Detection-delay-based freeway incident detection algorithms

Even though incident detection algorithms are designed and implemented for quickly detecting incidents, the criterion of mean detection delay has hardly been well defined and utilized in developing and evaluating incident detection algorithms. In addition, most incident detection algorithms do not have an optimal property in terms of detection delay with respect to false alarm rate. In the study presented in this paper, the incident detection problem was formulated as an optimization problem. To implement the algorithm, called the CUSUM algorithm that was derived from the optimization formulation of the incident detection problem, a simplified procedure was developed. Based on this procedure, three varieties of the CUSUM algorithm were developed and tested based on real incident data against a newly defined criterion for mean detection delay. Selected incident detection algorithms were also compared with the CUSUM algorithms. The comparison demonstrates the superiority of the CUSUM algorithms against other selected algorithms in reducing detection delay while maintaining an acceptable detection rate.     

Platoon based cooperative driving model with consideration of realistic inter-vehicle communication

Recent developments of information and communication technologies (ICT) have enabled vehicles to timely communicate with each other through wireless technologies, which will form future (intelligent) traffic systems (ITS) consisting of so-called connected vehicles. Cooperative driving with the connected vehicles is regarded as a promising driving pattern to significantly improve transportation efficiency and traffic safety. Nevertheless, unreliable vehicular communications also introduce packet loss and transmission delay when vehicular kinetic information or control commands are disseminated among vehicles, which brings more challenges in the system modeling and optimization. Currently, no data has been yet available for the calibration and validation of a model for ITS, and most research has been only conducted for a theoretical point of view. Along this line, this paper focuses on the (theoretical) development of a more general (microscopic) traffic model which enables the cooperative driving behavior via a so-called inter-vehicle communication (IVC). To this end, we design a consensus-based controller for the cooperative driving system (CDS) considering (intelligent) traffic flow that consists of many platoons moving together. More specifically, the IEEE 802.11p, the de facto vehicular networking standard required to support ITS applications, is selected as the IVC protocols of the CDS, in order to investigate how the vehicular communications affect the features of intelligent traffic flow. This study essentially explores the relationship between IVC and cooperative driving, which can be exploited as the reference for the CDS optimization and design.     

A new methodology for evaluating incident detection algorithms

We present a novel, off-line approach for evaluating incident detection algorithms. Previous evaluations have focused on determining the detection rate versus false alarm rate curve––a process which we argue is inherently fraught with difficulties. Instead, we propose a cost-benefit analysis where cost mimics the real costs of implementing the algorithm and benefit is in terms of reduction in congestion. We argue that these quantities are of more practical interest than the traditional rates. Moreover, these costs, estimated on training data, can be used both as a mechanism to fine tune a single algorithm as well as a meaningful quantity for direct comparisons between different types of incident detection algorithms. We demonstrate our approach with a detailed example.     

Vehicular Ad-Hoc Networks sampling protocols for traffic monitoring and incident detection in Intelligent Transportation Systems

Vehicular Ad-Hoc Networks (VANETs) are an emerging technology soon to be brought to everyday life. Many Intelligent Transport Systems (ITS) services that are nowadays performed with expensive infrastructure, like reliable traffic monitoring and car accident detection, can be enhanced and even entirely provided through this technology. In this paper, we propose and assess how to use VANETs for collecting vehicular traffic measurements. We provide two VANET sampling protocols, named SAME and TOME, and we design and implement an application for one of them, to perform real time incident detection. The proposed framework is validated through simulations of both vehicular micro-mobility and communications on the 68 km highway that surrounds Rome, Italy. Vehicular traffic is generated based on a large real GPS traces set measured on the same highway, involving about ten thousand vehicles over many days. We show that the sampling monitoring protocol, SAME, collects data in few seconds with relative errors less than 10%, whereas the exhaustive protocol TOME allows almost fully accurate estimates within few tens of seconds. We also investigate the effect of a limited deployment of the VANET technology on board of vehicles. Both traffic monitoring and incident detection are shown to still be feasible with just 50% of equipped vehicles.     

