Mixed Traffic Environment Research Articles

Deep Learning-Based Traffic Safety Solution for a Mixture of Autonomous and Manual Vehicles in a 5G-Enabled Intelligent Transportation System

It is expected that a mixture of autonomous and manual vehicles will persist as a part of the intelligent transportation system (ITS) for many decades. Thus, addressing the safety issues arising from this mix of autonomous and manual vehicles before autonomous vehicles are entirely popularized is crucial. As the ITS system has increased in complexity, autonomous vehicles exhibit problems such as a low intention recognition rate and poor real-time performance when predicting the driving direction; these problems seriously affect the safety and comfort of mixed traffic systems. Therefore, the ability of autonomous vehicles to predict the driving direction in real time according to the surrounding traffic environment must be improved and researchers must work to create a more mature ITS. In this paper, we propose a deep learning-based traffic safety solution for a mixture of autonomous and manual vehicles in a 5G-enabled ITS. In this scheme, a driving trajectory dataset and a natural-driving dataset are employed as the network inputs to long-term memory networks in the 5G-enabled ITS: the probability matrix of each intention is calculated by the softmax function. Then, the final intention probability is obtained by fusing the mean rule in the decision layer. Experimental results show that the proposed scheme achieves intention recognition rates of 91.58% and 90.88% for left and right lane changes, respectively, effectively improving both accuracy and real-time intention recognition and improving the lane change problem in a mixed traffic environment.

A multi-stage stochastic optimization approach to the stop-skipping and bus lane reservation schemes

The bus stop-skipping scheme is designed to reduce the number of stops and increase bus operating speed. But in a mixed traffic environment, buses can hardly maintain a high and stable operating speed due to frequent merging and overtaking activities. In this regard, the exclusive bus lane is used to separate buses from normal traffic. However, the permanent bus lane would inevitably decrease road capacity and result in more congestions along the bus lane, especially during peak hours. This paper proposes a hybrid bus operational scheme combining the bus lane reservation strategy and the stop-skipping control. Considering the uncertainty of passenger demand, this paper proposes a multi-stage stochastic programming model. The evolution of the uncertainty is interpreted by a scenario tree. A progressive hedging-based method is developed to separate the large-scale optimization problem into sub-problems. Two numerical experiments are conducted to verify the proposed model and solution algorithm.

2‐dimensional human‐like driver model for autonomous vehicles in mixed traffic

Classical artificial potential approach of motion planning is extended for emulating human driving behaviour in two dimensions. Different stimulus parameters including type of ego-vehicle, type of obstacles, relative velocity, relative acceleration, and lane offset are used. All the surrounding vehicles are considered to influence drivers' decisions. No emphasis is laid on vehicle control; instead, an ego vehicle is assumed to reach the desired state. The study is on human-like driving behaviour modelling. The developed motion planning algorithm formulates repulsive and attractive potentials in a data-driven way in contrast to the classical arbitrary formulation. Interaction between the stimulus parameters is explicitly considered by using multivariate cumulative distribution functions. Comparison of two-dimensional (lateral and longitudinal) performance indicators with a baseline model and generative adversarial networks indicate the effectiveness and suitability of the developed motion planning algorithm in the mixed traffic environment.

Stability and Environmental Analysis of Mixed Traffic Flow – Using the Markov Probabilistic Theory

The rapid growth of CAV (Connected and Automated Vehicle) market penetration highlights the need to gain insight into the overall stability of mixed traffic flows in order to better deploy CAVs. Several studies have examined the modelling process and stability analysis of traffic flow in a mixed traffic environment without considering its inner spatial distribution. In this paper, an innovative Markov chain-based model is established for integrating the spatial distribution of mixed traffic flow in the model process of car-following behaviour. Then the linear stability analysis of the mixed traffic flow is conducted for different CAV market penetration rates, different CAV platoon strength and different cooperation efficiency between two continuous vehicles. Moreover, several simulations under open boundary conditions in multiple scenarios are performed to explicate how CAV market penetration rate, platoon strength and cooperation efficiency jointly influence the stability performance of the mixed traffic flow. The results reveal that the performance of this mixed traffic flow stability could be strengthened in these three factors. In addition to stability, an investigation of the fuel consumption and emission reduction under different market penetration rates and the platoon strength of CAVs are explored, suggesting that substantial potential fuel consumption and emission could be reduced under certain scenarios.

