Neighboring Intersections Research Articles

Distributed optimization for multi-commodity urban traffic control

A distributed method for concurrent traffic signal and routing control of traffic networks is proposed. The method is based on the multi-commodity store-and-forward model, in which the destinations are the commodities. The system benefits from the communication between vehicles and infrastructure, providing optimal signal timings to intersections and routes to vehicles on a link-by-link basis. Using the augmented Lagrangian to model the constraints into the objective, the baseline centralized problem is decomposed into a set of objective-coupled subproblems, one for each intersection, enabling the solution to be computed by a distributed-gradient projection algorithm. The intersection agents only need to communicate and coordinate with neighboring intersections to ensure convergence to the optimal solution while tolerating suboptimal iterations that offer more flexibility, unlike other distributed approaches. Through microsimulation, we demonstrate the effectiveness of the proposed algorithm in traffic networks with time-varying demand. Computational analysis shows that the distributed problem is suitable for real-time applications. A robustness analysis show that the distributed formulation enables a graceful degradation of the system in case of failure.

KeyLight: Intelligent Traffic Signal Control Method Based on Improved Graph Neural Network

Graph neural network combined with reinforcement learning is one of the most effective traffic signal control methods. However, existing methods fail to pay enough attention to the key information, such as the traffic information of the downstream section in extracting state and the intersection’s own state in aggregating information from neighbor intersections. As a result, adverse reactions like unstable learning and limited performance occur frequently when agents and models focus on interfering information and useless information too much. In this article, we propose KeyLight, an intelligent traffic signal control method based on reinforcement learning by facilitating the attention of the learning algorithm and model to the key information that is usually ignored. In KeyLight, we design a new state representation NOV-LADLE and introduce residual connection in the graph neural network to highlight the importance of the intersection’s state. Experiments show that, in the case of comparable throughput, the proposed KeyLight has been greatly improved and enhanced in performance. Especially, the average travel time can be increased by up to 23.44% on the real-world dataset.

The Role of Protocadherin γ in Adult Sensory Neurons and Skin Reinnervation.

The clustered protocadherins (cPcdhs) play a critical role in the patterning of several CNS axon and dendritic arbors, through regulation of homophilic self and neighboring interactions. While not explored, primary peripheral sensory afferents that innervate the epidermis may require similar constraints to convey spatial signals with appropriate fidelity. Here, we show that members of the γ-Pcdh (Pcdhγ) family are expressed in both adult sensory neuron axons and in neighboring keratinocytes that have close interactions during skin reinnervation. Adult mice of both sexes were studied. Pcdhγ knock-down either through small interfering RNA (siRNA) transduction or AAV-Cre recombinase transfection of adult mouse primary sensory neurons from floxed Pcdhγ mice was associated with a remarkable rise in neurite outgrowth and branching. Rises in outgrowth were abrogated by Rac1 inhibition. Moreover, AAV-Cre knock-down in Pcdhγ floxed neurons generated a rise in neurite self-intersections, and a robust rise in neighbor intersections or tiling, suggesting a role in sensory axon repulsion. Interestingly, preconditioned (3-d axotomy) neurons with enhanced growth had temporary declines in Pcdhγ and lessened outgrowth from Pcdhγ siRNA. In vivo, mice with local hindpaw skin Pcdhγ knock-down by siRNA had accelerated reinnervation by new epidermal axons with greater terminal branching and reduced intra-axonal spacing. Pcdhγ knock-down also had reciprocal impacts on keratinocyte density and nuclear size. Taken together, this work provides evidence for a role of Pcdhγ in attenuating outgrowth of sensory axons and their interactions, with implications in how new reinnervating axons following injury fare amid skin keratinocytes that also express Pcdhγ.SIGNIFICANCE STATEMENT The molecular mechanisms and potential constraints that govern skin reinnervation and patterning by sensory axons are largely unexplored. Here, we show that γ-protocadherins (Pcdhγ) may help to dictate interaction not only among axons but also between axons and keratinocytes as the former re-enter the skin during reinnervation. Pcdhγ neuronal knock-down enhances outgrowth in peripheral sensory neurons, involving the growth cone protein Rac1 whereas skin Pcdhγ knock-down generates rises in terminal epidermal axon growth and branching during re-innervation. Manipulation of sensory axon regrowth within the epidermis offers an opportunity to influence regenerative outcomes following nerve injury.