Development of crash prediction models with individual vehicular data

Typical engineering research on traffic safety focuses on identifying either dangerous locations or contributing factors through a post-crash analysis using aggregated traffic flow data and crash records. A recent development of transportation engineering technologies provides ample opportunities to enhance freeway traffic safety using individual vehicular information. However, little research has been conducted regarding methodologies to utilize and link such technologies to traffic safety analysis. Moreover, traffic safety research has not benefited from the use of hurdle-type models that might treat excessive zeros more properly than zero-inflated models.This study developed a new surrogate measure, unsafe following condition (UFC), to estimate traffic crash likelihood by using individual vehicular information and applied it to basic sections of interstate highways in Virginia. Individual vehicular data and crash data were used in the development of statistical crash prediction models including hurdle models. The results showed that an aggregated UFC measure was effective in predicting traffic crash occurrence, and the hurdle Poisson model outperformed other count data models in a certain case.     

Evaluation of the Transferability of Incident Detection Algorithms Developed for Singapore Expressways

ABSTRACT

Two new detection algorithms, single-station DV (dual-variable) and dual-station CODE (COmbined Detector Evaluation) were developed earlier using 160 incidents collected along Singapore's Central Expressway (CTE). The transferability of these CTE-developed algorithms is assessed, as a case study, using 100 incidents collected from the Tullamarine Freeway and South Eastern Freeway in Melbourne, Australia. The investigation covers the differences in traffic detector systems (loop detectors versus video-based), road geometry and behaviour between drivers in Singapore and Australia. The re-calibrated application of these algorithms to freeways in Melbourne yielded a reasonably good detection performance as well as satisfying the average expected performances of seven traffic management centres surveyed in the USA. The results suggested that the detection logic of the algorithms developed for CTE possessed reasonably good transferability and are also suitable for receiving traffic inputs from video-based detectors as well as from loop detectors.     

Effective arterial road incident detection: A Bayesian network based algorithm

Timely and accurate incident detection is an essential part of any successful advanced traffic management system. The complex nature of arterial road traffic makes automated incident detection a real challenge. Stable performance and strong transferability remain major issues concerning the existing incident detection algorithms. A new arterial road incident detection algorithm TSC_ar is presented in this paper. In this algorithm, Bayesian networks are used to quantitatively model the causal dependencies between traffic events (e.g. incident) and traffic parameters. Using real time traffic data as evidence, the Bayesian networks update the incident probability at each detection interval through two-way inference. An incident alarm is issued when the estimated incident probability exceeds the predefined decision threshold. The Bayesian networks allow us to subjectively build existing traffic knowledge into their conditional probability tables, which makes the knowledge base for incident detection robust and dynamic. Meanwhile, we incorporate intersection traffic signals into traffic data processing. A total of 40 different types of arterial road incidents are simulated to test the performance of the algorithm. The high detection rate of 88% is obtained while the false alarm rate of the algorithm is maintained as low as 0.62%. Most importantly, it is found that both the detection rate and false alarm rate are not sensitive to the incident decision thresholds. This is the unique feature of the TSC_ar algorithm, which suggests that the Bayesian network approach is advanced in enabling effective arterial road incident detection.     

Modeling and simulation of vehicle projection arrival–discharge process in adaptive traffic signal controls

Real‐time signal control operates as a function of the vehicular arrival and discharge process to satisfy a pre‐specified operational performance. This process is often predicted based on loop detectors placed upstream of the signal. In our newly developed signal control for diamond interchanges, a microscopic model is proposed to estimate traffic flows at the stop‐line. The model considers the traffic dynamics of vehicular detection, arrivals, and departures, by taking into account varying speeds, length of queues, and signal control. As the signal control is optimized over a rolling horizon that is divided into intervals, the vehicular detection for and projection into the corresponding horizon intervals are also modeled. The signal control algorithm is based on dynamic programming and the optimization of signal policy is performed using a certain performance measure involving delays, queue lengths, and queue storage ratios. The arrival–discharge model is embedded in the optimization algorithm and both are programmed into AIMSUN, a microscopic stochastic simulation program. AIMSUN is then used to simulate the traffic flow and implement the optimal signal control by accessing internal data including detected traffic demand and vehicle speeds. Sensitivity analysis is conducted to study the effect of selecting different optimization criteria on the signal control performance. It is concluded that the queue length and queue storage ratio are the most appropriate performance measures in real‐time signal control of interchanges. Copyright © 2010 John Wiley & Sons, Ltd.     

