Multi-lane Intersections Research Articles

Assessing the impact of communication delays for Autonomous Intersection Management systems

Communication is essential for Cooperative Intelligent Transportation Systems (C-ITS) to achieve better road efficiency, especially for Autonomous Intersection Management (AIM) which coordinates vehicles to pass the intersection safely and efficiently. Communication delays cause severe safety crises (i.e., collisions) and vehicular-performance degradation regarding intersection capacities and vehicular delays. Targeting the delays, network researchers have been working on low-latency communication technologies, and C-ITS researchers have proposed delay-tolerant AIM systems to avoid collisions in intersections. The impacts of communication delays are observed and discussed in the literature; however, models and assessments of the delay requirements for AIM are needed to provide insights for future network and C-ITS research. Here, we model the impact of communication delays on vehicular performance at an autonomous intersection and validate the models with the simulation results from over two million experiments, two types of multi-lane intersections (a typical 4-legged intersection and a roundabout), and four AIM systems. The simulations are conducted with SUMO simulator and AIM systems, where communication delays are inserted into the message exchanges during the simulation. The models are represented in linear, quintic, and cubic polynomials, showing that communication delay between 0 to 100 milliseconds is linearly related to vehicular performance in terms of intersection capacity and vehicular delay. According to the models, we show that by reducing communication delay from 100 to 10 milliseconds, the capacity degradation can be reduced from 7-10% to 0.7-1.0%. Moreover, communication delays must be less than 247 milliseconds to allow AIM systems to outperform traditional traffic lights.

Дослідження безпечності перехрестя з круговим рухом

Roads ensure continuous, safe and convenient movement of vehicles. Intersections play a critical role in the road network in terms of capacity, service level and safety. They are designed in different sizes for different purposes and conditions and have their own defining characteristics that can affect their safety and ease of use.
 Particular attention is paid to roundabouts - where traffic slows down and becomes a one-way flow around a central island. Additional entrance and roundabout lanes improve transportation efficiency, but they also have an impact on safety. The safety disadvantage can be due to inappropriate driver behavior when approaching, circling, and exiting the intersection, as well as weaving maneuvers within the roundabout.
 The concept of turbo-roundabouts has emerged as a possible alternative to conventional multi-lane intersections, but the analysis of studies does not allow us to draw definitive conclusions about their effectiveness and safety, so it is recommended that such studies be conducted for specific road conditions.
 The paper proposes a design of a turbo-roundabouts to improve safety without reducing its efficiency at the intersection of international highways (European route E40 «Kyiv–Chop» and E85 «Domanove-Kovel-Chernivtsi-Terebleche») near the city of Dubno, where traffic accidents regularly occur.
 Among the different types of turbo-roundabouts, the basic turbo-roundabouts with a maximum capacity of up to 2,500 vehicles per hour and the largest traffic flow is taken as a basis.
 All geometric parameters correspond to the average size of a turbo intersection, take into account the overall dimensions of the truck, the speed of traffic and are built in accordance with the recommendations of regulatory documents of European countries specializing in their design.
 The designed turbo intersection with circular traffic has the best comparative option and will reduce the overall accident rate by 36 % and the number of injured people by 34 %.

A General Framework for Decentralized Safe Optimal Control of Connected and Automated Vehicles in Multi-Lane Signal-Free Intersections

We address the problem of optimally controlling Connected and Automated Vehicles (CAVs) arriving from four multi-lane roads at a signal-free intersection where they conflict in terms of safely crossing (including turns) with no collision. The objective is to jointly minimize the travel time and energy consumption of each CAV while ensuring safety. This problem was solved in prior work for single-lane roads. A direct extension to multiple lanes on each road is limited by the computational complexity required to obtain an explicit optimal control solution. Instead, we propose a general framework that first converts a multi-lane intersection problem into a decentralized optimal control problem for each CAV with less conservative safety constraints than prior work. We then employ a method combining optimal control and control barrier functions, which has been shown to efficiently track tractable unconstrained optimal CAV trajectories while also guaranteeing the satisfaction of all constraints. Simulation examples are included to show the effectiveness of the proposed framework under symmetric and asymmetric intersection geometries and different CAV sequencing policies.