Interrelationships among predictors of automated vehicle acceptance: a structural equation modelling approach

The study investigated the interrelationships between the UTAUT2 (Unified Theory of Acceptance and Use of Technology) constructs predicting intentions to use driverless automated shuttles. Survey data was gathered from individuals physically experiencing an automated shuttle in a mixed traffic environment on public roads in Trikala (Greece) as part of the CityMobil2 project. Structural equation modelling showed that intentions to use automated shuttles were most strongly driven by hedonic motivation, followed by performance expectancy and social influence. Performance expectancy mediated the relationship between effort expectancy and behavioural intention. This means that people's expectations of how difficult automated shuttles will be to use and their intentions to use them can be explained through their expectations around how these vehicles will perform. Technology savviness was a negative moderator of the relationship between social influence and performance expectancy and facilitating conditions, respectively. Tech-savvy individuals rely less on their social networks to nurture their beliefs that automated shuttles are useful and to have the necessary resources to use automated shuttles. Car use was a negative predictor of the intention to use automated shuttles. Future research should revisit the interrelationships between the UTAUT2 constructs and apply (quasi-) experimental studies to unravel the temporal interaction between constructs.Relevance to human factors/Relevance to ergonomics theoryThe study investigated the interrelationships between the UTAUT2 (Unified Theory of Acceptance and Use of Technology) constructs predicting intentions to use driverless automated shuttles. Survey data from individuals physically experiencing an automated shuttle in Trikala (Greece) as part of the CityMobil2 project was analysed by structural equation modeling. Examining the interrelationships between the UTAUT2 constructs enables us to identify underlying beliefs and devise adequate strategies to promote automated vehicle acceptance. Supplemental data for this article is available online at https://doi.org/10.1080/1463922X.2020.1814446.

Safety evaluation of connected and automated vehicles in mixed traffic with conventional vehicles at intersections

Connected and Automated Vehicles (CAVs) can potentially improve the performance of the transportation system by reducing human errors. This paper investigates the safety impact of CAVs in a mixed traffic with conventional vehicles at intersections. Analyzing real-world AV crashes in California revealed that rear-end crashes at intersections are the dominant crash type. Therefore, to enhance our understanding of the future interactions between human-driven vehicles with CAVs at intersections, a simulation framework was developed to model the mixed traffic environment of Automated Vehicles (AV), cooperative AVs, and conventional human-driven vehicles. In order to model AVs driving behavior, Adaptive Cruise Control (ACC) and cooperative ACC (CACC) models are utilized. Particularly, this study explores system improvements due to automation and connectivity across varying CAV market penetration scenarios. ACC and CACC car following models are used to mimic the behavior of AVs and cooperative AVs. Real-world connected vehicle data are utilized to modify and tune the acceleration/deceleration regimes of the Wiedemann model. Next, the driving volatility concept capturing variability in vehicle speeds was utilized to calibrate the simulation to represent the safety performance of a real-world environment. Two surrogate safety measures are used to evaluate the safety performance of a representative intersection under different market penetration rate of CAVs: the number of longitudinal conflicts and driving volatility. At low levels of ACC market penetration, the safety improvements were found to be marginal, but safety improved substantially with more than 40% ACC penetration. Additional safety improvements can be achieved more quickly through the addition of cooperation and connectivity through CACC. Furthermore, ACC/CACC vehicles were found to improve mobility performance in terms of average speed and travel time at intersections.

