Cooperative lane control application for fully connected and automated vehicles at multilane freeways

Khattak, Zulqarnain H.; Smith, Brian L.; Park, Hyung Jun; Fontaine, Michael D.

doi:10.1016/j.trc.2019.11.007

Cited by 59 publications

(36 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other significant research in this application context includes those by Khattak et al. (2020), Karimi et al. (2020), and Xiao and Cassandras (2019).…”

Section: Experiments Settingsmentioning

confidence: 99%

Graph neural network and reinforcement learning for multi‐agent cooperative control of connected autonomous vehicles

Chen

Dong

et al. 2021

Computer aided Civil Eng

138

View full text Add to dashboard Cite

A connected autonomous vehicle (CAV) network can be defined as a set of connected vehicles including CAVs that operate on a specific spatial scope that may be a road network, corridor, or segment. The spatial scope constitutes an environment where traffic information is shared and instructions are issued for controlling the CAVs movements. Within such a spatial scope, high‐level cooperation among CAVs fostered by joint planning and control of their movements can greatly enhance the safety and mobility performance of their operations. Unfortunately, the highly combinatory and volatile nature of CAV networks due to the dynamic number of agents (vehicles) and the fast‐growing joint action space associated with multi‐agent driving tasks pose difficultly in achieving cooperative control. The problem is NP‐hard and cannot be efficiently resolved using rule‐based control techniques. Also, there is a great deal of information in the literature regarding sensing technologies and control logic in CAV operations but relatively little information on the integration of information from collaborative sensing and connectivity sources. Therefore, we present a novel deep reinforcement learning‐based algorithm that combines graphic convolution neural network with deep Q‐network to form an innovative graphic convolution Q network that serves as the information fusion module and decision processor. In this study, the spatial scope we consider for the CAV network is a multi‐lane road corridor. We demonstrate the proposed control algorithm using the application context of freeway lane‐changing at the approaches to an exit ramp. For purposes of comparison, the proposed model is evaluated vis‐à‐vis traditional rule‐based and long short‐term memory‐based fusion models. The results suggest that the proposed model is capable of aggregating information received from sensing and connectivity sources and prescribing efficient operative lane‐change decisions for multiple CAVs, in a manner that enhances safety and mobility. That way, the operational intentions of individual CAVs can be fulfilled even in partially observed and highly dynamic mixed traffic streams. The paper presents experimental evidence to demonstrate that the proposed algorithm can significantly enhance CAV operations. The proposed algorithm can be deployed at roadside units or cloud platforms or other centralized control facilities.

show abstract

“…Other significant research in this application context includes those by Khattak et al. (2020), Karimi et al. (2020), and Xiao and Cassandras (2019).…”

Section: Experiments Settingsmentioning

confidence: 99%

Graph neural network and reinforcement learning for multi‐agent cooperative control of connected autonomous vehicles

Chen

Dong

et al. 2021

Computer aided Civil Eng

138

View full text Add to dashboard Cite

show abstract

“…The presence of connected and automated vehicle highway (CAVH) technology has given a unique opportunity to improve mobility through vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications [16], [23]. In a CAVH system, there is typically a dedicated lane for CAVs that quarantines them from the HDVs [21], [23], [30], and a diverging zone (DZ) for CAVs to carry out lane changes into the human driven vehicle (HDV) lane [17]. This gives rise to a significant challenge of managing mandatory lane changes of CAVs in a limited length of a DZ efficiently.…”

Section: A Overviewmentioning

confidence: 99%

A Prioritized Trajectory Planning Algorithm for Connected and Automated Vehicle Mandatory Lane Changes

Li¹,

Fan²,

Fischer³

et al. 2021

Preprint

View full text Add to dashboard Cite

We introduce a prioritized system-optimal algorithm for mandatory lane change (MLC) behavior of connected and automated vehicles (CAV) from a dedicated lane. Our approach applies a cooperative lane change that prioritizes the decisions of lane changing vehicles which are closer to the end of the diverging zone (DZ), and optimizes the predicted total system travel time. Our experiments on synthetic data show that the proposed algorithm improves the traffic network efficiency by attaining higher speeds in the dedicated lane and earlier MLC positions while ensuring a low computational time. Our approach outperforms the traditional gap acceptance model.

show abstract

“…In the connected automatic vehicle environment, the behavior of vehicles is consistent with traffic flow theory [24,25]. Many scholars have made a series of ideas about this, including a new lane-change protocol [26], a traffic flow model considering the influence of car-following [27], a proactive longitudinal control merging algorithm [28], and dynamic lane signals [29]. However, few studies have addressed merging and diverging induction strategies for vehicle groups of ramp areas in the connected vehicle environment.…”

Section: Introductionmentioning

confidence: 96%

Collaborative Strategies and Simulation of Vehicle Group Behaviors for Off-Ramp Areas

Zhang

et al. 2020

Journal of Advanced Transportation

View full text Add to dashboard Cite

With the increase of vehicle ownership and the rapid growth of urban traffic, the problem of congestion in the off-ramp area of the main expressway has become the main factor restricting overall section efficiency and inducing traffic accidents. This paper focuses on the problem of group collaborative lane-changing behaviors of off-ramp vehicles and through vehicles in off-ramp areas and proposes four kinds of vehicle group collaborative strategies based on different road space balance conditions. According to a three-lane expressway scene, a VISSIM-based simulation model is built and the optimization scheme is simulated and evaluated. The simulation results show that with the increase of traffic flow in off-ramp areas, a flow-balance strategy for downstream lanes where off-ramp vehicles merge with the outside lane in advance is more advantageous. When vehicles are leaving the main road, if traffic flow is heavy, the flow-balance strategy for lanes where off-ramp vehicles merge with the outside lane in advance (for example, the proportion of off-ramp vehicles in three lanes is 0 : 0 : 1) is better; otherwise, when the traffic flow on the main road is relatively small, the flow-balance strategy for lanes where off-ramp vehicles are distributed in lanes with different ratios (e.g., 1 : 3 : 6) is better. What is more, for future traffic management in connected vehicle environments, it can be concluded that collaborative vehicle lane-changing strategies with different traffic flow states can help to enhance traffic efficiency.

show abstract

Cooperative lane control application for fully connected and automated vehicles at multilane freeways

Cited by 59 publications

References 38 publications

Graph neural network and reinforcement learning for multi‐agent cooperative control of connected autonomous vehicles

Graph neural network and reinforcement learning for multi‐agent cooperative control of connected autonomous vehicles

A Prioritized Trajectory Planning Algorithm for Connected and Automated Vehicle Mandatory Lane Changes

Collaborative Strategies and Simulation of Vehicle Group Behaviors for Off-Ramp Areas

Contact Info

Product

Resources

About