An integrated intelligent intersection control system for preventing rear-end and angled crashes: System design and deployment results

In view of the dynamic all-red extension (DARE) system’s effectiveness in preventing angled crashes (Park et al., 2018), this study has further enhanced its function to contend with rear-end collisions with dynamic green extension (DGE). With such a function, the enhanced Integrated Intelligent Intersection control system (III-CS) is capable of dynamically terminating the green at the interval of the lowest rear-end collision risk, so as to prevent undesirable “max-out” under actuated signal control which often traps some vehicles in the dilemma zone during high-volume traffic conditions. To ensure its effectiveness in practice, the proposed III-CS has been designed with the following new features: (i) executing the DGE within a customized time window of the green phase to ensure the signal’s effective coordination with its neighboring intersections; (ii) adopting the comparison-based heuristic for the DGE’s real-time risk prediction so as to circumvent the computing and communications delays. The results of two after-deployment assessments show that the system’s DARE has perfectly detected all red-light runners; 66.7 percent of the decisions by the DGE module were observed to achieve the control objective during the first field assessment. The DGE’s performance in making optimal decisions has improved over time and reached the level of 81.3% in the second field evaluation. Other measures of effectiveness, such as the number of vehicles trapped in the dilemma zone and the average deceleration rate of the driving populations approaching the target intersection, have also evolved to the anticipated trend after the deployment.

GAN and Multi-Agent DRL Based Decentralized Traffic Light Signal Control

Adaptive traffic light signal control (ATSC) is a promising paradigm for alleviating traffic congestion in intelligent transportation systems. Most of the existing methods require heavy traffic data exchange among neighboring intersections to achieve collaborative ATSC, which may not be supported by bandwidth-limited communication links in practice. In this article, we develop a communication-efficient decentralized ATSC framework for traffic networks with multiple intersections, where each intersection only exchanges traffic statistics with its neighboring intersections. In particular, the proposed framework consists of a generative adversarial network (GAN) based algorithm for traffic data recovery, and a multi-agent deep reinforcement learning (DRL) based decentralized ATSC algorithm for traffic efficiency enhancement. By adopting the value decomposition technique that establishes a nonlinear mapping from the local state-action values to the global reward, each intersection can independently determine its traffic light signal based on its local traffic data while achieving collaboration among neighboring intersections. Our proposed decentralized ATSC framework is scalable to large-scale traffic networks, and is also robust to traffic flow variations via interacting with the environment. Simulations show that our proposed algorithm can significantly reduce the vehicle travel time while maintaining high and stable traffic throughput.

Decentralized arterial traffic signal optimization with connected vehicle information

This paper proposes a decentralized signal control algorithm that leverages connected vehicle information to improve traffic operations along arterials. The proposed algorithm obtains real-time vehicle locations and speeds, as well as information on pedestrians waiting to cross individual intersections, to optimize signal phasing and timing plans. Signal timing is optimized at individual intersections; however, information about vehicle platoons passing a given intersection is shared with neighboring intersections to facilitate natural coordination between adjacent intersections. The decentralized algorithm is compared to a centralized algorithm that optimizes signal timing at all intersections simultaneously, as well as a traditional coordination strategy. The proposed algorithm is shown both to be more computationally efficient than the centralized approach and provide better operational performance (in terms of person, vehicle and pedestrian delay) than both the centralized algorithm and the traditional strategy. The algorithm is robust to a range of demand patterns and can be applied under scenarios in which not all vehicles are connected or full information about pedestrian arrivals is not available.

Dynamic Local Vehicular Flow Optimization Using Real-Time Traffic Conditions at Multiple Road Intersections

Dynamic management of vehicular traffic congestion to maximize throughput in urban areas has been drawing increased attention in recent years. For that purpose, a number of adaptive control algorithms have been proposed for individual traffic lights based on the in-flow rate. However, little attention has been given to the traffic throughput maximization problem considering real-time road conditions from multiple intersections. In this paper, we formulate such a problem as maximum integer multi-commodity flow by considering incoming vehicles that have different outgoing directions. Then, we propose a novel adaptive traffic light signal control algorithm which opts to maximize traffic flow through and reduce the waiting time of vehicles at an intersection. The proposed algorithm adjusts traffic light signal phases and durations depending on real-time road condition of local and neighboring intersections. Via SUMO simulation, we demonstrate the effectiveness of the proposed algorithm in terms of traffic throughput and average travel time.

