Automated intersection delay estimation using the input–output principle and turning movement data

Adaptive signal control is a method that dynamically adjusts signal phases based on real-time traffic conditions, aiming to improve the efficiency of intersection light control. However, in practical applications, obtaining complete traffic spatiotemporal states at intersections is challenging given the limited data sources. To address this issue, this paper presents a novel deep reinforcement learning model, namely 3DQN-PSTER, which combines Dueling Deep Q Network, Double Deep Q Network, and Priority SumTree Experience Replay technology. This model effectively extracts traffic states from sampled floating car data (FCD) and achieves optimal timing schemes. To evaluate its performance, the proposed model is tested in a simulated intersection environment using actual intersection data. The model interacts with the environment by adjusting signal phases, updating traffic states, and obtaining optimal timing schemes. Simulation results demonstrate that the proposed model exhibits higher convergence efficiency and outperforms benchmark models. When applied, the reinforcement learning single control (RLSC) based on the 3DQN-PSTER model outperforms fixed-time signal control schemes and actuated signal control (ASC) schemes. Even in scenarios with low penetration ratios of FCD, RLSC still significantly outperforms ASC. Therefore, the signal timing optimization method proposed in this paper could greatly enhance intersection operation efficiency in both ideal overall data environments and partial states.

Traffic congestion and delays at signalized intersections remain a challenge in urban mobility. To minimize congestion, adaptive traffic signal control systems have been adopted across the United States. However, for these systems to function at their best, systems require an accurate estimation of traffic states, such as traffic density and queue length. This paper implements a relatively novel method, Physics-Informed Neural Networks (PINNs), for real-time traffic density estimation to enhance adaptive intersection signal control. The methodology leverages PINNs, which integrate both data-driven learning and physical constraints imposed by the Lighthill-Whitham-Richards (LWR) macroscopic traffic flow model. A simulation of a four-way intersection was used to generate realistic spatio-temporal traffic data to evaluate the performance of the model. Separate PINNs models, one trained for each incoming approach using simulation-based spatio-temporal density data, provide segment-level density predictions. These real-time density estimates are then employed within an adaptive traffic signal control algorithm designed to adjust green light phasing based on detected demand. The proposed PINNs control strategy was evaluated through simulation, comparing its performance against the Webster traffic timing method using key metrics such as average vehicle delay at the intersection and average vehicle travel time. The findings show an approximate 18% decrease in average vehicle delay and more than a 6% reduction in average travel time when utilizing adaptive traffic control based on the PINNs method for determining density values. These findings highlight the potential of leveraging PINNs for accurate, real-time traffic state estimation, which can effectively inform and improve the performance of adaptive traffic signal control systems, leading to reduced congestion and enhanced mobility at intersections.

Control methodologies of traffic signals have significantly improved during the recent past along with advancements in technology. Adaptive traffic signal control is the most recent and advanced control type of traffic signals. Adaptive control is able to efficiently relieve traffic congestion by continuously adjusting signal timings according to real-time traffic conditions. Conventional optimization methods such as integer programming, hill climbing, or descent gradient searching have been gradually overshadowed by genetic algorithms in many areas including traffic signal operation. The research presented in this article is distinct from previous studies in that it focuses on real-time adaptive signal optimization using genetic algorithms. The proposed adaptive signal system provides acyclic signal operation based on a rolling horizon real-time control approach. The algorithm was tested using microsimulation for on-line evaluation and comparison to fixed-time plans generated from the latest TRANSYT-7F version 9.7, which has a genetic optimization feature. The developed signal system consists of three major components including a genetic algorithm optimization module, an internal traffic simulation module, and a database management system all working in cooperation to optimize signal timings in real time. Using the pseudo on-line simulation platform, three testing scenarios for high, medium, and low level of traffic demands were conducted focusing on evaluating several important features of the proposed adaptive signal control system. The test results indicated that real-time genetic control outperformed fixed-signal timing plan in all scenarios based on total vehicle delay.

