Hierarchical multi-agent control of traffic lights based on collective learning

Jin, Junchen; Ma, Xiaoliang

doi:10.1016/j.engappai.2017.10.013

Cited by 58 publications

(21 citation statements)

References 24 publications

(40 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To verify the capability of the proposed method, it is needed to simulate the network with different arrival rates. Henceforth, the designed traffic network has been simulated with adaptive control method (method 1), presented by Maa et al (2016) [14], multi-agent based method (method 2) presented by Jin and Maa (2018) [30] and the proposed method. By varying the arrival rates, the average delay is computed for each simulation.…”

Section: B Results Discussionmentioning

confidence: 99%

Multi-Agent Based Traffic Signal Optimization under Fully Actuated Control

Rani¹,

Shaw²

2019

IJITEE

View full text Add to dashboard Cite

This paper presents a multi-agent based distributed traffic control model to optimize the traffic signal for multiple intersections. Previous works in the area of traffic signal control suffer from a number of inadequacies, including the use of fixed cycle length, centralized mode of operations and dependency on historical data. Considering these, the aim of this work is to control the traffic signal timings by adjusting the phase sequence in order to minimize the delay in traffic at the intersections. To model the traffic network, a three-tier multi-agent system has been adopted in distributed mode. In addition, a fully actuated signal control algorithm is designed and it utilizes state-space equations to formulate the queue length at the green light phase and red light phase. The proposed model is simulated with SUMO simulator and a comparative analysis has been made between adaptive control method, multi-agent method based on collective learning and multi-agent based fully actuated control method on a similar platform. The results spectacle the proposed traffic control model outperforms that of other existing control methods in all condition; hence it can be deployed to control the tremendous traffic on the road network and to optimize the traffic signal in more effective manner.

show abstract

Section: B Results Discussionmentioning

confidence: 99%

Multi-Agent Based Traffic Signal Optimization under Fully Actuated Control

Rani¹,

Shaw²

2019

IJITEE

View full text Add to dashboard Cite

show abstract

“…(2) from f 1 and the pressure from f 2 . The pressure generated from vehicle flow f 1 is associated with the cooperative phases cp 11 and cp 12 . If cp 11 or cp 12 are activated, vehicles on segment b 1 can drive into segments c 11 or c 12 .…”

Section: Cooperative Light Phase Switching Decisionmentioning

confidence: 99%

“…In this case, the number of vehicles departing from segment b 1 should be considered. If cp 11 and cp 12 are not to be activated or the DownstreamIntersection 1 does not exist, the number of vehicles departing from segment b 1 is zero. Similarly, the computation of pressure generated from vehicle flow f 2 should consider the downstream phase states cp 21 or cp 22 .…”

Section: Cooperative Light Phase Switching Decisionmentioning

confidence: 99%

“…Researchers have utilized intelligent computation methods to obtain the cycle length and splits by minimizing traffic parameters, such as total travel time, etc. These types of methods avoid huge computations, such as the colony optimization approach [10] and reinforcement learning algorithm [11]. However, it is still difficult for these types of traffic control methods to achieve online traffic timing decision making, since the traffic signal timing problem usually is NP hard, it may take long time to find an optimal solution for simple transportation systems [12,13].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Distributed Cooperative Backpressure-Based Traffic Light Control Method

Hao

Yang

Ding

et al. 2019

Journal of Advanced Transportation

View full text Add to dashboard Cite

On the foundation of the original backpressure-based traffic light control algorithm, a distributed cooperative backpressure-based traffic light control method is proposed in this paper. The urban traffic network is modeled as a smart agent-controlled queuing network, in which the intersection agents exchange the queue length information and the selected activating light phase information of neighboring intersections through communications and determine the activating light phase at each time slot according to local traffic information. The improved phase pressure computation method considers the phase state of downstream intersections instead of only the queue length of the local intersections. Light phase switching coordination among adjacent intersections is achieved using the consensus-based bundle algorithm, in which the cooperative light phase switching problem is viewed as a task assignment issue among adjacent intersections. Simulation results illustrated that the proposed cooperative backpressurebased traffic light control method obtained better performance than the original backpressure-based and fixed-time traffic control methods.

show abstract

“…State-of-the-art traffic control algorithms [4,5] are based on centralized techniques. The centralized traffic control approaches are computationally complex and inherently non-scalable.…”

Section: Introductionmentioning

confidence: 99%

A Neuroevolutionary Approach to Controlling Traffic Signals Based on Data from Sensor Network

Bernaś

Płaczek

Smyła

2019

Sensors

View full text Add to dashboard Cite

The paper introduces an artificial neural network ensemble for decentralized control of traffic signals based on data from sensor network. According to the decentralized approach, traffic signals at each intersection are controlled independently using real-time data obtained from sensor nodes installed along traffic lanes. In the proposed ensemble, a neural network, which reflects design of signalized intersection, is combined with fully connected neural networks to enable evaluation of signal group priorities. Based on the evaluated priorities, control decisions are taken about switching traffic signals. A neuroevolution strategy is used to optimize configuration of the introduced neural network ensemble. The proposed solution was compared against state-of-the-art decentralized traffic control algorithms during extensive simulation experiments. The experiments confirmed that the proposed solution provides better results in terms of reduced vehicle delay, shorter travel time, and increased average velocity of vehicles.

show abstract

Hierarchical multi-agent control of traffic lights based on collective learning

Abstract: This is the accepted version of a paper published in Engineering applications of artificial intelligence. This paper has been peer-reviewed but does not include the final publisher proof-corrections or journal pagination.

Cited by 58 publications

References 24 publications

Multi-Agent Based Traffic Signal Optimization under Fully Actuated Control

Multi-Agent Based Traffic Signal Optimization under Fully Actuated Control

Distributed Cooperative Backpressure-Based Traffic Light Control Method

A Neuroevolutionary Approach to Controlling Traffic Signals Based on Data from Sensor Network

Contact Info

Product

Resources

About