Traffic Participants Research Articles

Vision-Based Real-Time Online Vulnerable Traffic Participants Trajectory Prediction for Autonomous Vehicle

Vision-Based Real-Time Online Vulnerable Traffic Participants Trajectory Prediction for Autonomous Vehicle

The development and application of the drivers’ attitudes of right-of-way questionnaire (DARQ)

This study explored differences in the right-of-way attitudes of different drivers and the utility of right-of-way attitudes for predicting drivers’ driving behaviors through the development of the Drivers’ Attitudes of Right-of-way Questionnaire (DARQ). DARQ is a tool to judge the negative attitudes of drivers of the right-of-way and hence assist in the selection of excellent professional drivers. Moreover, the study defined drivers’ attitudes of the right-of-way and determines the psychological components of such attitudes. A total of 614 drivers participated in the study. After two tests, the DARQ was established, consisting of assessments of three dimensions: cognition, behavioral tendency, and emotion. We assessed Cronbach’s alpha, split-half reliability, and structural and criterion validity of the questionnaire; the DARQ had a sound theoretical construction and good reliability and validity. Results revealed that professional drivers and professional drivers without accidents had higher correctness of right-of-way attitudes. This shows that the questionnaire had good criterion validity and could be used to effectively screen professional drivers, especially those without accidents. The results also revealed differences in the correctness of drivers’ right-of-way attitudes according to gender, age, and driving experience (cognition and behavioral tendency). Male drivers, older drivers, and experienced drivers had more correct cognitions and behavioral tendencies than did female drivers, young drivers, and novice drivers. Finally, we conducted a third test with 214 drivers. The results revealed that the correctness of drivers’ right-of-way attitudes predicted prosocial and aggressive driving behavior. The higher the correctness of drivers’ right-of-way attitudes (cognition and behavioral tendency), the higher the level of prosocial driving behavior, and the lower the level of aggressive driving behavior. The more positive drivers’ emotions regarding right-of-way attitudes, the higher the level of prosocial driving behavior and the lower level of aggressive driving behavior. The study helps advance the measurement of right-of-way attitudes and automatic driving research. For example, this provides reference data and a model of human traffic participants’ right-of-way attitudes that could help inform research on automatic driving. Moreover, the results of this study could provide guidance for the screening and training of professional drivers, especially professional drivers without accidents, to reduce the rate of traffic accidents.

A qualitative cybersecurity analysis of time-triggered communication networks in automotive systems

Security is gaining increasing importance in automotive systems, driven by technical innovations. For example, automotive vehicles become more open systems, allowing the communication with other traffic participants and road infrastructure. Also, automotive vehicles are provided with increased autonomy which raises severe safety concerns, and consequently also security concerns—both concerns that interweave in such systems.In this paper we present a qualitative cybersecurity analysis by comparing different time-triggered (TT) communication networks. While TT communication networks have been analysed extensively for dependability, the contribution of this work is to identify security-related benefits that TT communication networks can provide. In particular, their mechanisms for spacial and temporal encapsulation of network traffic are instrumental to improve network security. The security arguments can be used as a design guide for implementing critical communication in flexible network standards like TSN.

Falsifying Motion Plans of Autonomous Vehicles With Abstractly Specified Traffic Scenarios

Verifying the safety of autonomous vehicles is one of the major challenges towards their deployment on public roads due to the vast number of possible situations that can occur in traffic. Scenario-based testing has been proposed to reduce the number of required tests using catalogs of abstractly defined scenarios. However, when specifying test scenarios abstractly, there is still an infinite number of possible concrete scenarios that can be derived from a specification. Available computational resources can thus be easily exceeded when using inefficient strategies for deriving concrete scenarios. In this work, we propose a novel method that synthesizes concrete scenarios complying with abstract scenario specifications. We compute the set of compliant trajectories for surrounding traffic participants and only sample trajectories within those sets. Our synthesis integrates a falsification algorithm that searches for specified failures of the vehicle under test. Compared to existing work, we can efficiently find scenario concretizations, especially for complex maneuver specifications. By directly considering failure specifications during the scenario synthesis, we avoid executing irrelevant simulations that cannot possibly result in failures. Our approach is demonstrated in several scenarios using Monte Carlo tree search as a search algorithm.