This paper presents an adaptive traffic signal controller algorithm that allows real time traffic flow data to control traffic signal timing for an isolated intersection. The proposed design allows greater flexibility and control of signal timings while keeping in view multiple criterions. It is based on simple rules that allow traffic flows on all intersection branches to control the timing of current signal phase without causing unrealistic delays on low volume side streets. The algorithm is also adjusted for capacity of different links. Detector data has been used to assess congestion situation and respond accordingly. A priority scheme for priority vehicles is also proposed. As a proof of concept, the proposed algorithm has been implemented on FPGA as a parameterized VERILOG model allowing adjustment to any intersection size and topology. An evaluator circuit was designed to assess the performance as compared to actuated signal controller. Improvement was observed in total stopped delay, number of stops and queue lengths.

The authors propose a real-time adaptive signal control model that aims to maintain the adaptive functionality of actuated controllers while improving the performance of traffic-actuated control systems. In this model, a flow-prediction algorithm is formulated to estimate the future vehicle arrival flow for each signal phase at the target intersection on the basis of the available signal-timing data obtained from previous control cycles. Optimal timing parameters are determined on the basis of these estimations and are used as signal-timing data for further optimizations. To be consistent with the operation logic of existing signal-control devices, this model is developed to optimize the basic control parameters that can be found in modern actuated controllers. Microscopic simulation is used to test and evaluate the proposed control model in a calibrated network consisting of 38 actuated signals. Simulation results indicate that this model has the potential to improve the performance of the signalized network under different traffic conditions.

Adaptive traffic signal controllers offer better signal time management especially when the traffic flow pattern is not uniform on all approaches. Traditional adaptive traffic controller use upstream or advance vehicle detection which works well in situations where traffic follows good lane discipline. However, when the spacing between intersections increases or in the case of complex geometry these systems may not be efficient. This is primarily because of the inability of traffic flow models to accurately estimate the traffic demand from the upstream detectors. Using stop-line detector information is best suited in such traffic conditions as they do not require any explicit prediction models. Furthermore, there are many intersections which works using stop-line detectors with preset maximum green timings as vehicle actuated controllers. These controllers can be easily converted into truly adaptive by changing their maximum green timings continuously with respect to changing traffic flow pattern. Hence, this paper proposes an adaptive traffic control model which uses stop-line detector information instead of upstream detector. The model aims at real-time allocation of green time through reinforcement learning; an approach originated from the machine learning community. This approach has the ability to learn relationships between signal control actions and their effect on the queue while pursuing the goal of maximizing throughput which is a distinct improvement over the traditional vehicle actuated system. To demonstrate the performance of the proposed model a typical four-way intersection with four-phase scheme is evaluated for various flow conditions with the proposed model as well as with the traditional vehicle actuated system. The results show improvement over traditional system, especially when the flow is near the capacity.

Traffic congestion is a major problem in modern urban areas due to the increasing number of vehicles and the limitations of traditional fixed-time traffic signal systems. These conventional systems fail to respond to real-time traffic conditions, resulting in longer waiting times, higher fuel consumption, and increased environmental pollution. This project presents a Dynamic Traffic Signal Allocation System that combines computer vision and real-time data processing to optimize traffic signal control. The system integrates the SUMO traffic simulator to model road networks and simulate traffic flow, while a YOLO-based object detection model is used to detect and count vehicles from simulated video streams. Based on the detected vehicle counts, a Q-Learning algorithm determines the optimal green signal duration for each lane by considering current traffic density and minimizing overall vehicle delay. A TraCI interface is used to communicate with the SUMO simulation in real time and control signal phase operations. Traffic data and system outputs are stored using Firebase Firestore, enabling realtime monitoring across sessions. A Flask-based backend handles data processing and serves the application, while a web-based dashboard built with HTML, CSS, and JavaScript displays traffic statistics through charts and exportable reports. The proposed system demonstrates improved traffic flow, reduced congestion at intersections, and a practical approach to adaptive signal control. It is designed with scalability in mind and shows potential for integration into broader smart city frameworks as a cost-effective alternative to conventional traffic management reflect the core contribution of the paper. Please avoid citations in the abstract.

