signal timing scheme of the designated intersection, the method proposed in this article is based on a modified Webster function. The method uses the signal cycle and proportion of green light duration as independent variables to establish the corresponding intersection vehicle delay function. This function is converted from a multiobjective optimization to a single-objective optimization formulation; a modified genetic algorithm is then used to find the optimal solution to this function. The experimental results show that the timing scheme optimized by the improved genetic algorithm can reduce the intersection delay by nearly 15.64%. The proposed traffic signal timing based on the modified Webster function will be of value as an important reference for the optimization of traffic lights at urban intersections.

scholarly journals Deep Reinforcement Learning Model to Mitigate Congestion in Real-Time Traffic Light Networks

2021 ◽  
Vol 6 (10) ◽  
pp. 138
Author(s):  
Fábio de Souza Pereira Borges ◽  
Adelayda Pallavicini Fonseca ◽  
Reinaldo Crispiniano Garcia
Keyword(s):  
Reinforcement Learning ◽  
Real Time ◽  
Traffic Control ◽  
High Volume ◽  
Urban Traffic ◽  
Traffic Data ◽  
Traffic Light ◽  
Urban Network ◽  
Traffic Demand ◽  
Traffic Lights

Urban traffic congestion has a significant detrimental impact on the environment, public health and the economy, with at a high cost to society worldwide. Moreover, it is not possible to continually modify urban road infrastructure in order to mitigate increasing traffic demand. Therefore, it is important to develop traffic control models that can handle high-volume traffic data and synchronize traffic lights in an urban network in real time, without interfering with other initiatives. Within this context, this study proposes a model, based on deep reinforcement learning, for synchronizing the traffic signals of an urban traffic network composed of two intersections. The calibration of this model, including training of its neural network, was performed using real traffic data collected at the approach to each intersection. The results achieved through simulations were very promising, yielding significant improvements in indicators measured in relation to the pre-existing conditions in the network. The model was able to deal with a broad spectrum of traffic flows and, in peak demand periods, reduced delays and queue lengths by more than 28% and 42%, respectively.

scholarly journals Testing an Adaptive Cruise Controller with coupled traffic and driving simulations

10.29007/84rc ◽  
2019 ◽  
Author(s):  
Mirko Barthauer ◽  
Alexander Hafner
Keyword(s):  
Traffic Flow ◽  
Driving Simulator ◽  
Traffic Simulation ◽  
Traffic Signals ◽  
Simulation Environment ◽  
Cruise Control ◽  
Traffic Light ◽  
Traffic Lights ◽  
Subjective Judgement ◽  
Traffic Simulations

In many cases, driving simulator studies target how test persons interact with surround- ing traffic and with traffic signals. Traffic simulations like SUMO specialize in modeling traffic flow, which includes signal control. Consequently, driving and traffic simulation are coupled to benefit from the advantages of both. This means that all except the driven (ego) vehicle are controlled by the traffic simulation. Essential vehicle dynamics data are exchanged and applied frequently to make the test person interact with SUMO-generated traffic. Additionally, traffic lights are controlled by SUMO and transferred to the driving simulation. The system is used to evaluate an Adaptive Cruise Control (ACC) system, which considers current and future traffic light states. Measures include objective terms like traffic flow as well as the subjective judgement of the signal program, the ACC and the simulation environment.

Sign in / Sign up

Export Citation Format

Share Document