MetaScenario: A Framework for Driving Scenario Data Description, Storage and Indexing

Autonomous driving related researches require the analysis and usage of massive amounts of driving scenario data. Compared to raw data collected by sensors, scenario data provide a preliminary abstraction of driving tasks and processes, explicitly integrate information about the road environment and the dynamic and static attributes of traffic participants, making it easier to conduct task understanding and decision making. However, many existing driving scenario datasets have the following two problems. First, it is not clear which data fields need to be recorded for driving scenarios. The data storage formats and organization standards are inconsistent. Second, the datasets cannot establish driving scenario indexing effectively. Existing datasets are sparsely annotated and difficult to index, which is detrimental to data sampling and extraction for machine learning process, thus hindering efficient fusion and reuse. In this paper, we propose MetaScenario, a framework for driving scenario data. We describe driving scenarios and design the centralized and unified data framework for the storage, processing, and indexing of scenario data based on relational database. The concept of atom scenario is proposed and characterized using semantic graphs. We also annotate and classify behaviors and interactions of traffic participants in atom scenarios by extracting the spatiotemporal evolution of semantic information. The annotation facilitates the indexing and extraction of data. The scenario datasets are further evaluated via the data distribution and annotation statistics. MetaScenario can provide researchers with convenient tools for scenario data extraction and important analytical references.

The concept of limited mobile objects: civil-legal aspects

The right of ownership and the possibility of using his property for purposes that do not contradict the law, in particular, for entrepreneurial and other activities not prohibited by regulatory and legal acts has been guaranteed to every person. The prescriptions of the legislation regulating public and private relations, in their totality, have created legal limits of the turnover of objects of civil rights, which have been implemented on the main principles and legal principles. At the same time, the issue of limited turnover objects remains an understudied domestic science.
 Only the state, represented by its legislative body, is the subject authorized to determine which objects of civil rights are subject to restriction in civil turnover. At the same time, it should be taken into account that the definition of limited turnover objects is the quintessence of maintaining a balance between public and private interests, and therefore the establishment of special conditions for the turnover of a specific object must be considered and justified.
 In the article, it has been proposed to understand limited movable objects as an independent variety of objects of civil rights, which are capable of passing from one person to another, but due to their specific properties and/or special characteristics, combined with the need for protection from the state, can belong only to certain traffic participants or to be in civilian traffic only under the condition of obtaining a special permit. Also, in view of the provisions of the Civil Code of Ukraine, it seems incorrect to define the types of limited turnover objects at a normatively lower level than the law. Considering this, we support the approach according to which, in order to ensure the certainty of legal regulation, it is necessary to adopt a special law, which will establish a list of restricted objects or bodies that will determine their belonging to restricted circulation.

Case Study on Road Safety Analysis in the Area of Educational Units

The article addresses the topic of road safety in the area of educational units, respectively the effect of road traffic. The aim of the study is to clearly highlight the causality between road accidents involving children as victims and road systematization. To achieve our main objectives, we used as a research method the analysis of documents: Road Accident Database, an application of the Romanian Police in which all traffic incidents registered in Romania are implemented, according to the criteria of Mehedinti County, student quality, road category (national, county, communal), the location of the school unit in the vicinity of the public road and the production of the traffic incident. One of the factors that decisively influences the quality of road traffic, therefore, implicitly the risk in traffic, is the public road network. The specialized studies, as well as the available international statistics, show that the main categories exposed to the risk of road accidents resulting in deaths and serious injuries are: pedestrians, cyclists, motorcyclists, and mopeds, in other words, the category known in specialized practice as "the most vulnerable traffic participants”.

