Exploiting domain constraints for exemplar based bus detection for traffic scheduling

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.

In this work, the connected vehicle's messages are used to create an enhanced adaptive traffic signal control (ATSC) system for improved traffic flow. Few existing studies use connected and automated vehicles (CAVs) to develop traffic signal control algorithms under hybrid connected and autonomous conditions. The proposed approach focuses on a four‐phase traffic intersection with both CAVs and human‐driven vehicles (HVs). CAVs share real‐time state information, and a model called Roads Dynamic Segmentation estimates queuing procedures and vehicle fleet numbers on dynamic road sections. This information is used in the Store and Forward Model (SFM) to predict intersection queuing length. The ATSC system, based on model predictive control (MPC), aims to minimize intersection queue length while considering traffic constraints (undersaturated, saturated, and oversaturated) and avoiding free‐flow problems due to queue overflow. To reduce computational complexity, a linear‐quadratic‐regulator (LQR) is used. Real‐world vehicle trajectories and the SUMO tool are used for experimental purposes. Results show that the proposed method reduces average delay by 38.50% and 33.42% compared to fixed timing and traditional MPC in cases of oversaturated traffic flow with 100% CAV penetration. Even with a penetration rate of only 20%, average delay decreases by 13.65% and 6.50%, respectively. This study showcases not only the potential benefits of CAV in enhancing traffic, but also enables the optimal utilization of green duration in signalized intersection control systems. This helps prevent traffic congestion and ensures the efficient and smooth movement of traffic flow.

Traffic congestion can be alleviated by infrastructure expansions, however, improving the existing infrastructure using traffic control is more plausible due to the obvious constraints on financial resources and physical space. Independent applications of Adaptive Traffic Signal Control (ATSC) and Ramp Metering (RM) have shown strong potential to effectively alleviate urban traffic congestion by adjusting the signal timings in real-time in response to traffic fluctuations to achieve desirable objectives (e.g., minimize delay at intersections or minimize travel time along freeways). This paper presents the problem formulation and the framework for addressing traffic control problem using an integrated solution combining ATSC and RM. According to that problem definition, an optimal closed-loop approach for ATSC and RM can be designed using a multi-agent reinforcement learning (MARL) approach. Authors' previous studies of MARL on a large-scale simulated network of 59 intersections in the lower downtown core of the City of Toronto for the morning rush hour have shown unprecedented reduction in the average intersection delay up to 39% at the network level, and travel time savings of up 2to 26% along the busiest routes in downtown Toronto. Additionally, authors' studies of MARL applied to a calibrated microsimulation model of the Gardiner Expressway in Toronto, Canada resulted in 50% reduction in total travel time compared with the base case scenario.

Building scalable, adaptive, and collaborative traffic signal control system still remains to be further explored across relevant research communities, including computer science and transportation groups. In this study, a scalable multi-agent framework is proposed based on the coordination graphs framework where the global objective is decomposed into a linear sum of local edge-based functions. The proposed edge-based decomposition scales linearly with edges in dense networks. A novel combination of max-plus joint action selection algorithm with two collaborative model-free methods, including sparse cooperative Q-learning (SparseQ) and relative sparse cooperative Q-learning (RSparseQ), is utilized to control multi-intersection networks. Extensive experiments are carried out, and their results demonstrate the effectiveness of our proposed framework. In comparison with independent Q-learning agents, our proposed framework achieves superior performance in terms of vehicle trip time, waiting time and jam length. In addition, the reported results show that the proposed RSparseQ outperforms SparseQ in avoiding vehicles teleports, which leads to better driver satisfaction.

Adaptive traffic signal control systems often rely on expensive physical detection infrastructure. However, with the advent of widespread trajectory data, it is now possible to implement adaptive control entirely avoiding such costs. We present two simple adaptive control policies which only require sample delay and number of stops, with the goal to mitigate the presence of oversaturation. The simplicity stems from the necessity of controlling under any trajectory penetration rate. The two policies differ on the possibilities of the control infrastructure to be implemented. The first one minimizes oversaturation by deviating from a reference pre-timed signal plan. This signal plan can be an existing one or an estimated one from aggregating trajectory data. The second policy creates first a set of green split plans to be then selected by a control logic. This second policy is intended to be used in SCATS-like systems where signal plans are limited to a pre-defined discrete set. We propose a plan selection logics or alternatively, the original plan selection policy can be used as well. Both policies are tested in the field, achieving a significant reduction in delay, oversaturation and spillover ratios. Lastly, we test an application of this policy as an enhancement of SCATS systems in the presence of malfunctioning physical detectors.

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.