TRAFFIC CONFLICT IDENTIFICATION OF E-BIKES AT SIGNALIZED INTERSECTIONS

The increase of e-bikes has raised traffic conflict concerns over past decade. Numerous conflict indicators are applied to measure traffic conflicts by detecting differences in temporal or spatial proximity between users. However, for traffic environment with plenty of e-bikes, these separate space-time approaching indicators may not be applicable. Thus, this study aims to propose a multi-variable conflict indicator and build a conflict identification method for e-bikes moving in the same direction. In particular, by analysing the conflict characteristics from e-bikes trajectories, a multi-variable conflict indicator utilizing change of forecast post encroachment time, change of relative speed and change of distance is derived. Mathematical statistics and cluster discriminant analyses are applied to identify types of conflict, including conflict existence identification and conflict severity identification. The experimental results show: in mixed traffic environments with many e-bikes, compared with time-to-collision and deceleration, accuracy of identifying e-bike conflict types based on proposed method is the highest and can reach more than 90%; that is, multi-variable indicator based on time and space are more suitable for identifying e-bike conflicts than separate space-time approaching indicators. Furthermore, setting of dividing strip between motor vehicle and non-motorized vehicle has significant influence on number and change trend of conflict types. The proposed method can not only provide a theoretical basis and technical support for automated conflict detection in mixed transportation, but also give the safety optimization sequence of e-bikes at different types of intersections.

Detection of Collision-Prone Vehicle Behavior at Intersections Using Siamese Interaction LSTM

As a large proportion of road accidents occur at intersections, monitoring traffic safety of intersections is important. Existing approaches are designed to investigate accidents in lane-based traffic. However, such approaches are not suitable in a lane-less mixed-traffic environment where vehicles often ply very close to each other. Hence, we propose an approach called Siamese Interaction Long Short-Term Memory network (SILSTM) to detect collision prone vehicle behavior. The SILSTM network learns the interaction trajectory of a vehicle that describes the interactions of a vehicle with its neighbors at an intersection. Among the hundreds of interactions for every vehicle, there maybe only some interactions that may be unsafe, and hence, a temporal attention layer is used in the SILSTM network. Furthermore, the comparison of interaction trajectories requires labeling the trajectories as either unsafe or safe, but such a distinction is highly subjective, especially in lane-less traffic. Hence, in this work, we compute the characteristics of interaction trajectories involved in accidents using the collision energy model. The interaction trajectories that match accident characteristics are labeled as unsafe while the rest are considered safe. Finally, there is no existing dataset that allows us to monitor a particular intersection for a long duration. Therefore, we introduce the SkyEye dataset that contains 1 hour of continuous aerial footage from each of the 4 chosen intersections in the city of Ahmedabad in India. A detailed evaluation of SILSTM on the SkyEye dataset shows that unsafe (collision-prone) interaction trajectories can be effectively detected at different intersections.

Cooperative decision-making for mixed traffic: A ramp merging example

The rapid conceptual development and commercialization of connected automated vehicle (CAV) has led to the problem of mixed traffic, i.e., traffic mixed with CAVs and conventional human-operated vehicles (HVs). The paper studies cooperative decision-making for mixed traffic (CDMMT). Using discrete optimization, a CDMMT mechanism is developed to facilitate ramp merging, and to properly capture the cooperative and non-cooperative behaviors in mixed traffic. The CDMMT mechanism can be described as a bi-level optimization program in which state-constrained optimal control-based trajectory design problems are imbedded in a sequencing problem. A bi-level dynamic programming-based solution approach is developed to efficiently solve the problem. The proposed modeling mechanism and solution approach are generic to deterministic decisions and can guarantee system-efficient solutions. A micro-simulation environment is built for model validation and analysis of mixed traffic. The results show that compared to the scenario with 100% HVs, ramp-merging can be smoother in mixed traffic environment. At high CAV penetration, the section throughput increases about 18%. With the proposed CDMMT mechanism, traffic throughput can be further increased by 10–15%. The proposed methods form the basis of traffic analysis and cooperative control at ramp-merging sections under mixed traffic environment.

Influence of Individual Perceptions on the Decision to Adopt Automated Bus Services

The rapid development of automated buses holds great potential for the development of transportation systems. As research into innovative forms of automated transportation systems gains momentum, it is important to understand the public’s perceptions of such public transport systems. Previous studies have contributed based on hypothetical scenarios, but not based on real observations. Based on an online survey in Stockholm in March 2019, the current research addresses this gap by investigating the public’s perceptions from a real, fully operational, automated public transportation service operated in a mixed traffic environment on public roads. The respondents were selected along the automated bus line in Barkabystaden, Stockholm. Our findings indicate that (1) The presence of onboard operators has a positive impact on respondents’ perceived safety, (2) People who have not taken automated buses before have a more negative perception of driving speed of the bus service than people who have taken the buses before, (3) Attitudinal factors, such as public perceptions of safety, driving speed, reliability, and convenience, have a significant influence on the acceptance of the new bus system, (4) As an emerging and innovative transportation mode, automated buses are expected to attract a high share of regular public transportation mode users and the younger generations in the future, (5) Social-demographic characteristics such as gender and income had no significant impacts on the adoption of the new technology. The results provide the characteristics of early bus adopters and their travel behavior and help to prioritize possible investments and allow the policymakers and private industries to identify the special needs of users.