Autonomous navigation at unsignalized intersections: A coupled reinforcement learning and model predictive control approach

This paper develops an integrated safety-enhanced reinforcement learning (RL) and model predictive control (MPC) framework for autonomous vehicles (AVs) to navigate unsignalized intersections. Researchers have extensively studied how AVs drive along highways. Nonetheless, how AVs navigate intersections in urban environments remains a challenging task due to the constant presence of moving road users, including turning vehicles, crossing or jaywalking pedestrians, and cyclists. AVs are thus required to learn and adapt to a dynamically evolving urban traffic environment. This paper proposes a design benchmark that allows AVs to sense the real-time traffic environment and perform path planning. The agent dynamically generates curves for feasible paths. The ego vehicle attempts to follow these paths under specific constraints. RL and MPC navigation algorithms run in parallel and are suitably selected to enhance ego vehicle safety. The ego AV is modeled with lateral and longitudinal dynamics and trained in a T-intersection using the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm under various traffic scenarios. It is then tested on a straight road and a single or multi-lane intersections. All these experiments achieve desirable outcomes in terms of crash avoidance, driving efficiency, comfort, and tracking accuracy. The developed AV navigation system provides a design benchmark for an adaptive AV that can navigate unsignalized intersections.

Integrated decision and control at multi-lane intersections with mixed traffic flow

Autonomous driving at intersections is one of the most complicated and accident-prone traffic scenarios, especially with mixed traffic participants such as vehicles, bicycles and pedestrians. The driving policy should make safe decisions to handle the dynamic traffic conditions and meet the requirements of on-board computation. However, most of the current researches focuses on simplified intersections considering only the surrounding vehicles and idealized traffic lights. This paper improves the integrated decision and control framework and develops a learning-based algorithm to deal with complex intersections with mixed traffic flows, which can not only take account of realistic characteristics of traffic lights, but also learn a safe policy under different safety constraints. We first consider different velocity models for green and red lights in the training process and use a finite state machine to handle different modes of light transformation. Then we design different types of distance constraints for vehicles, traffic lights, pedestrians, bicycles respectively and formulize the constrained optimal control problems (OCPs) to be optimized. Finally, reinforcement learning (RL) with value and policy networks is adopted to solve the series of OCPs. In order to verify the safety and efficiency of the proposed method, we design a multi-lane intersection with the existence of large-scale mixed traffic participants and set practical traffic light phases. The simulation results indicate that the trained decision and control policy can well balance safety and tracking performance. Compared with model predictive control (MPC), the computational time is three orders of magnitude lower.

Cooperative signal-free intersection control using virtual platooning and traffic flow regulation

The emerging technologies of connectivity and automation enable the potential for signal-free intersection control. In this context, virtual platooning is posited to be an innovative, decentralized control strategy that maps two-dimensional vehicle movements onto a one-dimension virtual platoon to enable intersection operations. However, the effectiveness of virtual platooning-based control can be limited or degraded by parametric inaccuracies and unparameterized disturbances in vehicle dynamics, heavy traffic congestion, and/or uncoordinated platoons in multi-lane intersections. To explicitly address these limitations, this study proposes a hybrid cooperative intersection control framework consisting of microscopic-level virtual platooning control and macroscopic-level traffic flow regulation for traffic environments with connected autonomous vehicles. In virtual platooning control, vehicles approaching an intersection are organized into coordinated independent virtual platoons to avoid potential conflicts triggered by platoon formation changes. Through coordination, vehicles in a platoon are grouped into compatible passing sets to maintain desired safe spacing when proceeding through the intersection. We propose a distributed adaptive sliding mode controller (DASMC) which uses the backstepping control method and model reference adaptive control method to address parametric inaccuracies, and the sliding mode control method to consistently suppress the negative effects of the unparameterized disturbances. Each vehicle approaching the intersection utilizes the kinematic information from neighboring vehicles to implement the DASMC in a distributed manner such that vehicles within the same virtual platoon can achieve consensus safely. However, virtual platooning control cannot preclude excessive traffic from approaching the intersection, which can cause undesired spillbacks and degrade intersection control performance. To address this issue, traffic flow regulation is integrated with the virtual platooning control using an iterative feedback loop mechanism. In each iteration of the iterative feedback loop, a constrained finite-time optimal control (CFTOC) problem is solved to determine the optimal input flow permitted to proceed through the intersection, and the virtual platooning control provides feedback on the queue status to the CFTOC to initiate the next iteration. The effectiveness of the proposed intersection control framework is evaluated through numerical experiments. The results indicate that the proposed virtual platooning DASMC controller can mitigate the effects of parametric inaccuracies and unparameterized disturbances to achieve consensus for approaching vehicles, as well as guarantee string stability. Further, the proposed framework can alleviate traffic spillbacks and travel delays effectively through traffic flow regulation.

Scheduling-Based Optimization for Motion Coordination of Autonomous Vehicles at Multilane Intersections

This paper considers the motion coordination problem of autonomous vehicles in an intersection of a traffic network. The featured challenge is the design of an intersection traffic manager, in the form of a supervisory control algorithm, that regulates the motion of the autonomous vehicles in the intersection. We cast the multivehicle coordination task as an optimization problem, with a one-dimensional search-space. A model- and optimization-based heuristic method is employed to compute the control policy that results in the collision-free motion of the vehicles at the intersection and, at the same time, minimizes their delay. Our approach depends on a computation framework that makes the need for complex analytical derivations obsolete. A complete account of the computational complexity of the algorithm, parameterized by the configuration parameters of the problem, is provided. Extensive numerical simulations validate the applicability and performance of the proposed autonomous intersection traffic manager.