An Intersection Importance Estimation Method Based on the Road Network Topology

Introduction: The expansion of road network and continuous increase of vehicle ownership challenge the performance of routine traffic control. It is necessary to make a balanced adjustment and control from the perspective of the road network to disperse the traffic flow on the entire road network. Methods: This paper develops a method to quantify the intersections’ importance at a global level based on the road network topology, which is the location of the intersection in the road network and the structural characteristics of the intersection decided by the traffic movement. The priority order in traffic signal coordination is the sorting results of intersection’s importance. The proposed method consists of two consecutive algorithms. Firstly, the graph connectivity of network is defined based on the shortest path distance and spatial connectivity between adjacent intersections. Secondly, The Importance Estimation Model (IEM) is built, which is the function of the importance indexes of current intersection and its neighboring intersections. A simulated case of a six by eight grid network was employed to evaluate the effectiveness of the proposed method in TRANSYT. Results and Conclusion: The results show that the Importance Estimation Model (IEM) minimized the measure of effectiveness compared with the schemes obtained by the volume sorting method, the saturation degree sorting method, and the method SMOO. It also created a higher frequency of small queues than the other methods.

Comparison Approach of Intersection Distances for Advanced TOA Trilateration

The time of arrival trilateration method is one of the representative algorithms for the location detection technology, which estimates the location of mobile station (MS) at a unique intersection point of three circles with radiuses corresponding to distances between MS and base stations (BSs) and centers corresponding to coordinates of BSs. However, there may be serious estimation errors, when they do not meet at a point because the estimated radiuses of them are increased. The solutions for reducing the estimation position error in the main case of meeting three circles with the extended radius have been recently provided as the shortest distance algorithm and the line intersection algorithm. In general, they have good performance for the location estimation, but they may have serious errors in some cases. In this paper, we propose the efficient location estimation algorithm for the specific case of two large circles and one relatively small circle, which is located in the area of two large circles. In this case, there are six intersections in total based on the three extended circles and a small circle has four intersections with two large circles. The proposed approach compares four distances based on four neighboring intersections and selects the shortest one. Finally, it determines the averaged coordinate of two intersections corresponding to the shortest distance, as the location of MS. The location-estimating performance of the proposed algorithm is illustrated by the computer simulation example.

Cycle-Length Strategies for a Diverging Diamond Interchange in a Coordinated Arterial

The diverging diamond interchange (DDI) is growing in popularity as an interchange treatment, yet there is rather limited guidance available on signal timing practices. One particular area of concern is the coordination of a DDI along with neighboring intersections in an arterial. This study examines three different cycle length strategies for DDI coordination: (1) using the full cycle length of the corridor; (2) using a half-cycle; and (3) using a previously described three-phase scheme intended to manage queues within the DDI. Six different origin-destination (O-D) scenarios are tested in a microsimulation study. Results are presented in terms of the number of stops, movement delays at the DDI, queue lengths, and delay by O-D path. The outcomes show that the half-cycle strategy yielded lower total and average delays yet resulted in more stops along the arterial and higher arterial O-D path delays. The full-cycle option, meanwhile, tended to achieve fewer stops and lower delays for arterial routes but increased total and average delays for other movements. The three-phase strategy often reduced delays and queue lengths for the arterial movements exiting the DDI, but increased these for other movements.

Emergency Traffic-Light Control System Design for Intersections Subject to Accidents

Petri nets (PNs) are well utilized as a visual and mathematical formalism to model discrete-event systems. This paper uses deterministic and stochastic PNs to design an emergency traffic-light control system for intersections providing emergency response to deal with accidents. According to blocked crossing sections, as depicted by dynamic PN models, the corresponding emergency traffic-light strategies are designed to ensure the safety of an intersection. The cooperation among traffic lights/facilities at those affected intersections and roads is illustrated. For the upstream neighboring intersections, a traffic-signal-based emergency control policy is designed to help prevent accident-induced large-scale congestion. Deadlock recovery, livelock prevention, and conflict resolution strategies are developed. We adopt a reachability analysis method to verify the constructed model. To our knowledge, this is the first paper that employs PNs to model and design a real-time traffic emergency system for intersections facing accidents. It can be used to improve the state of the art in real-time traffic accident management and traffic safety at intersections.