Navigation Data Exchange for Traffic Control

An increase in the number of cars is higher than rates of transport infrastructure development, resulting in a reduction of cargo and passenger transportation efficiency in city conditions. Simulation of flow irregularity in time (peak hour) shows the key role of a car motion interval as a factor of overcoming accumulation at average speed reduction in conditions of highly loaded roads. To reduce the effective time of driver reaction, defining the least distance between cars, it is necessary to minimize the influence of human factors. Automation of the process (unmanned control) requires an effective exchange of navigation and route data between traffic participants. A summary of requirements for such an information exchange system defines the priority of the suggested communication and navigation system (CNS) on the base of radio broadcast communication. Its application gives an opportunity to rise simultaneously traffic safety and efficiency. An increase in neighbor driver action predictability leads to traffic safety ensuring. The exchange of data with traffic control centers (TCC) enables the centralization of motion regulation. A distributed network of transceiver stations forms a local positioning system based on trilateration principles. Algorithms of onboard positioning result verification and automatic resolution of communication conflicts ensure high reliability of CNS functioning. Refusal from point-to-point communication principles allows it to operate even in conditions of high car density up to several thousand per square kilometer. In cooperation with advanced technologies of traffic organization (formation of city highway grid and “total green wave” mode), CNS and TCC are capable of rising the average speed in city conditions higher than 45 km/hour. The aggregate economy of expense on last mile transportation because of the suggested innovations is to be at the level of several GDP percent due to a decrease in accidents and congestion even without accounting for social and ecological effects.

Detection of object throwing behavior in surveillance videos

Anomalous behavior detection is a challenging research area within computer vision. One such behavior is throwing action in traffic flow, which is one of the unique requirements of our Smart City project to enhance public safety. This paper proposes a solution for throwing action detection in surveillance videos using deep learning. At present, datasets for throwing actions are not publicly available. To address the use-case of our Smart City project, we first generate the novel public 'Throwing Action' dataset, consisting of 271 videos of throwing actions performed by traffic participants, such as pedestrians, bicyclists, and car drivers, and 130 normal videos without throwing actions. Second, we compare the performance of different feature extractors for our anomaly detection method on the UCF-Crime and Throwing-Action datasets. Finally, we improve the performance of the anomaly detection algorithm by applying the Adam optimizer instead of Adadelta, and we propose a mean normal loss function that yields better anomaly detection performance. The experimental results reach an area under the ROC curve of 86.10 for the Throwing-Action dataset, and 80.13 on the combined UCF-Crime+Throwing dataset, respectively.

Traffic flow digital twin generation for highway scenario based on radar-camera paired fusion

Autonomous driving is gradually moving from single-vehicle intelligence to internet of vehicles, where traffic participants can share the traffic flow information perceived by each other. When the sensing technology is combined with the internet of vehicles, a sensor network all over the road can provide a large-scale of traffic flow data, thus providing a basis for building a traffic digital twin model. The digital twin can enable the traffic system not only to use past and present information, but also to predict traffic conditions, providing more effective optimization for autonomous driving and intelligent transportation, so as to make long-term rational planning of the overall traffic state and enhance the level of traffic intelligence. The current mainstream traffic sensors, namely radar and camera, have their own advantages, and the fusion of these two sensors can provide more accurate traffic flow data for the generation of digital twin model. In this paper, an end-to-end digital twin system implementation approach is proposed for highway scenarios. Starting from a paired radar-camera sensing system, a single-site radar-camera fusion framework is proposed, and then using the definition of a unified coordinate system, the traffic flow data between multiple sites is combined to form a dynamic real-time traffic flow digital twin model. The effectiveness of the digital twin building is verified based on the real-world traffic data.