A computationally efficient algorithm for estimating time delay between signals received at two spatially separated sensors is proposed. The delay estimate is adapted directly to maximise the mean product of the first sensor output and the filtered output of the second received signal. The convergence behaviour and variance of the delay estimate are derived. It is shown that the proposed algorithm outperforms the explicit time delay estimator at a low signal-to-noise ratio.

As with the advances in location-based technology that emerged from ecommerce and wireless communication, individual vehicular information is becoming available instantaneously and could be used for traffic signal control. A new paradigm of a signal control algorithm might be needed to accommodate such abundant location-based information. This preliminary study investigates the benefit of adaptive signal control under such conditions. A simple event-based simulation program along with a genetic algorithm-based signal optimization program developed in this study evaluates various scenarios including both demand and market penetration levels. A test bed used in the study consists of two one-way streets with single-lane approaches. This study provides a ceiling benchmark of adaptive signal control under perfect knowledge in vehicle arrivals. The results indicate that adaptive signal control outperforms pretimed signal control for all cases considered, but the marginal benefit of adaptive signal control increases up to a certain volume level and then decreases. The results also indicate that the use of imperfect knowledge improves performance of adaptive signal timing plans over pretimed timing plans.

Basic signal operation strategies allocate green time to different traffic movements to control the flow at an intersection. Signal control applications consider different objectives, such as coordination with multiple intersections, multimodal priority, and safety. Real-time signal control applications rely mainly on infrastructure-based detection data. With the emergence of connected vehicle technology, high-resolution data from connected vehicles will become available for signal control. This paper presents a framework that uses connected vehicle data for adaptive signal control and considers dilemma zone protection, multimodal signal priority, and coordination. Initially, the market penetration rate of connected vehicles will be low, so infrastructure-based detector actuation logic is integrated into the framework to improve performance. Simulation analysis demonstrated good results when the penetration rate was medium to high and that the actuation logic was necessary when the penetration rate was low.

CAV-enabled data analytics for enhancing adaptive signal control safety environment

With the development of connected vehicles (CVs) technology, it has become a new research topic to capture the dynamic traffic system by using CVs data. The traditional vehicle arrival prediction models are limited to the fixed detectors, which can only recognize the passing information of vehicles, but cannot identify the state of vehicles. This paper proposed a new vehicle arrival prediction model of traffic signal control in a connected vehicle environment. First, the vehicle's identification number (ID), position, velocity, and acceleration were obtained in a CV environment. Second, a new vehicle arrival prediction model was developed by the joint probability distribution calibrated based on CV data. Then, the simulation experiment was designed for analyzing influence factors on model performance. The results show that the average relative error of each factor is less than 10%. Finally, the reliability of the proposed model was verified based on an adaptive signal control algorithm. Therefore, the proposed model can be used in the adaptive signal control system.

