Connected autonomous vehicles for improving mixed traffic efficiency in unsignalized intersections with deep reinforcement learning

Peng, Bile; Keskin, Musa Furkan; Kulcsár, Balázs; Wymeersch, Henk

doi:10.1016/j.commtr.2021.100017

Cited by 81 publications

(27 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the development of NGSIM [17], high-quality trajectory data and driver behavior aspects have further strengthened traffic flow modeling for evaluating policy interventions more comprehensively. Further, in recent times, researchers [18][19][20] tested the deep learning and reinforcement learning strategies for improving the mixed traffic flow efficiency levels.…”

Section: Introductionmentioning

confidence: 99%

Data-Driven Approach for Modeling the Nonlane-Based Mixed Traffic Conditions

Raju

Arkatkar

Easa

et al. 2022

Journal of Advanced Transportation

View full text Add to dashboard Cite

The diverse nature of vehicle categories and the resultant lane discipline in mixed (heterogeneous) traffic cause complex spatial interactions. As a result, the driving behavior process in mixed traffic conditions is meaningfully different, where both longitudinal and lateral movements of the vehicles continuously occur. Under prevailing homogeneous traffic conditions in developed countries, driving behavior is partially discrete, where following longitudinal behavior and outboard lane-change models can model traffic behavior. However, the established car-following and lane-change models cannot be directly used in shaping mixed traffic conditions. Such conditions also warrant the use of high-quality microlevel vehicular trajectory data. Accordingly, realizing this need, vehicular trajectory data for different traffic flow conditions were developed. The data were used to extract the parameters required for modeling the vehicles’ positions using machine learning algorithms. Three established supervised machine learning algorithms (k-NN, random forest, and regression tree) and deep learning are selected to model mixed traffic conditions. The parameters which influence longitudinal and lateral movements are identified using Spearman correlation analysis. Furthermore, simulation runs are performed using the python language. The performance of the algorithms is evaluated both at the microscopic and macroscopic levels using relevant traffic indicators. The results show that a deep learning model and k-NN tend to replicate better-mixed traffic conditions than random forest and regression trees.

show abstract

Section: Introductionmentioning

confidence: 99%

Data-Driven Approach for Modeling the Nonlane-Based Mixed Traffic Conditions

Raju

Arkatkar

Easa

et al. 2022

Journal of Advanced Transportation

View full text Add to dashboard Cite

show abstract

“…e filtering lane channelizes motorcycle riders to penetrate the queue in a discipline lane, where other road users can expect their trajectory and are aware of a potential conflict with motorcycles. Moreover, the findings can support connected autonomous vehicles [42] for controlling autonomous motorcycles and microscopic traffic simulations when motorcycles filter lanes in mixed traffic at signalized urban intersections.…”

Section: Conclusion and Recommendationsmentioning

confidence: 60%

Lane-Filtering Behavior of Motorcycle Riders at Signalized Urban Intersections

Promraksa

Satiennam

et al. 2022

Journal of Advanced Transportation

View full text Add to dashboard Cite

In developing countries, motorcycle riders typically perform lane filtering at signalized urban intersections. This study aims to determine the factors that affect the lateral clearance of motorcycle riders as they travel between two lanes of mixed traffic at signalized urban intersections in developing countries. In this study, an onboard measurement device was developed to measure the lane-filtering behavior of motorcycle riders. It was installed on a test motorcycle to continuously record the lateral clearance, riding behavior, and surrounding traffic conditions. Thirty participants rode the test motorcycle through a signalized urban intersection. Multilevel linear regression was applied to analyze the relationship between lateral clearance and relevant variables at a significance level of 0.05. The instant speed and side of the filtering motorcycle, condition of the lateral vehicle, type of lateral vehicle, and riding frequency of the motorcycle rider significantly influenced the lateral clearance. The findings of this study can contribute to filtering lane management, connected autonomous vehicles, and microscopic traffic simulations for motorcycles traveling in mixed traffic at signalized urban intersections.

show abstract

“…However, with vehicle communication and autonomous driving technologies, new possibilities exist to prevent or mitigate such adverse traffic effects in the ramp merging areas. Traditional traffic management approaches such as ramp metering (Papageorgiou et al , 1991; Papageorgiou et al , 1997; Ahn et al , 2007; Papamichail et al , 2010), variable speed limits/mainline metering (Carlson et al , 2010; Jin et al , 2017; Zhang et al , 2017; Peng et al , 2021; Lu and Liu, 2021; Chen et al , 2021c) and hard shoulder running (Haj-Salem et al , 2014; Li et al , 2014). Unfortunately, these approaches can only control the traffic at an aggregated level.…”

Section: Introductionmentioning

confidence: 99%

Merging control strategies of connected and autonomous vehicles at freeway on-ramps: a comprehensive review

Zhu

Easa

Gao

2022

JICV

View full text Add to dashboard Cite

Purpose On-ramp merging areas are typical bottlenecks in the freeway network since merging on-ramp vehicles may cause intensive disturbances on the mainline traffic flow and lead to various negative impacts on traffic efficiency and safety. The connected and autonomous vehicles (CAVs), with their capabilities of real-time communication and precise motion control, hold a great potential to facilitate ramp merging operation through enhanced coordination strategies. This paper aims to present a comprehensive review of the existing ramp merging strategies leveraging CAVs, focusing on the latest trends and developments in the research field. Design/methodology/approach The review comprehensively covers 44 papers recently published in leading transportation journals. Based on the application context, control strategies are categorized into three categories: merging into sing-lane freeways with total CAVs, merging into sing-lane freeways with mixed traffic flows and merging into multilane freeways. Findings Relevant literature is reviewed regarding the required technologies, control decision level, applied methods and impacts on traffic performance. More importantly, the authors identify the existing research gaps and provide insightful discussions on the potential and promising directions for future research based on the review, which facilitates further advancement in this research topic. Originality/value Many strategies based on the communication and automation capabilities of CAVs have been developed over the past decades, devoted to facilitating the merging/lane-changing maneuvers at freeway on-ramps. Despite the significant progress made, an up-to-date review covering these latest developments is missing to the authors’ best knowledge. This paper conducts a thorough review of the cooperation/coordination strategies that facilitate freeway on-ramp merging using CAVs, focusing on the latest developments in this field. Based on the review, the authors identify the existing research gaps in CAV ramp merging and discuss the potential and promising future research directions to address the gaps.

show abstract

Connected autonomous vehicles for improving mixed traffic efficiency in unsignalized intersections with deep reinforcement learning

Cited by 81 publications

References 10 publications

Data-Driven Approach for Modeling the Nonlane-Based Mixed Traffic Conditions

Data-Driven Approach for Modeling the Nonlane-Based Mixed Traffic Conditions

Lane-Filtering Behavior of Motorcycle Riders at Signalized Urban Intersections

Merging control strategies of connected and autonomous vehicles at freeway on-ramps: a comprehensive review

Contact Info

Product

Resources

About