Vehicular emissions prediction with CART-BMARS hybrid models

Vehicular emission models play a key role in the development of reliable air quality modeling systems. To minimize uncertainties associated with these models, it is essential to match the high-resolution requirements of emission models with up-to-date information. However, these models are usually based on average trip speed, not on environmental parameters like ambient temperature, and vehicle’s motion characteristics, such as speed, acceleration, load and power. This contributes to the degradation of its predictive performance. In this paper, we propose to use the non-parametric Classification and Regression Trees (CART), the Boosting Multivariate Adaptive Regression Splines (BMARS) algorithm and a combination of them in hybrid models to improve the accuracy of vehicular emission prediction using on-board measurements and the chassis dynamometer testing. The experimental comparison between the proposed CART-BMARS hybrid model with the BMARS and artificial neural networks (ANNs) algorithms demonstrates its effectiveness and efficiency in estimating vehicular emissions.     

Experimental evaluation of CAM and DENM messaging services in vehicular communications

The Cooperative Awareness Basic Service and Decentralized Environmental Notification Basic Service have been standardized by the European Telecommunications Standards Institute (ETSI) to support vehicular safety and traffic efficiency applications needing continuous status information about surrounding vehicles and asynchronous notification of events, respectively. These standard specifications detail not only the packet formats for both the Cooperative Awareness Message (CAM) and Decentralized Environmental Notification Message (DENM), but also the general message dissemination rules. These basic services, also known as facilities, have been developed as part of a set of standards in which both ISO and ETSI describe the Reference Communication Architecture for future Intelligent Transportation Systems (ITS). By using a communications stack that instantiates this reference architecture, this paper puts in practice the usage of both facilities in a real vehicular scenario. This research work details implementation decisions and evaluates the performance of CAM and DENM facilities through a experimental testbed deployed in a semi-urban environment that uses IEEE 802.11p (ETSI G5-compliant), which is a WiFi-like communication technology conceived for vehicular communications. On the one hand, this validation considers the development of two ITS applications using CAM and DENM functionalities for tracking vehicles and disseminating traffic incidences. In this case, CAM and DENM have demonstrated to be able to offer all the necessary functionality for the study case. On the other hand, both facilities have been also validated in a extensive testing campaign in order to analyze the influence in CAM and DENM performance of aspects such as vehicle speed, signal quality or message dissemination rules. In these tests, the line of sight, equipment installation point and hardware capabilities, have been found as key variables in the network performance, while the vehicle speed has implied a slight impact.     

A systematic review of route optimisation and pre-emption methods for emergency vehicles

ABSTRACT

Reducing the travel time of emergency vehicles (EVs) is an effective way to improve critical services such as ambulance, fire, and police. Route optimisation and pre-emption are powerful techniques used to reduce EV travel time. This paper presents a systematic literature review of optimisation and pre-emption techniques for routing EVs. A detailed classification of existing techniques is presented along with critical analysis and discussion. The study observes the limitations of existing routing systems and lack of real-world applications of the proposed pre-emption systems, leading to several interesting and important knowledge and implementation gaps that require further investigation. These gaps include optimisations using real-time dynamic traffic data, considering time to travel as a critical parameter within dynamic route planning algorithms, considering advanced algorithms, assessing and minimising the effects of EV routing on other traffic, and addressing safety concerns in traffic networks containing multiple EVs at the same time.     

Simulation assessment of incident detection by cellular phone call-in programs

This research study was designed to assess by simulation the efficacy of incident detection by cellular phone call-in programs. The assessment was conducted by varying the proportion of drivers with cellular phones on the highway so as to mirror the cellular industry statistics that show a continued growth of ownership of cellular phones in the United States. An analytical model, which combined simulation and the limited field data available in the literature, was used to determine measures of effectiveness of the cellular phone-based detection system. The results showed that a cellular phone detection system offers fast incident detection times and higher detection rates for both shoulder and lane blocking incidents. For example, in moderate traffic flow (i.e. 1,550 vehicles per hour per lane), 90 percent of incidents blocking two lanes were detected in 1.5 minutes when the proportion of drivers with cellular phones was one out of 10 drivers, even with only 20 percent of them willing to report incidents. When the current proportion of cellular ownership, i.e. 1 out of 3, was used in the simulation, the detection time improved to 0.8 minutes. The simulation analysis of incident detection by cellular phones also showed that there is a direct relationship between the probability of detection and the detection time; that is, the specification of a higher detection rate resulted in slower detection times. This is in sharp contrast with the results of field study of automatic incident detection (AID) systems which demonstrated an inverse relationship between probability of detection and detection time. This revised version was published online in June 2006 with corrections to the Cover Date.     

