Combined variable speed limit and lane change guidance for secondary crash prevention using distributed deep reinforcement learning

Peng, Chang; Xu, Chengcheng

doi:10.1080/19439962.2021.2011810

Cited by 12 publications

(3 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The traffic conflict severity was quantified via time-to-collision (TTC), time exposed TTC, and time integrated TTC. Peng and Xu [ 11 ] evaluated the effectiveness of ASLG from arrays of roadside variable message signs on SC prevention where the evolutionary traffic condition under roadside ASLG after PC occurs can solely be predicted via simulation. The trajectories were obtained from the microscopic traffic simulator SUMO where CF and LC models.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Modelling and Mitigating Secondary Crash Risk for Serial Tunnels on Freeway via Lighting-Related Microscopic Traffic Model with Inter-Lane Dependency

Chen

Song

et al. 2023

IJERPH

View full text Add to dashboard Cite

This paper models and mitigates the secondary crash (SC) risk for serial tunnels on the freeway which is incurred by traffic turbulence after primary crash (PC) occurrence and location-heterogeneous lighting conditions along serial tunnels. A traffic conflict approach is developed where SC risk is quantified using a surrogate safety measure based on the simulated vehicle trajectories after PC occurs from a lighting-related microscopic traffic model with inter-lane dependency. Numerical examples are presented to validate the model, illustrate SC risk pattern over time, and evaluate the countermeasures for SC, including adaptive tunnel lighting control (ATLC) and advanced speed and lane-changing guidance (ASLG) for connected vehicles (CVs). The results demonstrate that the tail of the stretching queue on the PC occurrence lane, the adjacent lane of the PC-incurred queue, and areas near tunnel portals are high-risk locations. In serial tunnels, creating a good lighting condition for drivers is more effective than advanced warnings in CVs to mitigate SC risk. Combined ATLC and ASLG is promising since ASLG informs CVs of an immediate response to traffic turbulence on the lane where PC occurs and ATLC alleviates SC risks on adjacent lanes via smoothing the lighting condition variations and reducing inter-lane dependency.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

“…SCs are crashes that occur within the spatial and temporal impact range of a primary crash (PC) [ 9 , 10 , 11 ]. As described above, SC risk in serial tunnels mainly results from traffic turbulence, which is caused by both PC occurrence and lighting variations along serial tunnels.…”

Section: Introductionmentioning

confidence: 99%

Modelling and Mitigating Secondary Crash Risk for Serial Tunnels on Freeway via Lighting-Related Microscopic Traffic Model with Inter-Lane Dependency

Chen

Song

et al. 2023

IJERPH

View full text Add to dashboard Cite

show abstract

“…Results were obtained that VSL was effective in decreasing the risk of secondary collisions in all types of weather. Peng et al [25] designed a combined controller using the VSL and lane change guidance (LCG) theories to avoid secondary collisions on accident segments.…”

Section: Speed Limits In Expressway Accident Segmentsmentioning

confidence: 99%

Drivers’ Decelerating Behaviors in Expressway Accident Segments under Different Speed Limit Schemes

Zhang

et al. 2022

IJERPH

View full text Add to dashboard Cite

Traffic accidents occurring on expressways tend to give rise to traffic bottlenecks. To ensure the vehicles safely and smoothly pass through the accident segments, speed limits are generally taken to regulate the vehicles’ movements. This study aims to explore the decelerating behaviors of drivers under different speed limit schemes. We designed traffic accident scenarios under four speed limit schemes using the driving simulator. A total of 60 subjects drove the simulator passing the accident segments according to their habits. The vehicles’ kinematic data and the subjects’ operating data were recorded. To further analyze the drivers’ decelerating behaviors in different speed limit scenarios, driving experience was also taken into account. The results show that the speed limit schemes have significant effects on drivers’ decelerating behaviors. The more speed limit signs there are, the smoother the decelerating process will be. Driving experience significantly affects some of the decelerating parameters, including the location of deceleration starting point, average deceleration, and locations of decelerating to the initial and final speed limits. These results provide a theoretical basis for traffic safety and driving behavior management.

show abstract

A Survey About Learning-Based Variable Speed Limit Control Strategies: RL, DRL and MARL

Rhanizar,

El Akkaoui

2024

Studies in Computational Intelligence

View full text Add to dashboard Cite

Combined variable speed limit and lane change guidance for secondary crash prevention using distributed deep reinforcement learning

Cited by 12 publications

References 33 publications

Modelling and Mitigating Secondary Crash Risk for Serial Tunnels on Freeway via Lighting-Related Microscopic Traffic Model with Inter-Lane Dependency

Modelling and Mitigating Secondary Crash Risk for Serial Tunnels on Freeway via Lighting-Related Microscopic Traffic Model with Inter-Lane Dependency

Drivers’ Decelerating Behaviors in Expressway Accident Segments under Different Speed Limit Schemes

A Survey About Learning-Based Variable Speed Limit Control Strategies: RL, DRL and MARL

Contact Info

Product

Resources

About