IntelliLight

Wei, Hua; Zheng, Guopei; Yao, Huaxiu; Li, Zhenhui

doi:10.1145/3219819.3220096

Cited by 449 publications

(103 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Traditional traffic light control [37,38] provides pre-timed signal control with an assigned (fixed) time, without considering situations in real-time. Intelligent control systems can be dynamically utilized in real-time with an effective deep reinforcement learning model [39][40][41][42]. The system can be intelligently adjusted to traffic congestion by observing the traffic.…”

Section: Road Infrastructure Algorithmsmentioning

confidence: 99%

A Review of Intelligent Self-Driving Vehicle Software Research

2019

KSII TIIS

View full text Add to dashboard Cite

Interest in self-driving vehicle research has been rapidly increasing, and related research has been continuously conducted. In such a fast-paced self-driving vehicle research area, the development of advanced technology for better convenience safety, and efficiency in road and transportation systems is expected. Here, we investigate research in self-driving vehicles and analyze the main technologies of driverless car software, including: technical aspects of autonomous vehicles, traffic infrastructure and its communications, research techniques with vision recognition, deep leaning algorithms, localization methods, existing problems, and future development directions. First, we introduce intelligent self-driving car and road infrastructure algorithms such as machine learning, image processing methods, and localizations. Second, we examine the intelligent technologies used in self-driving car projects, autonomous vehicles equipped with multiple sensors, and interactions with transport infrastructure. Finally, we highlight the future direction and challenges of self-driving vehicle transportation systems.

show abstract

Section: Road Infrastructure Algorithmsmentioning

confidence: 99%

A Review of Intelligent Self-Driving Vehicle Software Research

2019

KSII TIIS

View full text Add to dashboard Cite

show abstract

“…There have been numerous researches, such as [4] and [5], which introduce artificial intelligence to allow better control over road traffic situation. By employing reinforcement learning algorithms, researchers build computer programs, which allow to control traffic flow using real-time data as well as previous experience.…”

Section: B Intelligent Road Traffic Control Systemsmentioning

confidence: 99%

Usage of SUMO Computer Modeling Software for Road Traffic Control System Validation

Ivanov¹,

Abu-Abed²

2019

IJRTE

View full text Add to dashboard Cite

Modern road traffic control systems become more complex with each year due to the growing number of cars, demand for more optimized road network designs, and desire to decrease road traffic delays at the intersections during rush hours because of the constantly growing metropolitan area and hence the need of moving farther away across the city. Therefore, a need is very much relevant nowadays for technologies, which can help build more optimal and intelligent road traffic control systems, which in turn will help optimize already existing road network designs. With the help of computer modeling software, it is possible to recreate already existing segments of road network, and by implementing control logic, it is possible to observe how control system and road traffic would react to various changes. This paper looks at how computer modeling software (namely SUMO) can help with the validation of road traffic control system changes without the risks of road traffic accidents caused by manipulation of real control systems.

show abstract

“…A DQN algorithm is a type of RL that combines the benefits of Qlearning and neural networks. Previous studies [11,[21][22][23][24][25][26][27][28] achieved good results when applying DQN methods using continuous state representations.…”

Section: Introductionmentioning

confidence: 99%

“…In general terms, the definitions and representations of state space in existing papers (e.g., total number of queued vehicles [12, 19-21, 27, 29], length of queued vehicles [12], speed of vehicles [11,18,23,27], or traffic flow [15,30]) can be modified to relay more effective information about the environment, which leads to more accurate judgments about the actions. e action space has been defined as all available signal phases [11,18,20,27,30,31], or alternatively, it has been defined to maintain a sequence [22]. As for the definition of a reward function, most studies choose a reduction in the travel time of a vehicle [11,22,23], length of a vehicle queue [13,15], or the time delay in queuing [11,19,20,26,28,30].…”

Section: Introductionmentioning

confidence: 99%

“…e action space has been defined as all available signal phases [11,18,20,27,30,31], or alternatively, it has been defined to maintain a sequence [22]. As for the definition of a reward function, most studies choose a reduction in the travel time of a vehicle [11,22,23], length of a vehicle queue [13,15], or the time delay in queuing [11,19,20,26,28,30]. Others [18] use the increase of throughput as reward, or the difference in queue length in different directions [24,25,27].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Traffic Signal Control Model on Intersections Based on Deep Reinforcement Learning

et al. 2020

Journal of Advanced Transportation

View full text Add to dashboard Cite

Controlling traffic signals to alleviate increasing traffic pressure is a concept that has received public attention for a long time. However, existing systems and methodologies for controlling traffic signals are insufficient for addressing the problem. To this end, we build a truly adaptive traffic signal control model in a traffic microsimulator, i.e., “Simulation of Urban Mobility” (SUMO), using the technology of modern deep reinforcement learning. The model is proposed based on a deep Q-network algorithm that precisely represents the elements associated with the problem: agents, environments, and actions. The real-time state of traffic, including the number of vehicles and the average speed, at one or more intersections is used as an input to the model. To reduce the average waiting time, the agents provide an optimal traffic signal phase and duration that should be implemented in both single-intersection cases and multi-intersection cases. The co-operation between agents enables the model to achieve an improvement in overall performance in a large road network. By testing with data sets pertaining to three different traffic conditions, we prove that the proposed model is better than other methods (e.g., Q-learning method, longest queue first method, and Webster fixed timing control method) for all cases. The proposed model reduces both the average waiting time and travel time, and it becomes more advantageous as the traffic environment becomes more complex.

show abstract

IntelliLight

Cited by 449 publications

References 9 publications

A Review of Intelligent Self-Driving Vehicle Software Research

A Review of Intelligent Self-Driving Vehicle Software Research

Usage of SUMO Computer Modeling Software for Road Traffic Control System Validation

Adaptive Traffic Signal Control Model on Intersections Based on Deep Reinforcement Learning

Contact Info

Product

Resources

About