A Speed Control Method at Successive Signalized Intersections Under Connected Vehicles Environment

Lu, Yingrong; Xu, Xing; Ding, Chuan; Lu, Guangquan

doi:10.1109/mits.2019.2919638

Cited by 39 publications

(17 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…erefore, the demand per kilometer for LiDAR in different road scenarios d Li,i can be calculated by equation (5), where r li is the coverage radius of LiDAR.…”

Section: Model Constructionmentioning

confidence: 99%

“…Based on the core autonomous driving functions, ICVs can replace human beings to complete driving tasks. It can not only provide passengers with a safer, more comfortable, and intelligent driving experience but also improve travel efficiency [3][4][5][6], save energy and reduce emissions [7][8][9], and reduce the traffic accident rate [10][11][12]. At present, the development route of autonomous driving is gradually changing from vehicle intelligence to "vehicle to X" (V2X) [13].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of the Cost of Intelligent Upgrades of Transportation Infrastructure for Intelligent Connected Vehicles

Liu

Song

Tan

et al. 2022

Journal of Advanced Transportation

View full text Add to dashboard Cite

Intelligent connected vehicles (ICVs) have become the focus and development direction of the automobile industry. As a flexible intelligent terminal, ICVs will become a necessary part of the intelligent transportation system. The routes of developing ICVs based on “vehicle to X” (V2X) can effectively alleviate the demands of vehicles for intelligent functions and cut related research costs, accelerating commercialization of ICVs and leading to many social benefits. At present, China has made it clear to develop ICVs based on V2X, which requires simultaneous intelligent upgrades of vehicles and transportation infrastructure. Therefore, intelligent upgrades of transportation infrastructure must match the functional requirements of ICVs. In addition, the investment in intelligent upgrades of transportation infrastructure is mainly from the government, so the costs must be controlled reasonably to find the most cost-effective upgrade route. In this paper, the types of intelligent transportation infrastructures were determined by sorting out the demands of ICVs for transportation infrastructure, and the deployment methods and upgrade routes of intelligent transportation infrastructures were designed. Then, the cost evaluation model for intelligent upgrade of transportation infrastructures was established, based on which, the cost evaluation of different intelligent upgrade routes of transportation infrastructure was carried out in closed highway and open urban road scenarios to determine the optimal route. Besides, the key elements affecting the cost of transportation infrastructure upgrades were identified, and their impact degrees on transportation infrastructure upgraded were analyzed by scenario analysis. The results show that the intelligent transportation infrastructure for advanced ICVs mainly includes communication base stations, roadside units (RSUs), vision sensors, millimeter-wave radars, laser radars (LiDARs), meteorological sensors, intelligent signal machines, edge computing servers, and cloud computing centers. The route of deploying primary intelligent transportation infrastructure at first and then directly upgrading them to advanced level can well match the functional requirements of ICVs on the basis of lower costs. The costs of RSUs, LIDARS, and edge computing servers as well as data transmission rate of 5G are key elements affecting the costs of intelligent upgrades of transportation infrastructure.

show abstract

“…erefore, the demand per kilometer for LiDAR in different road scenarios d Li,i can be calculated by equation (5), where r li is the coverage radius of LiDAR.…”

Section: Model Constructionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Evaluation of the Cost of Intelligent Upgrades of Transportation Infrastructure for Intelligent Connected Vehicles

Liu

Song

Tan

et al. 2022

Journal of Advanced Transportation

View full text Add to dashboard Cite

show abstract

“…In equation (9), When this data enters the neural network as input, the position of the variables will play an important role. e above operation can decouple the identity and running information of the vehicles so that the proposed CoMADDPG can be adapted to the scenario of more agents.…”

Section: Cooperative Maddpg (Comaddpg)mentioning

confidence: 99%

“…Lu et al presented a novel speed control method for the successive signalized intersections under connected vehicles environment. With the timing information and vehicle queues at the signalized intersection, vehicle speed was optimized to reduce fuel consumption and emissions [9]. Xu proposed a cooperative method to optimize roadside signal optimization and on-board vehicle speed control at the same time [10].…”