The increasing complexity of urban transportation systems and the growing volume of vehicles have made traffic congestion a persistent challenge in modern cities. Efficient traffic flow prediction is essential for mitigating congestion, improving road safety, optimizing traffic signal control, and enhancing overall transportation efficiency. In recent years, artificial intelligence (AI) has emerged as a transformative tool in the field of traffic management, offering sophisticated algorithms capable of modeling, analyzing, and predicting complex traffic patterns with high accuracy. The application of AI in traffic flow prediction leverages vast amounts of real-time and historical data to generate precise forecasts, supporting data-driven decision-making by urban planners and traffic control authorities. The prediction of traffic flow involves analyzing time-series data that exhibit nonlinear, dynamic, and often stochastic behavior. Traditional statistical models, such as autoregressive integrated moving average (ARIMA), have proven to be limited in handling the high dimensionality and variability inherent in traffic systems. In contrast, AI algorithms possess the capacity to learn and adapt from complex data inputs without the need for explicit programming, making them particularly suitable for traffic-related applications. AI algorithms used in traffic flow prediction can be broadly categorized into machine learning (ML) and deep learning (DL) approaches. Machine learning algorithms such as k-nearest neighbors (KNN), support vector machines (SVM), decision trees, and random forests have demonstrated effectiveness in short-term traffic prediction tasks. These algorithms are capable of identifying hidden patterns in traffic data and adjusting to changes in traffic behavior over time. Ensemble methods, which combine the strengths of multiple learning models, further enhance prediction accuracy and robustness. Deep learning algorithms, a subfield of AI inspired by the human brain’s neural architecture, have shown exceptional performance in capturing spatial-temporal dependencies in traffic data. Recurrent neural networks (RNNs), particularly long short-term memory (LSTM) networks and gated recurrent units (GRUs), are widely used for their ability to process sequential data and retain information over extended time intervals. Convolutional neural networks (CNNs) are employed to extract spatial features from traffic sensor data or road network imagery. Hybrid models that integrate CNNs with RNNs have achieved high levels of predictive precision by simultaneously learning spatial and temporal correlations. In addition to supervised learning methods, unsupervised and reinforcement learning techniques are also applied in traffic flow prediction. Clustering algorithms, such as k-means and DBSCAN, assist in identifying traffic patterns, while reinforcement learning models optimize adaptive traffic signal control systems by learning optimal actions through environmental interaction. This study explores the different types of AI algorithms used in traffic flow prediction, examining their theoretical foundations, structural differences, and practical applications. It aims to evaluate the comparative advantages of various algorithms in addressing the challenges of real-time traffic prediction in increasingly complex transportation networks.

This research presents a model for an adaptive traffic signal control system aimed at improving urban traffic regulation. It dynamically adjusts signal timing based on vehicle volume at intersections, prioritizing emergency vehicles by allowing them immediate passage. Utilizing Arduino coding, the system controls traffic light intensity according to the traffic flow, enhancing road safety and efficiency. This innovative approach not only facilitates faster clearance for emergency services without human intervention but also reduces congestion and accident rates. This research creates a model for a prioritized traffic signal control system. When the vehicular volume at the intersection varies, the signal time alters autonomously. It identifies the ambulance/emergency vehicles and allows the green light for emergency vehicles like ambulances, and fire engines. This approach may be used to detect traffic accidents and infractions of automobile spiral motions. When erected on the road, the entire system allows for quick traffic clearing for rescue vehicles without requiring a policeman. The system's design eliminates the need for sensors or radio frequency identification (RFID) tags, simplifying traffic management. Simulations validate that emergency vehicle travel time is significantly reduced, proving the system's effectiveness in streamlining urban traffic flows.

As traffic demand continues to grow in many densely populated urban areas around the world, traffic congestion has become an increasingly critical challenge for transportation agencies to deal with, causing travel delays and environmental pollution. Adaptive traffic signal control systems based on data from associated sensors are used to address the problem. However, often, sensors have errors, such as undercounting actual flows. This dissertation develops an optimization-based methodology, by which undercounted flows by inductive loop detectors can be corrected, and link level travel times can be estimated. The proposed models are validated by both a simulation environment and a real-world case study. Through day-by-day training, the performance of the models improves and stabilizes.The approach is based on a physics-based Traffic Queue model, as a general method for travel time estimation for urban links with typical layouts. A negative binomial regression-based gap inference model is proposed to correct the undercounting error of inductive loop detectors (ILD). The model estimates the number of missing gaps within a time window of one minute. Without ground truth flow count data to train the gap inference model, an optimization platform is proposed to train the model parameters in an indirect way. The model minimizes overall error with respect to link level travel time and flow conservation of intersections. Travel time data are obtained from API such as Google. The proposed approach is validated and illustrated using both simulated and actual data from London, UK. London uses the adaptive control system SCOOT for traffic management. SCOOT ILDs are known to undercount flows under congested conditions. The results show that the model can estimate travel times with good accuracy under heavy congestion, and can tolerate the flow count error up to around 30%. The location-specific model parameters, trained and applied in a day-by-day scenario, show a stabilizing trend and the travel time estimation for online applications improves over time.--Author's abstract