Research on Mandatory Lane-Changing Behavior in Highway Weaving Sections

As the accident-prone sections and bottlenecks, highway weaving sections will become more complicated when it comes to the mixed-traffic environments with connected and automated vehicles (CAVs) and human-driven vehicles (HVs). In order to make CAVs accurately identify the driving behavior of manual-human vehicles to avoid traffic accidents caused by lane changing, it is necessary to analyze the characteristics of the mandatory lane-changing (MCL) process in the weaving area. An analytical MCL method based on the driver’s psychological characteristics is proposed in this study. Firstly, the driver’s MLC pressure concept was proposed by leading in the distance of the off-ramp. Then, the lane-changing intention was quantified by considering the driver’s MLC pressure and tendentiousness. Finally, based on the lane-changing intention and the headway distribution of the target lane, an MLC positions probability density model was proposed to describe the distribution characteristics of the lane-changing position. Through the NGSIM data verification, the lane-changing analysis models can objectively describe the vehicle lane-changing characteristics in the actual scenarios. Compared with the traditional lane-changing model, the proposed models are more interpretable and in line with the driving intention. The results show significant improvements in the lane-changing safe recognition of CAVs in heterogeneous traffic flow (both CAVs and HVs) in the future.

Exploratory Investigation of Disengagements and Crashes in Autonomous Vehicles Under Mixed Traffic: An Endogenous Switching Regime Framework

Autonomous Vehicles (AVs) have a large potential to improve traffic safety but also pose some critical challenges. While AVs may help reduce crashes caused by human error, they still may experience failures of technologies and sensing, as well as decision-making errors in a mixed traffic environment. A disengagement refers to an AV transitioning control from autonomous systems to the trained test driver. The safety critical nature of disengagements makes it imperative to analyze disengagements and crashes together. This study analyzes both crashes and disengagements from real-world AV driving in California to fill the knowledge gap regarding the relationship between disengagements and crashes in a mixed traffic environment. A nested logit model was calibrated using three different outcomes: (1) disengagement with a crash, (2) disengagement with no crash, and (3) no disengagement with a crash. Furthermore, endogenous switching regime models were also calibrated to draw distinctions between the relation of disengagements and crashes while accounting for endogeneity effects. The results show that factors related to AV systems (such as software failures) and other roadway participants increase the propensity of a disengagement without a crash. Furthermore, AVs were observed to disengage less often as the technology matured over time. Marginal effects revealed an 8% decrease. The results thus suggest that disengagements are a part of AVs’ safe performance and disengagement alerts may need to be triggered in order to avoid certain failures with current technology.

Passenger opinions of the perceived safety and interaction with automated shuttles: A test ride study with ‘hidden’ safety steward

Abstract A necessary condition for the effective integration of automated vehicles in our daily lives is their acceptance by passengers inside and pedestrians and cyclists outside the automated vehicle. 119 respondents experienced an automated shuttle ride with a ‘hidden steward on board’ in a mixed traffic environment in Berlin-Schoneberg. A mixed-method approach was applied gathering qualitative interview data during the ride and quantitative questionnaire data after the ride. Responses were classified into three main categories: (1) Perceived safety, (2) interactions with automated shuttles in crossing situations, and (3) communication with automated shuttles. Respondents associated their perceptions of safety with the low speed, dynamic object and event identification, longitudinal and lateral control, pressing the emergency button inside the shuttle, their general trust in technology, sharing the shuttle with fellow travellers, the operation of the shuttle in a controlled environment, and the behaviour of other road users outside the shuttle. Respondents pressed the emergency button inside the automated shuttle on 28 out of 62 test rides in order to test its behavior. They further expected to be more cautious in crossing the road before an automated shuttle due to the lack of eye contact with the human driver and a lack of trust in the behavior of the automated shuttle, and expected road users testing the automated shuttle due to the conservative driving behavior of automated shuttles. We recommend future research into the hypothesis that the acceptance of automated shuttles will be associated with the perceived safety of and their effective and intuitive interaction and communication with both passengers and other road users.