MKL-SING: A data-driven approach of sign recognition for managing and improving public services

The detection and identification of traffic signs is a fundamental function of an intelligent transportation system. The extraction or identification of a road sign poses the same problems as object identification in natural contexts: conditions of illumination are variable and uncontrollable, and various objects frequently surround road signs. These difficulties make the extraction of features difficult. The fusion of time and space features of traffic signs is important for improving the performance of sign recognition. Deep learning-based algorithms are time-consuming to train based on a large amount of data. They are difficult to deploy on resource-constrained portable devices and conduct sign detection in real time. The accuracy of sign detection should be further improved, which is related to the safety of traffic participants. To improve the accuracy of feature extraction and classification of traffic signs, we propose MKL-SING, a hybrid approach based on multi-kernel support vector machine (MKL-SVM) for public transportation SIGN recognition. It contains three main components: a principal component analysis for image dimension reduction, a fused feature extractor, and a multi-kernel SVM-based classifier. The fused feature extractor extracts and fuses the time and space features of traffic signs. The multi-kernel SVM then classifies the traffic signs based on the fused features. Different kernel functions in the multi-kernel SVM are fused based on a feature weighting procedure. Compared with single-core SVM, multi-kernel SVM can better process massive data because it can project each kernel function into high-dimensional feature space to get global solutions. Finally, the performance of SVM-TSR is validated based on three traffic sign datasets. Experiment results show that SVM-TSR performs better than state-of-the-art methods in terms of dynamic traffic sign identification and recognition.

Spatial–Temporal Data Imputation Model of Traffic Passenger Flow Based on Grid Division

Traffic flows (e.g., the traffic of vehicles, passengers, and bikes) aim to reveal traffic flow phenomena generated by traffic participants in traffic activities. Various studies of traffic flows rely heavily on high-quality traffic data. The taxi GPS trajectory data are location data that include latitude, longitude, and time. These data are critical for traffic flow analysis, planning, infrastructure layout, and recommendations for urban residents. A city map can be divided into multiple grids according to the latitude and longitude coordinates, and traffic passenger flows data derived from taxi trajectory data can be extracted. However, random missing data occur due to weather and equipment failure. Therefore, the effective imputation of missing traffic flow data is a hot topic. This study proposes the spatio-temporal generative adversarial imputation net (ST-GAIN) model to solve the traffic passenger flows imputation. An adversarial game with multiple generators and one discriminator is established. The generator observes some components of the time-domain and regional traffic data vector extracted from the grid. It effectively imputes the missing values of the spatio-temporal traffic passenger flow data. The experimental data are accurate Kunming taxi trajectory data, and experimental results show that the proposed method outperforms five baseline methods regarding the imputation accuracy. It is significant and suggests the possibility of effectively applying the model to predict the passenger flows in some areas where traffic data cannot be collected for some reason or traffic data are randomly missing.

What should AI see? Using the public’s opinion to determine the perception of an AI

Deep neural networks (DNN) have made impressive progress in the interpretation of image data so that it is conceivable and to some degree realistic to use them in safety critical applications like automated driving. From an ethical standpoint, the AI algorithm should take into account the vulnerability of objects or subjects on the street that ranges from “not at all”, e.g. the road itself, to “high vulnerability” of pedestrians. One way to take this into account is to define the cost of confusion of one semantic category with another and use cost-based decision rules for the interpretation of probabilities, which are the output of DNNs. However, it is an open problem how to define the cost structure, who should be in charge to do that, and thereby define what AI-algorithms will actually “see”. As one possible answer, we follow a participatory approach and set up an online survey to ask the public to define the cost structure. We present the survey design and the data acquired along with an evaluation that also distinguishes between perspective (car passenger vs. external traffic participant) and gender. Using simulation based F-tests, we find highly significant differences between the groups. These differences have consequences on the reliable detection of pedestrians in a safety critical distance to the self-driving car. We discuss the ethical problems that are related to this approach and also discuss the problems emerging from human–machine interaction through the survey from a psychological point of view. Finally, we include comments from industry leaders in the field of AI safety on the applicability of survey based elements in the design of AI functionalities in automated driving.