Space Distribution Method for Autonomous Vehicles at a Signalized Multi-Lane Intersection

Under the connected vehicle environment, autonomous vehicles (AVs) could bring numerous advantages including: improving the traffic flow, enhancing safety and alleviating air pollution. However, optimally operating AVs at signalized multi-lane intersections is a challenging problem due to the complex interaction of vehicles between lanes. It is thus a desire to manage and control the dynamics of AVs at signalized multi-lane intersections. To this end, this paper puts forward a bi-level control framework to optimize the intersection throughput. In our proposed method, the upper level (i.e. the intersection controller) is used to optimize the lane usages of each approach and the AVs' positions. In contrast, the lower level (i.e. the vehicle controllers) receives information from the upper level to control the AVs to get the maximum speed. More specifically, in the upper level, we apply a novel Space Distribution Method (SDM) for the AVs to maximize the throughput (i.e. a number of AVs) of the (multi-lane) intersection where signal timings are predefined. The SDM is divided into three steps: i) platoon formulation; ii) lane-mode optimization; and iii) AVs' position distribution. To maximize the throughput, the intersection controller receives information about the states of the AVs (e.g. the trajectories), then optimizes the lane usages for each approach, the desired speed, and the gap of the AVs as well as the AV's position along the approach. After that, each AV which is allowed to cross the intersection will determine its own trajectory and travel with the scheduled time without crash. Numerical simulations are set up to show that the throughput increases significantly, even more than twice of the throughput obtained from other methods in some circumstances.

Design and Analysis of Delay-Tolerant Intelligent Intersection Management

The rapid development of vehicular network and autonomous driving technologies provides opportunities to significantly improve transportation safety and efficiency. One promising application is centralized intelligent intersection management, where an intersection manager accepts requests from approaching vehicles (via vehicle-to-infrastructure communication messages) and schedules the order for those vehicles to safely crossing the intersection. However, communication delays and packet losses may occur due to the unreliable nature of wireless communication or malicious security attacks (e.g., jamming and flooding), and could cause deadlocks and unsafe situations. In our previous work, we considered these issues and proposed a delay-tolerant intersection management protocol for intersections with a single lane in each direction. In this work, we address key challenges in efficiency and deadlock when there are multiple lanes from each direction, and propose a delay-tolerant protocol for general multi-lane intersection management. We prove that this protocol is deadlock free, safe, and satisfies the liveness property. Furthermore, we extend the traffic simulation suite SUMO with communication modules, implement our protocol in the extended simulator, and quantitatively analyze its performance with the consideration of communication delays. Finally, we also model systems that use smart traffic lights with various back-pressure scheduling methods in SUMO, including the basic back-pressure control, the capacity-aware back-pressure control, and the adaptive max-pressure control. We then compare our delay-tolerant intelligent intersection protocol with smart traffic lights that use the three back-pressure scheduling methods, in the case of a network of interconnected intersections. Simulation results demonstrate that our approach significant outperforms the smart traffic lights under normal operation (i.e., when the communication delay is not too large).

Crossroads+

As vehicles become autonomous and connected, intelligent management techniques can be utilized to operate an intersection without a traffic light. When a Connected Autonomous Vehicle (CAV) approaches an intersection, it shares its status and intended direction with the Intersection Manager (IM), and the IM checks the status of other CAVs and assigns a target velocity/reference trajectory for it to maintain. In practice, however, there is an unknown delay between the time a CAV sends a request to the IM and the moment it receives back the response, namely, the Round-Trip Delay (RTD). As a result, the CAV will start tracking the target velocity/reference trajectory later than when the IM expects, which may lead to accidents. In this article, we present a time-aware approach, Crossroads+, that makes CAVs’ behaviors deterministic despite the existence of the unknown RTD. In Crossroads+, we use timestamping and synchronization to ensure that both the IM and the CAVs have the same notion of time. The IM will also set a fixed start time to track the target velocity/reference trajectory for each CAV. The effectiveness of the proposed Crossroads+ technique is illustrated by experiments on a 1/10 scale model of an intersection with CAVs. We also built a simulator to demonstrate the scalability of Crossroads+ for multi-lane intersections. Results from our experiments indicate that our approach can reduce the position uncertainty by 15% in comparison with conventional techniques and achieve up to 36% better throughputs.