Simulator evaluation of incident detection by transponder-equipped vehicles

This paper explores the efficacy of the driver-based incident detection using the vehicle-to-roadside communication (VRC) system. The proliferation of vehicle tags in the US for automatic toll collection, traffic monitoring, and vehicle navigation and information systems has created an infrastructure capable of supporting a driver-based incident detection system. The research reported herein investigated the use of "activatable" vehicle tags by drivers to send an incident signal to the Traffic Management Center through VRC reader stations spaced uniformly on a highway. The simulation results showed that good detection performance was achieved even at lower levels of market penetration of vehicle tags. The results further showed that detection performance is significantly affected by the severity of the incident in terms of number of lanes closed, the spacing of the VRC reader stations, traffic volume at the time of the incident, and the reporting propensity of the traveling public.The performance of the VRC-based incident reporting system was compared to the performance of two incident detection algorithms that rely on traffic data collected through the automatic vehicle identification (AVI) system. The comparison showed that the VRC-based incident reporting system attained shorter detection times and higher detection rates under fairly similar simulated conditions. The paper also discusses issues that need further study through simulation and field experimentation of the VRC-based incident reporting system.     

Real-time motion planning methods for autonomous on-road driving: State-of-the-art and future research directions

Currently autonomous or self-driving vehicles are at the heart of academia and industry research because of its multi-faceted advantages that includes improved safety, reduced congestion, lower emissions and greater mobility. Software is the key driving factor underpinning autonomy within which planning algorithms that are responsible for mission-critical decision making hold a significant position. While transporting passengers or goods from a given origin to a given destination, motion planning methods incorporate searching for a path to follow, avoiding obstacles and generating the best trajectory that ensures safety, comfort and efficiency. A range of different planning approaches have been proposed in the literature. The purpose of this paper is to review existing approaches and then compare and contrast different methods employed for the motion planning of autonomous on-road driving that consists of (1) finding a path, (2) searching for the safest manoeuvre and (3) determining the most feasible trajectory. Methods developed by researchers in each of these three levels exhibit varying levels of complexity and performance accuracy. This paper presents a critical evaluation of each of these methods, in terms of their advantages/disadvantages, inherent limitations, feasibility, optimality, handling of obstacles and testing operational environments.Based on a critical review of existing methods, research challenges to address current limitations are identified and future research directions are suggested so as to enhance the performance of planning algorithms at all three levels. Some promising areas of future focus have been identified as the use of vehicular communications (V2V and V2I) and the incorporation of transport engineering aspects in order to improve the look-ahead horizon of current sensing technologies that are essential for planning with the aim of reducing the total cost of driverless vehicles. This critical review on planning techniques presented in this paper, along with the associated discussions on their constraints and limitations, seek to assist researchers in accelerating development in the emerging field of autonomous vehicle research.     

Generating lane-based intersection maps from crowdsourcing big trace data

Lane-based road information plays a critical role in transportation systems, a lane-based intersection map is the most important component in a detailed road map of the transportation infrastructure. Researchers have developed various algorithms to detect the spatial layout of intersections based on sensor data such as high-definition images/videos, laser point cloud data, and GPS traces, which can recognize intersections and road segments; however, most approaches do not automatically generate Lane-based Intersection Maps (LIMs). The objective of our study is to generate LIMs automatically from crowdsourced big trace data using a multi-hierarchy feature extraction strategy. The LIM automatic generation method proposed in this paper consists of the initial recognition of road intersections, intersection layout detection, and lane-based intersection map-generation. The initial recognition process identifies intersection and non-intersection areas using spatial clustering algorithms based on the similarity of angle and distance. The intersection layout is composed of exit and entry points, obtained by combining trajectory integration algorithms and turn rules at road intersections. The LIM generation step is finally derived from the intersection layout detection results and lane-based road information, based on geometric matching algorithms. The effectiveness of our proposed LIM generation method is demonstrated using crowdsourced vehicle traces. Additional comparisons and analysis are also conducted to confirm recognition results. Experiments show that the proposed method saves time and facilitates LIM refinement from crowdsourced traces more efficiently than methods based on other types of sensor data.     