Operational Design Domain-Driven Coverage for the Safety Argumentation of Automated Vehicles

Automated Vehicles aim to increase road safety as automated driving systems (ADS) take over the human driving task in the operational design domain (ODD), introducing severe challenges for safety validation. Pure driving over many kilometers to gather enough evidence for a safety argument is not feasible. Scenario-based testing is an approach to overcome this, but challenges like parameter discretization still prevail, hindering safety assurance. This work proposes contributions towards a traceable and efficient safety argumentation for ADS built upon ODD coverage. First, ODD coverage is thoroughly quantified across all scenario levels, assuming distribution functions’ availability for the scenario parameters. Secondly, a sampling method for n-dimensional scenario parameter distributions is proposed. The provided algorithms adapt an initial k-means clustering using pre-defined boundary conditions requiring significantly fewer scenarios. Furthermore, a risk metric for urban intersections is presented for scenario evaluation. The risk metric consists of two parts, scene prediction of traffic participants (TPs) and risk assessment. The scene prediction uses a manoeuvre-based motion model with a data-driven approach towards trajectory prediction, increasing the validity. For the risk assessment, a probabilistic risk prediction for the TPs is performed for each scenario scene. The risk metric shows a reasonable tradeoff between sensitivity and specificity, outperforming time-to-collision. These contributions are exemplarily applied at an intersection using a simplified setup for generating TPs and ego vehicle trajectories. The results indicate that an increased safety argumentation is enabled using the proposed methods alongside a coverage process, facilitating further research.

The Conflict Between Pedestrians and Right-turning Vehicles at Signal Intersections from the Psychological Level

With the accelerating urbanization, the urban population growth, road construction by leaps and bounds, the rapid improvement of the road traffic participants formed a fierce contradiction, intersection pedestrians and right turn drivers often conflict, pose a threat to pedestrian traffic safety, also signal the overall operation efficiency and service level has an important influence. The traffic violations of pedestrians and drivers will inevitably be accompanied by a series of psychological activities, and they are dominated by their psychological activities. Therefore, from the perspective of traffic participants’ psychology, it is of great significance to solve the violations of pedestrians and right-turning vehicles from the root cause. Based on psychological theory, survey data, behavioral psychology, traffic psychology, safety psychology, social psychology, criminal psychology and other relevant knowledge, this paper adopts both qualitative and quantitative analysis methods to analyze and study the traffic violations of pedestrians and right-turn vehicle drivers.

Stochastic Model Predictive Control With a Safety Guarantee for Automated Driving

Automated vehicles require efficient and safe planning to maneuver in uncertain environments. Largely this uncertainty is caused by other traffic participants, e.g., surrounding vehicles. Future motion of surrounding vehicles is often difficult to predict. Whereas robust control approaches achieve safe, yet conservative motion planning for automated vehicles, Stochastic Model Predictive Control (SMPC) provides efficient planning in the presence of uncertainty. Probabilistic constraints are applied to ensure that the maximal risk remains below a predefined level. However, safety cannot be ensured as probabilistic constraints may be violated, which is not acceptable for automated vehicles. Here, we propose an efficient trajectory planning framework with safety guarantees for automated vehicles. SMPC is applied to obtain efficient vehicle trajectories for a finite horizon. Based on the first optimized SMPC input, a guaranteed safe backup trajectory is planned using reachable sets. This backup is used to overwrite the SMPC input if necessary for safety. Recursive feasibility of the safe SMPC algorithm is proved. Highway simulations show the effectiveness of the proposed method regarding performance and safety.

On Security and Privacy in Vehicle Speed-Limiting Services in the Internet of Vehicles

Currently, the number of vehicles in road traffic is increasing, which enhances the variety of traffic situations and needs related to road traffic and safety. A cooperative intelligent transport system (C-ITS) can improve road safety and benefit drivers and traffic participants. The C-Roads specification defines many different use cases for informing road vehicles about speed limits, impending danger, road work, signalized intersections, and more. In this article, we propose a new use case targeting the need for Integrated Rescue System services to slow down or stop selected vehicles that are violating rules. Unlike most use cases in C-Roads, in our case, it is not enough to only notify the driver’s vehicle; it must also be slowed down or stopped completely. This intervention requires addressing issues from a technical and a procedural/legal point of view. In this work, we define the use case itself, following the templates of the specification in C-Roads. Then, we discuss the issues in terms of secure communication between vehicles and privacy. We also analyze existing protection security techniques against typical cybersecurity attacks and privacy countermeasures. Next, we propose a system architecture concerning appropriate C-ITS messages and communication between vehicles and present an onboard diagnostics simulator implementing the proposed architecture for the core needs of a given use case. Furthermore, we create a practical demonstrator of our proposal based on real vehicle components. Finally, we discuss open research questions and the ongoing development of the use case before the application on the Internet of Vehicles.