Traffic congestion is a major challenge in urban environments due to increasing vehicle density and inefficient fixed-time traffic signal systems.Traditional traffic lights operate on predefined timers that do not consider real-time traffic conditions, resulting in unnecessary delays, increased fuel consumption, and higher carbon emissions.This paper proposes an Adaptive Traffic Signal Timer system using realtime computer vision and deep learning techniques to dynamically adjust traffic signal timings based on lane-wise vehicle density.The system employs the YOLO (You Only Look Once) object detection algorithm integrated with OpenCV to detect and count vehicles from live video streams.Based on calculated density metrics, optimal green signal durations are assigned dynamically.The proposed system improves traffic flow efficiency, reduces waiting time, and supports intelligent transportation and smart city infrastructure development.

Efficient management of urban traffic is crucial for public safety. The traditional fixed-timing traffic light system presents considerable challenges for the seamless movement of emergency vehicles, notably ambulances. To tackle this problem, our IoT-based solution consists of two essential hardware components: a signal-emitting device integrated into emergency vehicles and a signal-receiving device at traffic signal intersections. These components utilize wireless communication to enable continuous data exchange. On the software front, we’ve developed a sophisticated traffic management system that can receive and process signals from the signal-emitting device, allowing for real-time adjustments to traffic signal timings. Our primary goal with this system is to prioritize emergency vehicles, particularly ambulances, by dynamically altering signal timings based on precise vehicle location and direction. This innovative approach eliminates the need for manual traffic control intervention and greatly enhances the efficiency of emergency vehicle response within the urban traffic environment.

This paper documents the results of a before-after study evaluating the effectiveness of Sydney Coordinated Adaptive Traffic System (SCATS), an adaptive traffic signal control system, implemented on Boulder Highway, an arterial in the Las Vegas urban area. The evaluation was based on comparisons of various performance measures before and after the SCATS system was implemented. Extensive travel time runs were conducted for all the major travel routes within the study network during the weekday and weekend peak periods. Travel times and number of stops were then compared between conventional time-of-day (TOD) coordinated control plans and SCATS control plans. Based on the data collected in this study, the general conclusion was that no significant improvement on arterial progression was achieved with SCATS under normal traffic conditions. However, this conclusion was made based on a major limitation of using video detection in the field, which may have significantly limited the performance of SCATS.

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

An adaptive traffic signal controller (ATSC) combined with a connected vehicle (CV) concept uses real-time vehicle trajectory data to regulate green time and has the ability to improve travel time in a signalized corridor. This study introduces an innovative "slow poisoning" cyberattack for a waiting-time-based ATSC algorithm and a corresponding detection strategy. The objectives of this paper are to (1) develop a "slow poisoning" attack generation strategy for an ATSC and (2) develop a prediction-based "slow poisoning" attack detection strategy using a recurrent neural network—i.e., long short-term memory model. We have generated a "slow poisoning" attack modeling strategy using a microscopic traffic simulator—Simulation of Urban Mobility (SUMO)—and used generated data from the simulation to develop both the attack model and detection model. Our analyses revealed that the attack strategy is effective in creating a congestion in an approach and that our detection strategy can capably flag the attack.

Population is steadily increasing worldwide, resulting in intractable traffic congestion in dense urban areas. Adaptive traffic signal control (ATSC) has shown strong potential to effectively alleviate urban traffic congestion by adjusting signal timing plans in real time in response to traffic fluctuations to achieve desirable objectives (e.g., minimize delay). Efficient and robust ATSC can be designed using a multiagent reinforcement learning (MARL) approach in which each controller (agent) is responsible for the control of traffic lights around a single traffic junction. Applying MARL approaches to the ATSC problem is associated with a few challenges as agents typically react to changes in the environment at the individual level, but the overall behavior of all agents may not be optimal. This paper presents the development and evaluation of a novel system of multiagent reinforcement learning for integrated network of adaptive traffic signal controllers (MARLIN-ATSC). MARLIN-ATSC offers two possible modes: 1) independent mode, where each intersection controller works independently of other agents; and 2) integrated mode, where each controller coordinates signal control actions with neighboring intersections. MARLIN-ATSC is tested on a large-scale simulated network of 59 intersections in the lower downtown core of the City of Toronto, ON, Canada, for the morning rush hour. The results show unprecedented reduction in the average intersection delay ranging from 27% in mode 1 to 39% in mode 2 at the network level and travel-time savings of 15% in mode 1 and 26% in mode 2, along the busiest routes in Downtown Toronto.