On the performance of adaptive traffic signal control

Hengst, Bernhard; Ye, Getian; Huang, Eric; Wang, Yang; Aydos, Carlos; Geers, Glenn

doi:10.1145/1645373.1645380

Cited by 10 publications

(7 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To mitigate underestimation, they used heuristics based on differences in vehicle counts reported by advance and stop bar detectors [64]. They considered overestimation acceptable, as it provides the algorithm with buffer time; similarly, [65] found that moderate queue length overestimation significantly improves the performance of adaptive control.…”

Section: Lessons From Deploymentsmentioning

confidence: 99%

The Real Deal: A Review of Challenges and Opportunities in Moving Reinforcement Learning-Based Traffic Signal Control Systems Towards Reality

Chen¹,

Fang²,

Sadeh³

2022

Preprint

View full text Add to dashboard Cite

Traffic signal control (TSC) is a high-stakes domain that is growing in importance as traffic volume grows globally. An increasing number of works are applying reinforcement learning (RL) to TSC; RL can draw on an abundance of traffic data to improve signalling efficiency. However, RL-based signal controllers have never been deployed. In this work, we provide the first review of challenges that must be addressed before RL can be deployed for TSC. We focus on four challenges involving (1) uncertainty in detection, (2) reliability of communications, (3) compliance and interpretability, and (4) heterogeneous road users. We show that the literature on RL-based TSC has made some progress towards addressing each challenge. However, more work should take a systems thinking approach that considers the impacts of other pipeline components on RL.

show abstract

Section: Lessons From Deploymentsmentioning

confidence: 99%

The Real Deal: A Review of Challenges and Opportunities in Moving Reinforcement Learning-Based Traffic Signal Control Systems Towards Reality

Chen¹,

Fang²,

Sadeh³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Cai et al [3] carried out the modelling of STL for an intersection that has traffic approaching from four different directions. The Queue Tracker Model (QTM) shown in equation 1 (explained in table 1) is modelled to calculate the queue length at each traffic light.…”

Section: Ramp Meteringmentioning

confidence: 99%

Modelling a Smart Motorway

Richardson¹,

Davies

Newell

2019

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

The increasing number of vehicles in the UK is putting high levels of strain upon the motorway's infrastructure. Smart Motorways have been implemented in the UK using smart technology to try and reduce congestion. To test systems before they are physically built they are simulated using objects models and GIS data. This paper has modelled a new smart traffic light system for a slip road joining a smart motorway. The smart traffic light models have been simulated alongside Driver Behavior models. The driver behavior models have been designed to validate that the smart traffic light system can adapt to continuously fluctuating traffic flow. The smart traffic light system has been successfully validated and reduced the number of congestion alerts by 80% on the smart motorway.

show abstract

“…While online traffic signal control can be significantly more useful, it is also a challenging problem because scalable, network-wide control must be achieved under limited planning time, constantly changing traffic patterns, and realworld uncertainty associated with vehicle turn movements (Xie et al 2014;Cai et al 2009;Yu and Recker 2006). Related Work: Owing to the practical benefits and the challenging nature of the underlying control problem, there have been multiple threads of research dedicated to online traffic signal control.…”

Section: Introductionmentioning

confidence: 99%

Online Traffic Signal Control through Sample-Based Constrained Optimization

Dhamija

Gon

Varakantham

et al. 2020

ICAPS

View full text Add to dashboard Cite

Traffic congestion reduces productivity of individuals by increasing time spent in traffic and also increases pollution. To reduce traffic congestion by better handling dynamic traffic patterns, recent work has focused on online traffic signal control. Typically, the objective in traffic signal control is to minimize expected delay over all vehicles given the uncertainty associated with the vehicle turn movements at intersections. In order to ensure responsiveness in decision making, a typical approach is to compute a schedule that minimizes the delay for the expected scenario of vehicle movements instead of minimizing expected delay over the feasible vehicle movement scenarios. Such an approximation degrades schedule quality with respect to expected delay as vehicle turn uncertainty at intersections increases. We introduce TUSERACT (TUrn-SamplE-based Real-time trAffic signal ConTrol), an approach that minimizes expected delay over samples of turn movement uncertainty of vehicles. Specifically, our key contributions are: (a) By exploiting the insight that vehicle turn movements do not change with traffic signal control schedule, we provide a scalable constraint program formulation to compute a schedule that minimizes expected delay across multiple vehicle movement samples for a traffic signal; (b) a novel mechanism to coordinate multiple traffic signals through vehicle turn movement samples; and (c) a comprehensive experimental evaluation to demonstrate the utility of TUSERACT over SURTRAC, a leading approach for online traffic signal control which makes the aforementioned approximation. Our approach provides substantially lower (up to 60%) mean expected delay relative to SURTRAC with very few turn movement samples while providing real-time decision making on both real and synthetic networks.

show abstract

On the performance of adaptive traffic signal control

Cited by 10 publications

References 6 publications

The Real Deal: A Review of Challenges and Opportunities in Moving Reinforcement Learning-Based Traffic Signal Control Systems Towards Reality

The Real Deal: A Review of Challenges and Opportunities in Moving Reinforcement Learning-Based Traffic Signal Control Systems Towards Reality

Modelling a Smart Motorway

Online Traffic Signal Control through Sample-Based Constrained Optimization

Contact Info

Product

Resources

About