Towards a generic benchmarking platform for origin–destination flows estimation/updating algorithms: Design,demonstration and validation

Estimation/updating of Origin–Destination (OD) flows and other traffic state parameters is a classical, widely adopted procedure in transport engineering, both in off-line and in on-line contexts. Notwithstanding numerous approaches proposed in the literature, there is still room for considerable improvements, also leveraging the unprecedented opportunity offered by information and communication technologies and big data. A key issue relates to the unobservability of OD flows in real networks – except from closed highway systems – thus leading to inherent difficulties in measuring performance of OD flows estimation/updating methods and algorithms. Starting from these premises, the paper proposes a common evaluation and benchmarking framework, providing a synthetic test bed, which enables implementation and comparison of OD estimation/updating algorithms and methodologies under “standardized” conditions. The framework, implemented in a platform available to interested parties upon request, has been flexibly designed and allows comparing a variety of approaches under various settings and conditions. Specifically, the structure and the key features of the framework are presented, along with a detailed experimental design for the application of different dynamic OD flow estimation algorithms. By way of example, applications to both off-line/planning and on-line algorithms are presented, together with a demonstration of the extensibility of the presented framework to accommodate additional data sources.     

Evaluation of forced flows on freeways with single‐loop detectors

This paper documents the development of a simple method for identifying and/or predicting freeway congestion using single loop detection systems. The proposed algorithm is simple and easy to incorporate into most freeway management systems. The Washington State Department of Transportation's Traffic Systems Management Center (TSMC) sponsored the original study. The investigation also led to a recommendation to replace the original TSMC definition of congestion or forced flow conditions with a more reliable indicator. Although, the TSMC has recently implemented a more advanced prediction system based on fuzzy set theory and neural networks to further identify patterns and rules for ramp metering strategies, the findings presented here continue to be constructive to freeway managers looking for quick and easy analyses that rely solely on single‐loop detection systems. The Seattle Area freeway study section used for the original study was the portion of mainline 1–5 northbound starting at the downtown Seattle Station 108 and ending at the Mountlake Terrace Station 193. Several days' worth of volume and lane‐occupancy data were collected for the afternoon time period from 2:30 p.m. to 6:30 p.m. Time intervals of 20 seconds were chosen for each data collection period. Important products of this research include the following:

• simple, and more reliable criterion for the definition of “bottleneck” or forced flow conditions than that originally used by the TSMC.
• simple, and reliable criterion for predicting impending “bottlenecks” or forced flow conditions.
• A proposed variable for improved selection of the appropriate metering rate. (Further analysis of the use of this variable for determining metering rates is recommended for future studies.

The proposed criteria are simple and easy to incorporate into current freeway management computer systems. Further investigation of freeway performance measurement using volume and occupancy data obtained from single‐loop systems is currently being performed.     

Enhanced cooperative car-following traffic model with the combination of V2V and V2I communication

Vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication are emerging components of intelligent transport systems (ITS) based on which vehicles can drive in a cooperative way and, hence, significantly improve traffic flow efficiency. However, due to the high vehicle mobility, the unreliable vehicular communications such as packet loss and transmission delay can impair the performance of the cooperative driving system (CDS). In addition, the downstream traffic information collected by roadside sensors in the V2I communication may introduce measurement errors, which also affect the performance of the CDS. The goal of this paper is to bridge the gap between traffic flow modelling and communication approaches in order to build up better cooperative traffic systems. To this end, we aim to develop an enhanced cooperative microscopic (car-following) traffic model considering V2V and V2I communication (or V2X for short), and investigate how vehicular communications affect the vehicle cooperative driving, especially in traffic disturbance scenarios. For these purposes, we design a novel consensus-based vehicle control algorithm for the CDS, in which not only the local traffic flow stability is guaranteed, but also the shock waves are supposed to be smoothed. The IEEE 802.11p, the defacto vehicular networking standard, is selected as the communication protocols, and the roadside sensors are deployed to collect the average speed in the targeted area as the downstream traffic reference. Specifically, the imperfections of vehicular communication as well as the measured information noise are taken into account. Numerical results show the efficiency of the proposed scheme. This paper attempts to theoretically investigate the relationship between vehicular communications and cooperative driving, which is needed for the future deployment of both connected vehicles and infrastructure (i.e. V2X).