Characterisation of the impacts of autonomous driving on highway capacity in a mixed traffic environment: an agent‐based approach

The current planning and operational analysis tools utilised by researchers and practitioners for transportation facilities evaluation purposes are limited in their relevance to evaluate the future impact of connected and automated vehicles (CAVs). Since CAV technologies are becoming more prevalent on the market, the adaptation of the conventional methodologies to estimate highway performance is becoming essential to accommodate these technologies. This study tries to fill up this gap in the literature by formulating capacity analysis model estimate the potential impacts of CAVs on the capacity of highways at different market penetration (MP) levels of CAVs. The developed analytical model would present itself as a guideline to transportation agencies while developing CAV-based transportation infrastructure. Later, this study proposes an agent-based modelling and simulation framework to address the heterogeneity of drivers behaviour and the potential impact of CAVs on highway traffic performance under different MP levels. Results showed that deploying CAVs in the traffic stream has the potential to double the capacity of the highway corridor at high MP levels. The results show CAV operation and implementation readiness for both public agencies as well as state Departments of Transportation or private industries in the future.

A Division Method of Determining the Early-Warning Zone on an Expressway for Automated Vehicles

Using a cellular automaton model, this paper studied the evolution mechanism of traffic incidents affecting the capacity of urban expressway under the mixed traffic environment of manual driving and automatic driving. It showed that the length of the automated-driving early-warning zone could affect the capacity of expressway. Specifically, the early-warning zone is divided into an accelerate lane-changing area, a decelerate lane-changing area, and a forced lane-changing area. The areas vary according to the distance between the vehicle and the location of incident. Based on the study, this paper establishes a codirectional two-lane cellular automaton model. The analysis showed that the capacity of the urban expressway varies under different combinations of early-warning area length and division ratio of early-warning zone. In the case of two-lane reduction caused by traffic incidents, the capacity of the expressway is optimized when the length of early-warning zone is between 450 and 600 m, and the ratio of accelerate zone, decelerate zone, and forced zone to the length of early-warning zone is, respectively, 75%, 10%, and 15%. In addition, this study showed that the capacity will rise with the increase in automated vehicles.

Pedestrian Crossing Warrants for Urban Midblock Crossings under Mixed-Traffic Environment

AbstractIn recent times, amplified pedestrian-vehicle interaction, especially at urban midblock crossings, have ensued in higher risks and fatalities during pedestrian crossings. This situation fur...

Modeling and field experiments on autonomous vehicle lane changing with surrounding human‐driven vehicles

AbstractAutonomous vehicle (AV) technology is widely studied in both industrial and academic communities since it is regarded as a promising means for improving transportation safety and efficiency. Lane changing is a critical link for higher‐level AV operations. However, few studies on AV lane changing consider the dynamics of surrounding vehicles, particularly in a mixed traffic environment including human‐driven vehicles (HVs). Therefore, this article presents a dynamic lane‐changing model for AV incorporating human driver behavior in mixed traffic. The proposed model includes four key components: car following (and lane keeping), lane‐changing decision, dynamic trajectory generation, and model predictive control (MPC)‐based trajectory tracking. AV longitudinal control algorithm is also depicted in detail in this article. Field experiments are conducted on a large‐scale test track to test and validate the proposed model. An AV and three HVs are used in the lane‐changing experiments. Different human driver behaviors are considered in the experiment settings. Experimental results show that the proposed lane‐changing model can complete lane‐changing maneuvers efficiently when HVs are cooperative and can also robustly abort them when HVs are uncooperative. Compared with the measured human lane‐changing maneuvers, AV lane‐changing maneuvers from the proposed model are more comfortable and safer.