Rapid urbanization and the growth of multimodal transport systems have increased the complexity of pedestrian–vehicle interactions at urban corridors, leading to heightened safety risks and congestion. This study develops a quantitative simulation framework using PTV VISSIM to evaluate how smart-corridor interventions—such as adaptive signal control, pedestrian detection systems, and geometric traffic-calming measures—can enhance pedestrian safety without compromising traffic efficiency. A 2.0-km urban corridor featuring multiple signalized and unsignalized crossings was modeled and calibrated with empirical traffic and pedestrian data collected from typical weekday and weekend conditions. Five simulation scenarios were constructed, including a baseline case and four smart-corridor configurations representing various technology integrations. Each scenario was replicated across different demand states using stochastic seeding to ensure statistical robustness. Conflict-based safety indicators such as Time-to-Collision (TTC), Post-Encroachment Time (PET), and Deceleration Rate to Avoid Crash (DRAC) were extracted from trajectory files using the Surrogate Safety Assessment Model (SSAM). These surrogate measures were normalized by pedestrian exposure to compute conflict rates per 1,000 crossings. Results were analyzed using negative binomial generalized linear mixed models (NB-GLMM) to estimate incidence rate ratios (IRRs) for both total and severe conflicts. Complementary linear mixed models (LMM) were applied to evaluate mobility outcomes including pedestrian delay, vehicle delay, and mean speed. Sensitivity analyses tested variations in threshold definitions (TTC, PET) and behavioral parameters to validate the robustness of findings. Preliminary results indicate that smart-corridor configurations integrating adaptive pedestrian detection and traffic-calming geometry achieved up to a 35% reduction in severe conflicts (IRR = 0.65, p < 0.05) while maintaining acceptable vehicle delay increases below 10%. Pedestrian delay improvements were most pronounced under adaptive signal logic, suggesting strong synergies between detection-based actuation and optimized signal timing. The study concludes that smart-corridor designs, when strategically modeled and validated through microsimulation, can serve as a reliable decision-support tool for urban planners seeking to balance pedestrian safety and traffic mobility. The research contributes a reproducible, data-driven framework for evidence-based evaluation of intelligent transportation systems (ITS) in pedestrian-rich urban environments.

It is interesting to realize that traffic intersections provide an essential mechanism to handle traffic flows in different directions while ironically traffic bottlenecks, gridlocks, and accidents tend to occur in the vicinity of the intersections. Meanwhile, with the recent developments in internet of things (IoT) technologies, there is a great potential for integrating them for improving operational efficiencies of road infrastructure and connected autonomous vehicles (CAVs). This paper aims to leverage the capabilities of both autonomous intersection manager (AIM) and CAVs for more energy-saving and safe-traffic management. A mixed-traffic environment where human-driven vehicles (HDVs) and CAVs sharing the same road is considered. A two-layer framework is adopted to handle signal and vehicle controls effectively. The first layer is a signal control layer where the AIM receives the traffic network states, trains with the data through machine learning (ML), and outputs a set of optimal green times for each intersection phase. The second layer is a decentralized-vehicle control layer where the CAVs receive the signal phase and timing (SpaT) information from the AIM to compute the optimal speed values. The proposed solution helps the CAVs to minimize idling at red signals or to speed up to safely arrive at and pass through a green signal. Our proposed framework is designed to optimize intersection efficiency and minimize vehicle average delay and fuel consumption. All experiments have been conducted in a microscopic traffic simulation environment, the PTV-VISSIM, simulating real-world dynamics of vehicles and drivers’ behaviors based on decades of field-data.

Urban traffic congestion necessitates a transition from reactive signal control toward proactive, prediction-driven traffic management strategies.This study proposes a multivariate forecasting framework based on Long Short-Term Memory (LSTM) neural networks to support short-term adaptive signal control at urban intersections.Using high-resolution traffic data collected at 20-second intervals, three independent yet structurally consistent LSTM models were developed to predict vehicle count, traffic density, and adaptive green time.The models exploit temporal dependencies through sequence-based learning and are trained using a supervised multivariate formulation.Experimental results demonstrate stable convergence and strong generalization, with validation loss values below 0.093 across all targets.Additional evaluation using RMSE, MAE, and MAPE confirms robust predictive accuracy under heterogeneous traffic conditions.Twenty-stepahead forecasts (approximately 6-7 minutes) reveal coherent temporal behavior, characterized by increasing and stabilizing traffic demand alongside converging green time allocations, indicating that the models capture key nonlinear interactions between congestion and control logic.Compared with conventional statistical and machine learning approaches, the proposed framework achieves competitive accuracy with lower computational complexity.The findings highlight the potential of LSTM-based forecasting to enable anticipatory traffic signal control, improve intersection performance, and reduce congestion-related environmental impacts.