Dynamic Bandwidth Analysis for Coordinated Arterial Streets

A commonly used strategy for improving mobility along signalized arterials is to coordinate neighboring intersections to minimize vehicle stops by maximizing the duration of green bands, otherwise known as arterial bandwidth. Signal coordination has been researched, developed, and refined for five decades. In lieu of traditional methods that are based on the analysis of programmed green times (which assume all phases operate at their maximum settings), a dynamic bandwidth analysis method is presented that reproduces actual dynamic bandwidth durations using closed loop signal data. The analysis is intended to help assess the performance of semi-actuated coordinated signal systems on arterial streets. In addition, the study highlights the arterial progression benefits that result from changing coordinated intersection offsets based on optimizing the dynamic, rather than the programmed, bandwidths. Detailed analysis at three arterial sites revealed that coordinated green phase time distributions are complex and multimodal and cannot be represented by a single-valued statistic. Dynamic bandwidth analysis confirmed that programmed green bandwidth consistently underestimates the size of the actual dynamic bandwidth, and exhaustive search results highlighted the potential for further improvements in coordination. Future research will include field and simulation comparative studies and the development of efficient methods for dynamic bandwidth optimization.

A Signal Timing Method to Reduce the Emissions in Arterials (Case Study: Enghelab Avenue in Ahvaz)

Actuated signal control is very efficient for isolated intersections, but along arterials it lacks the means to synchronize signals, leading to high delays and frequent stops which produce high emissions and fuel consumption. This research aims to use new paradigms based on actuated control that can lead signals to synchronize with their neighboring intersections resulting in reduction of emissions, fuel consumption and travel time in the arterials. In this research, traffic signal coordination software Synchro 8 was used to coordinate the signals on closely spaced intersections in Enghelab avenue in Ahvaz. In order to evaluate the effectiveness of proposed control logic, a simulation test bed was developed in the traffic simulation model SimTraffic 8 and 3D viewer 8.The Proposed logic resulted in total travel time, emissions and fuel consumption reductions of up to 25.6 %, 12.61% and 16.4% respectively compared to current condition logic in Enghelab avenue.

A New Design of Intelligent Traffic Signal Control

Dynamic traffic signal control in Intelligent Transportation System (ITS) recently has received increasing attention. This paper proposed an adaptive and cooperative multi-agentfuzzy system for a decentralized traffic signal control. The proposed model has three levels of control, the current intersection traffic situation, its neighboring intersections recommendations and a knowledge base, which provides the current intersection traffic pattern. The proposed architecture comprises a knowledge base, prediction module and a traffic observer that provide data to real traffic data preparation module, then a decision-making layer takes decision to how long should the intersection green light be extended. Also every intersection flow is predicted in two different ways: 1- through a recursive algorithm. 2- based on a two stage fuzzy clustering algorithm. The proposed solution is tested with traffic control of a large connected junction and the result obtained is promising in comparison to the conventional fixed sequence traffic signal and to the vehicle actuated traffic signal control strategies which are the most applicable strategies in this area. Also to simulate the proposed traffic control solutions, a Netlogo-based traffic simulator has been developed as the agents’ world which simulates the roads, traffic flow and intersections.

Intelligent Traffic Light System to Prioritized Emergency Purpose Vehicles Based on Wireless Sensor Network

The use of Wireless Sensor Network (WSN) has proved to be a very beneficial in the design of adaptive and dynamic traffic light intersection system that will minimize the waiting time of vehicles and also manage the traffic load at the intersection adaptively. In this paper, we propose an adaptive traffic intersection system based on Wireless Sensor Network where the traffic light of one intersection can communicate with the traffic light of the next neighboring intersections and traffic clearance will be prioritized for special vehicles with the help of sensors. General Terms: Wireless Sensor Network.

Traffic Signal Transition in Coordinated Meshed Networks

Transition of signal plans in networks with controlled traffic lights always has a disruptive impact on traffic flow. The extent of these disruptions depends on the transition method, and therefore increases in delay or travel time may be more or less severe. The task of transitioning becomes even more complex in coordinated networks in which new coordination patterns have to be established quickly without inducing major disturbances. Several transition methods exist, some of which are rather abrupt; others are smoother. Many of these methods have been analyzed in simulation studies. Two extensive studies investigated not only transition effects at isolated intersections but also transition effects on coordinated arterials. This paper adds to these studies by investigating transition effects in a meshed network with different coordinated relations. Furthermore, an additional transition method and variations of previously tested methods have been considered. Four scenarios have been set up and simulated. The results of this study are discussed in detail, delivering not only information on the overall performance of each method but also allowing for some further insights into what is happening during transition. Some effects at intersections are induced by transition at that very intersection, while others have to be ascribed to neighboring intersections. Dwell methods are unfavorable for undisturbed transitioning; smooth methods perform better, especially if transition takes no more than three cycles. The results of this study are valuable for both time-of-day signal plan selection and for adaptive traffic control strategies.