Real-time regional path decision method in cooperative vehicle infrastructure system

Impact of early-stage cooperative vehicle infrastructure systems on traffic and energy consumption under various traffic conditions: From application to policy

Unknown remaining time of signal phase at a signalized intersection generally results in extra accelerations and decelerations that increase variations of operating conditions and thus emissions. A cooperative vehicle-infrastructure system can reduce unnecessary speed changes by establishing communications between vehicles and the signal infrastructure. However, the environmental benefits largely depend on drivers’ compliance behaviors. To quantify the effects of drivers’ compliance rates on emissions, this study applied VISSIM 5.20 (Planung Transport Verkehr AG, Karlsruhe, Germany) to develop a simulation model for a signalized intersection, in which light duty vehicles were equipped with a cooperative vehicle-infrastructure system. A vehicle-specific power (VSP)-based model was used to estimate emissions. Based on simulation data, the effects of different compliance rates on VSP distributions, emission factors, and total emissions were analyzed. The results show the higher compliance rate decreases the proportion of VSP bin = 0, which means that the frequencies of braking and idling were lower and light duty vehicles ran more smoothly at the intersection if more light duty vehicles complied with the cooperative vehicle-infrastructure system, and emission factors for light duty vehicles decreased significantly as the compliance rate increased. The case study shows higher total emission reductions were observed with higher compliance rate for all of CO2, NOx, HC, and CO emissions. CO2 was reduced most significantly, decreased by 16% and 22% with compliance rates of 0.3 and 0.7, respectively.

Video application is a research hotspot in cooperative vehicle-infrastructure systems (CVIS) which is greatly related to traffic safety and the quality of user experience. Dealing with large datasets of feedback from complex environments is a challenge when using traditional video application approaches. However, the in-depth structure of deep learning has the ability to deal with high-dimensional data sets, which shows better performance in video application problems. Therefore, the research value and significance of video applications over CVIS can be better reflected through deep learning. Firstly, the research status of traditional video application methods and deep learning methods over CVIS were introduced; the existing video application methods based on deep learning were classified according to generative and discriminative deep architecture. Then, we summarized the main methods of deep learning and deep reinforcement learning algorithms for video applications over CVIS, and made a comparative study of their performances. Finally, the challenges and development trends of deep learning in the field were explored and discussed.

As one of the most important part of the modern comprehensive transportation system, highway plays a critical role in national traffic system, which bears the most of traffic load. Whereas, ramp areas may become bottleneck areas of highway if the control is inappropriate or ineffective. The cooperative vehicle infrastructure system (CVIS) brings great opportunities for ramp control to address many tricky problems, among which the merging control of on-ramp vehicles is one of the most prominent problem related to traffic efficiency and safety. In this paper, we apply the technology of cooperative vehicle infrastructure control in the highway ramp area to enhance the traffic efficiency and safety, and propose a merging control method for on-ramp vehicles. At last, a simulation is conducted to evaluate this control method.

The ability of edge computing determines the effectiveness of the cooperative vehicle-infrastructure system to improve traffic safety, efficiency and capacity, enabling traditional information release method have backstage processing and distribution. It is converted to vehicle, road and backstage after being processed by edge computing algorithm. Vehicles are timely and effectively controlled and induced. Based on the full analysis of the development status at home and abroad and the analysis of actual engineering needs, this paper proposes the composition of the cooperative vehicle-infrastructure system and the main factors affecting edge computing, studies the existing edge computing methods, and finally combines the current smart highway demonstration projects. The actual needs put forward the cooperative vehicle-infrastructure use case research based on edge computing. The use case analysis has significant guiding role for the design, R&D and engineering implementation of the smart highway cooperative vehicle-infrastructure system in China.

Collaboration between infrastructures and connected and autonomous vehicles (CAVs) at unsignalised intersections has emerged as an effective strategy for improving transportation efficiency. To enhance the safety and efficiency of CAVs passing through unsignalised intersections, this paper proposes a cooperative vehicle-infrastructure system (CVIS) based multi-vehicle trajectory planning architecture. The architecture comprises a roadside planner and vehicle planners. The roadside planner formulates the problem of generating multi-vehicle trajectories as an optimisation task and addresses it using an improved particle swarm optimisation (PSO) approach along with a space-time voxels strategy to determine the times for vehicles to reach the intersection and the trajectories passing through it. Then, the vehicle planner plans according to the results of the roadside planner. The results show that our approach enables potentially conflicting CAVs to pass through unsignalised intersections without stopping and waiting, ensuring safety while improving traffic efficiency.

As the trend of the new generation of intelligent transportation systems, the application of the cooperative vehicle-infrastructure system (CVIS) is important to reduce traffic congestion and accidents. For the cooperative vehicle-infrastructure system, the roadside unit (RSU) is a new application without enough deployment experience. Meanwhile the deployment of traditional mechanical and electrical infrastructure is generally based on experience and is easy to change the design. This paper analyzes the key technical parameters of RSU and the Digital Measurable Image (DMI) method in context of the CVIS. After collecting field data from a smart highway pilot project (the Deqing-Fuyang expanded Huzhou section in Chang-Shen Highway) and matching the DMI method with highway mileage pile numbers, an RSU deployment scheme based on DMI data was completed. It provides significant support for smart highway demonstration projects with cooperative vehicle-infrastructure intelligent management and control applications.