Traffic Conflict Analysis of Motor Vehicles and Nonmotor Vehicles Based on Improved Cellular Automata

In recent years, with the rapid development of China’s logistics industry and urban service industry, electric bicycles have gradually become an important means of transportation in cities due to their flexibility, green technology, and low operating costs. Because electric bicycles travel though motor vehicle lanes and nonmotor vehicle lanes, the conflict between motor and nonmotor vehicles has become increasingly prominent, and the safety situation is not optimistic. However, most theories and models of mixed traffic flow are based on motor vehicles and bicycles and few involve electric bicycles. To explore the traffic safety situation in an urban mixed traffic environment, this paper first uses cellular automata (CA) to establish a three-strand mixed traffic flow model of motor vehicles, electric bicycles, and bicycles and verifies the reliability of the model by using a MATLAB simulation based on the actual survey data. Then, using the technology of traffic conflicts and the conflict rate as the index to evaluate the traffic safety situation, the change in the conflict rate with different road occupancies and different proportional coefficients of motor vehicles is studied. In the end, the conflict rate is compared between the mixed traffic flow and the setting of a physical isolation divider, which provides some suggestions on when to set a physical isolation divider to separate motor vehicles from nonmotor vehicles. The results show that in a mixed traffic environment, the conflict rate first increases and then decreases with increasing road occupancy and reaches a peak when the road occupancy is 0.6. In addition, in mixed traffic environments, the conflict rate increases with an increasing proportional coefficient of the motor vehicle. When the road occupancy rate is within the range of [0.6, 0.9] or when the proportional coefficient of motor vehicle is between [0.8, 0.9], a physical isolation divider can be set to separate motor vehicles and nonmotor vehicles from the space to improve traffic safety.

A Vision-Based Video Crash Detection Framework for Mixed Traffic Flow Environment Considering Low-Visibility Condition

In this paper, a vision-based crash detection framework was proposed to quickly detect various crash types in mixed traffic flow environment, considering low-visibility conditions. First, Retinex image enhancement algorithm was introduced to improve the quality of images, collected under low-visibility conditions (e.g., heavy rainy days, foggy days and dark night with poor lights). Then, a Yolo v3 model was trained to detect multiple objects from images, including fallen pedestrians/cyclists, vehicle rollover, moving/stopped vehicles, moving/stopped cyclists/pedestrians, and so on. Then, a set of features were developed from the Yolo outputs, based on which a decision model was trained for crash detection. An experiment was conducted to validate the model framework. The results showed that the proposed framework achieved a high detection rate of 92.5%, with relatively low false alarm rate of 7.5%. There are some useful findings: (1) the proposed model outperformed empirical rule-based detection models; (2) image enhancement method can largely improve crash detection performance under low-visibility conditions; (3) the accuracy of object detection (e.g., bounding box prediction) can impact crash detection performance, especially for minor motor-vehicle crashes. Overall, the proposed framework can be considered as a promising tool for quick crash detection in mixed traffic flow environment under various visibility conditions. Some limitations are also discussed in the paper.

Deployment of roadside units to overcome connectivity gap in transportation networks with mixed traffic

In the foreseeable future, the traffic stream will be likely mixed with connected automated vehicles (CAVs) and regular vehicles (RVs). In the mixed traffic environment, when following a RV, due to the lack of vehicle-to-vehicle communications, it may take longer time for a CAV to sense and react than a human driver, which results in longer time headway and the loss of highway throughput. To address such a connectivity gap, this paper investigates an infrastructure-based solution, i.e., the deployment of roadside units to help CAVs in the heterogeneous traffic stream. Specifically, it is envisioned that these roadside units can sense vehicles in their coverage areas and provide the beyond-line-of-sight motion information to CAVs to empower them to react proactively, as they would do when following other CAVs. This paper is devoted to the analysis of the impacts of this type of roadside units at a strategic planning stage. In doing so, we first derive an analytical link performance function to capture their impact on the link capacity and travel time, and then develop a network equilibrium model to gauge their effect on travelers’ route choices and thus the flow distribution of both RVs and CAVs across the whole network. This modeling development will allow us to conduct a cost-benefit analysis for a given deployment plan of roadside units. For fair analyses, we further develop an optimization model to determine the optimal deployment plan for a given budget, while focusing on the worst case of its impact, because the flow distribution resulting from our network equilibrium model is not unique. Such a model provides a conservative estimate of the benefit brought by roadside units. Lastly, we offer case studies to demonstrate the models and unveil the potential of such an infrastructure-based solution.