Section: Introductionmentioning

confidence: 99%

Cooperative Multiagent Deep Deterministic Policy Gradient (CoMADDPG) for Intelligent Connected Transportation with Unsignalized Intersection

Jiang

Zhang

2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Unsignalized intersection control is one of the most critical issues in intelligent transportation systems, which requires connected and automated vehicles to support more frequent information interaction and on-board computing. It is very promising to introduce reinforcement learning in the unsignalized intersection control. However, the existing multiagent reinforcement learning algorithms, such as multiagent deep deterministic policy gradient (MADDPG), hardly handle a dynamic number of vehicles, which cannot meet the need of the real road condition. Thus, this paper proposes a Cooperative MADDPG (CoMADDPG) for connected vehicles at unsignalized intersection to solve this problem. Firstly, the scenario of multiple vehicles passing through an unsignalized intersection is formulated as a multiagent reinforcement learning (RL) problem. Secondly, MADDPG is redefined to adapt to the dynamic quantity agents, where each vehicle selects reference vehicles to construct a partial stationary environment, which is necessary for RL. Thirdly, this paper incorporates a novel vehicle selection method, which projects the reference vehicles on a virtual lane and selects the largest impact vehicles to construct the environment. At last, an intersection simulation platform is developed to evaluate the proposed method. According to the simulation result, CoMADDPG can reduce average travel time by 39.28% compared with the other optimization-based methods, which indicates that CoMADDPG has an excellent prospect in dealing with the scenario of unsignalized intersection control.

show abstract

“…In this study, aiming at the issue of optimal decision-making for intersection signal control [11,[30][31][32], we designed a real-time information collection scheme for the far vehicles using a VANET, and took them into consideration, as well as the information of the intersection vehicles, to determine the intersection traffic condition at a certain time in the future. According to the calculated waiting time of each traffic flow, the signal decision could be made more precisely.…”

Section: Introductionmentioning

confidence: 99%

An Intersection Signal Control Mechanism Assisted by Vehicular Ad Hoc Networks

Cai

Deng

et al. 2019

Electronics

View full text Add to dashboard Cite

The urban intersection signal decision-making in traditional control methods are mostly based on the vehicle information within an intersection area. The far vehicles that have not reached the intersection area are not taken into account, which results in incomplete information and even incorrectness in decision-making. This paper presents an intersection signal control mechanism assisted by far vehicle information. Using the aid of real-time information collection for far vehicles through vehicular ad hoc networks (VANETs), we can consider them together and calculate the accumulative waiting time for each intersection traffic flow at a future moment to make the optimal signal decision. Simulation results show that, under three different traffic flow environments—same even traffic flows, same uneven traffic flows, and different traffic flows—the two proposed implementation schemes based on the mechanism (fixed phase and period timing improvement scheme, and dynamic phase and period control scheme) show good performances, in which the average waiting time and the ratio of long-waiting vehicles are both less than the results of the traditional signal timing scheme. Especially, in the second scheme, the waiting time was reduced by an average of 38.6% and the ratio of long-waiting vehicles was reduced by an average of 7.67%.

show abstract

A Speed Control Method at Successive Signalized Intersections Under Connected Vehicles Environment

Cited by 39 publications

References 32 publications

Evaluation of the Cost of Intelligent Upgrades of Transportation Infrastructure for Intelligent Connected Vehicles

Evaluation of the Cost of Intelligent Upgrades of Transportation Infrastructure for Intelligent Connected Vehicles

Cooperative Multiagent Deep Deterministic Policy Gradient (CoMADDPG) for Intelligent Connected Transportation with Unsignalized Intersection

An Intersection Signal Control Mechanism Assisted by Vehicular Ad Hoc Networks

Contact Info

Product

Resources

About