Stochastic Model Predictive Control for Relative-Velocity Based Multimodal Risk Avoidance under a Vehicle Coming Scenarios

The present paper proposes a novel model predictive control (MPC) for generating vehicle trajectories that can apply to environments in which multiple optimal trajectories exist. MPC can recursively generate an optimal trajectory that adapts to intermittently changing traffic conditions. In complicated situations, however, the optimal trajectory is not unique, and such multimodality induces difficulty in finding and determining a suitable trajectory. In order to deal with this issue, we first set up an evaluation function that incorporates collision risk concerning the relative distance, the velocity, and their uncertainties with respect to other traffic participants. Then, we introduce a Monte Carlo MPC (MCMPC) that can handle multimodality and guarantee an upper bound on computational complexity. Using this method, we can achieve real-time driving control that generates a sub-optimal trajectory and opt for acceleration or deceleration according to the situation. The results of numerical simulations and experiments, assuming an overtaking scenario that requires a decision to go ahead or not, show that the proposed controller can cope with a challenging situation and achieve real-time feasibility.

Investigations on Speed Planning Algorithm and Trajectory Tracking Control of Intersection Scenarios Without Traffic Signs

Efficient intersection planning is one of the most challenging tasks for an autonomous vehicle at present. The degree of response to other traffic participants and whether the path tracking effect is good are the key aspects that determine the performance of planning algorithm for an autonomous vehicle. In order to deal with these problems, in this paper, the frame structure of POMDP (Partially Observable Markov Decision Processes) and the time distance coordinate system are combined to carry out the speed planning for the self-propelled vehicle. The speed planning designs a novel POMDP model to ensure effective prediction of behavioral intentions and decision-making at intersections with no traffic signs. Specifically, the method is considered both the driving position and the time range of arrival of the vehicle at the intersection in real-world situations. At the same time, the algorithm is projected the state information into the time distance coordinate system in the form of probability, and used the value iteration method to solve the optimal solution, so as to improve the adaptability of the algorithm to real-world scenarios. Furthermore, MPC control is added on this basis. Rational use of dynamic MPC and kinematic MPC can effectively reduce the tracking error, improve the stability of tracking, and carry out finer control when the speed frequently fluctuates.

A Less-Disturbed Ecological Driving Strategy for Connected and Automated Vehicles

This paper proposes a less-disturbed ecological driving strategy for connected and automated vehicles (CAVs). The proposed strategy integrates the offline planning and the online tracking. In offline planning, an energy efficient reference speed is created based on traffic information (such as the average traffic speed) and characteristics of the vehicle (such as the engine efficiency map) via dynamic programming. The consideration of average traffic speed in speed planning avoids selfish optimisations. In online tracking, model predictive control is employed to update the vehicle speed in real-time to track the reference speed. A key challenge in applying ecological driving strategies in real driving is that the vehicle has to consider other traffic participants when tracking the reference speed. Therefore, this paper combines both longitudinal control and lateral control to achieve better speed tracking by overtaking the preceding vehicle when necessary. The proposed less-disturbed ecological driving strategy has been evaluated in simulations in both single road segment scenario and real traffic environment. Comparisons of the proposed method with benchmark strategies and human drivers are made. The results demonstrate that the proposed less-disturbed ecological driving strategy is more effective in energy saving. Compared to human drivers, the less-disturbed eco-driving strategy improves the fuel efficiency of CAVs by 4.53%.