The premise of implementing an effective traffic control strategy is the accurate traffic state recognition. In the existing study, traffic state recognition methods were processed by using statistical characteristics and long-term scale detection of field traffic data. Hence, the dynamic characteristics and subtle changes in traffic flow were easy to overlook. At present, more and more advanced traffic detection technology provides reliable and accurate data for measuring and distinguishing the state of urban road traffic, such as the cooperative vehicle-infrastructure system, wide-area radar technology, and 5G technology. This study proposes a novel method called HTSI (High Precision Traffic State Identification Method), which is based on the advanced detection technology in traffic state recognition at the intersection: The raw data used for intersection traffic state recognition is high-precision detection data of tracking characteristics, which make the data look like a picture of the intersection at God’s perspective. To this end, we construct an image model for intersections and implement image feature extraction in a way that is different from traditional image processing. Then, the traffic state recognition problem at the intersection is translated into an image searching problem with tags. The image searching is realized by the hashing algorithm. Finally, the comprehensive experiments prove that the proposed method is more accurate and finer than other methods.

A distributed dynamic route guidance approach based on short-term forecasts in cooperative infrastructure-vehicle systems

Development and experiment of an intelligent connected cooperative vehicle infrastructure system based on multiple V2I modes and BWM-IGR method

The advent of Web 2.0 has contributed to the development of adaptive learning by expanding its possibilities for interaction such as personalization; It has also enabled it to involve a considerable variety of artificial intelligence technologies. An adaptive learning system allows the presentation of learning materials to be tailored to needs, the characteristics and learning styles of learners and the dynamic change in the learning environment, by offering them personalized paths in real time and predicting dynamic learning situations. To ensure this intelligent customization and improve the quality of adaptation, we propose an architecture of a Multi-Agent adaptive learning system based on Incremental Hybrid Case-Based Reasoning (IHCBR) to make the right decision in real time in the face of a current learning situation, using both the execution of a classical cycle (linear process) and a dynamic cycle (dynamic process) of Case-Based Reasoning. This decision will be made by assigning each step of the Incremental Hybrid Case-Based Reasoning at least one agent who ensures a precise task and collaborates with other agents to follow dynamically the learner during the learning process by offering them a personalized real-time learning path.

In recent years there has been a shift from traditional expert systems to cooperative systems for workgroups. This shift stems from the realization that designers must consider the workplace's contextual information if they are to create successful applications, rather than developing applications to perform a task in isolation. The traditional expert systems development methods are insufficient to create effective cooperative systems. This special issue focuses on some of the central problems that arise when building cooperative expert systems.

Smart mobility, with its urban transportation services ranging from real-time traffic control to cooperative vehicle infrastructure systems, is becoming increasingly critical in smart cities. These smart mobility services thus need to be very well protected against a variety of security threats, such as intrusion, jamming, and Sybil attacks. One of the frequently cited attacks in smart mobility is the jamming attack. In order to detect the jamming attacks, different anti-jamming applications have been developed to reduce the impact of malicious jamming attacks. One important step in anti-jamming detection is to cluster the vehicular data. However, it is usually very time-consuming to detect the jamming attacks that may affect the safety of roads and vehicle communication in real-time. Therefore, this paper proposes an efficient big data clustering model, coresets-based clustering, to support the real-time detection of jamming attacks. We validate the model efficiency and applicability in the context of a typical smart mobility system: Vehicular Ad-hoc Network, known as VANET.

With the rapid development of the cooperative vehicle infrastructure system, eco‐approach and departure has been attracting increasing attention for mitigating the impact of signalized intersections, which helps improve the energy efficiency of equipped vehicles. However, existing studies have rarely considered the balance of electric bus energy consumption and traveling time. Meanwhile, the joint effect of bus stops and signalized intersections, and their interactions were not discussed widely with connected and automated electric buses (CAEBs). In this study, an integrated CAEB trajectory planning methodology with the balance of traveling time and energy consumption is proposed. A bi‐level programming model is developed to obtain the optimal trajectories of CAEBs. Numerical experiments are conducted to analyse and compare the model with two baseline models. The results demonstrate the optimal performance of the derived scheme in terms of bus energy consumption, with approximately 30–50% energy savings. Furthermore, model sensitivity analysis is conducted to quantify the impacts of the related system parameters. The findings also reveal that the entry time, conversion coefficient, and final speed have significant impacts on electric bus energy consumption along signalized arterials with bus stops.

With the rapid development of information technology, there is an increasing interest in connected vehicle and related technology. Compared to the large number of simulation studies on connected vehicle, there appeared to be few empirical studies on the performance of networks and applications due to the lack of suitable hardware facilities. Therefore, Chang’an University started to build a cooperative vehicle-infrastructure system test bed with different types of ITS scenarios and communication systems such as 4G-LTE and VANET (Vehicular Ad Hoc Network), which was called CU-CVIS test bed and located in its Weishui campus. In this paper, the architecture and detailed functions of CU-CVIS test bed are presented. Firstly, some important connected vehicle test beds in the world are introduced. Next, based on the demand of applications on connected vehicle, details of CU-CVIS test bed, such as architecture of the test bed, construction of 4G-LTE and DSRC communication systems and result of performance test, are described. The characteristics of CU-CVIS test bed are also presented. Finally, the vision and developing strategy of the test bed in the future are discussed with opportunities and challenges. It can be concluded that CU-CVIS can simulate various connected vehicle scenarios with reliable heterogeneous vehicular network and support future empirical study on connected vehicle and other related technologies.