Effectiveness of adaptive control of traffic light intersection on isolated multi-lane intersections

The use of information technology in traffic management can increase the capacity of traffic intersections and reduce vehicle delays. In cities, adaptive traffic control at traffic lights intersections has been well established. Adaptive regulation is applied mainly on isolated traffic lights, where the traffic flow has a predominantly exponential distribution of intervals. It was established experimentally that the effectiveness of the method decreases with a supersaturated traffic flow, which makes it difficult to find a “cutoff point”, a convenient moment for switching the traffic light signal. The article shows that at isolated multi-band intersections, the search for a convenient signal switching time is difficult at low loading levels. At uninsulated intersections, the incoming flow will have clear periods of time without vehicles, which makes the operation of adaptive traffic control in these conditions at a multi-lane crossing more efficient. This suggests the need for further study of the patterns of distribution of intervals between cars in urban environments at the approaches to non-isolated intersections and at the approach to intersections operating without coordination with other traffic lights.

On‐line vehicle detection at nighttime‐based tail‐light pairing with saliency detection in the multi‐lane intersection

A nighttime vehicle detection method in the multi-lane intersection has been proposed based on saliency detection for traffic surveillance system in this study. Frame difference method is applied to detect moving objects at first, and all the rear lights of vehicles are extracted based on saliency map and colour information. Second, vehicles are detected through pairing off all the lamps, which include such steps as rechecking tail-lamp pairs by using prior knowledge, eliminating repaired tail-lamps on the same vehicle and removing the paired lamps across two lanes. Furthermore, to detect the vehicles that only have a single valid tail-lamp, a proving approach for virtual tail-lamp is investigated. Finally, the proposed method is verified to be more reliable and faster for nighttime vehicle detection by comparing with other detection methods, which can satisfy real-time requirements of a vehicle detection system with good performance.

Dynamical Systems and Network Flows: Traffic Flow Problem on Multi-lane Intersections (Economic Analysis)

Nowadays due to rapid population growth and hence increasing demand for transportation, traffic congestion at road intersections become a serious problem for developed as well as developing countries. Traffic congestion causes considerable costs due to unproductive time losses, extra fuel consumption, accidents and also has a negative impact on the environment such as air pollution, noise and stress. Thus, economic analysis of multi-lane intersections and improvement alternatives take account of vehicles cost of fuel consumption and time costs incurred by users of the road junctions. The objective of this study was about determining average waiting time of vehicles and estimating cost incurred due to delay at unsignalized double lane roundabouts and signalized cross intersections. In this study MMAS Cellular Automata model and Poisson queuing model were used. The study tried to calculate the average waiting time (delay) of vehicles in the system (in queue plus in service) at both types of road intersections. The study was tried to quantify vehicles waiting time at both types of road intersections (cost incurred due to delay); that is cost of time lost for passengers and cost of extra fuel consumed by vehicles. Based on the findings of the study, that is based on time and fuel lost (though other factors are not included), signalized cross intersections are better than roundabouts to minimize traffic congestion problem at road junctions.

Efficiency of Roundabouts as Compared to Traffic Light Controlled Intersections in Urban Road Networks

Evaluating the performance of a multi-lane intersection is important to identify the best scheme as congestion is becoming a worldwide serious problem. A Multi-stream Minimum Acceptable Space (MMAS) Cellular Automata (CA) model is used for the simulation of vehicular traffic at double-lane roundabouts and cross intersection. Comparison is made between roundabouts with traffic light and without traffic light and signalized intersections on the basis of their performance to simplify traffic congestion. Computer simulations are used to propose critical arrival rates to separate between the three mentioned modes to decrease congestion at intersection points.

Performance Analysis of Basic Turbo-Roundabouts in Urban Context

A turbo roundabout is a new type of canalized multilane intersection in which the physical separation between lanes helps to prevent side collisions when crossing the roundabout. This paper presents an estimation of capacity, delays and level of service of basic turbo roundabouts in undersaturation conditions, considering both vehicle flow and pedestrian traffic. The traffic performance model was developed by evaluating the capacity for each entry lane. Owing to the geometric features of the intersection, the total entry capacity is obtained by considering different values of the pedestrian impedance factor and degree of saturation at both the right-turn and left-turn lanes.

Lane Volume and Saturation Flow Rate for Multilane Intersection Approach

One factor that can reduce a lane's saturation flow to less than ideal conditions is when turning vehicles share the lane with through vehicles. The slow discharge rate of the turning vehicles reduces the lane's effective saturation flow rate in direct proportion to the percentage of turn vehicles in it. A model is described that predicts this percentage and the resulting saturation flow rate of the shared lane. Based on the results of this research, it is believed that the proposed model accurately predicts the lane volume for any approach to a signalized intersection and the uncontrolled approach to an unsignalized intersection. The model extends previous models by incorporating a sensitivity to both left- and right-turn movements and the probability of a lane change into a closed-form solution. Some field data are used to validate the proposed model.