Ebook: Advances in Intelligent Traffic and Transportation Systems

The International Conference on Intelligent Traffic and Transportation (ICITT) is a major event for academics, researchers and industrialists engaged in intelligent traffic and transportation research. Held annually since 2016, the conference is renowned as a friendly and inclusive platform that brings together a broad community of researchers sharing a common goal: the developing and management of the engineering and technology revolution of those transportation systems and operations key to sustaining the success of the intelligent traffic and transportation industries. For over a decade, ICITT has been the main research conference devoted to intelligent traffic and transportation, both in the EU and worldwide, successfully bringing together researchers, academics and industrialists to share their knowledge, know-how and experiences. Initiated as a national Intelligent Traffic and Transportation workshop by an ICITT Consortium of well-known university professors working in the field of applied intelligent traffic and transportation research, it became an international conference in 2016.

The ICITT Consortium is an independent body established in 2010. Its main aim is to promote engineering and technology education, training and research, and knowledge exchange and transfer related to intelligent traffic and transportation. To achieve this, the conference chairmen, consortium and committee members maintain a close association with those international bodies concerned with the training and continuing development of professional engineers and technologists, while responding to appropriate consultative and discussion documents and other initiatives. The conference also plans major industrial visits to small to medium enterprise (SME) and large enterprise (LE) industries to enhance the knowledge and experience of conference participants as regards the existing and future industrial revolution (i.e. digital agenda, autonomous technology, industrial automation, Industry 4.0 and beyond etc.) and its impact on the intelligent traffic and transportation market.

In 2016, the ICITT conference was given the title International to reflect current trends in intelligent traffic and transportation engineering and technology and to promote the exchange of research, engineering and technology application experiences internationally.

In previous years, the ICITT has taken place in the following countries:

ICITT 2016  China

ICITT 2017  France

ICITT 2018  Sweden

ICITT 2019  Netherlands

ICITT 2020  VR Online

ICITT 2021  VR Online

ICITT 2022  France.

This design is based on MSP432 single chip microcomputer as the core, combined with visual recognition technology, through the speed closed loop to control the intelligent car, and realize the dual car to follow and overtake on the predetermined track. In this design, MSP432P401Y is selected as the main control, and the identification information is sent to the master control through the serial port, so as to enter the corresponding road and prevent the car from deviating from the predetermined track; The leading car and the following car communicate with each other through Bluetooth module to achieve the goa of two vehicle collaborative transportation; Through the feedback information of the motor encoder, the speed closed-loop control system of the trolley is designed through the feedback information of the motor encoder to realize the precise control of the transportation distance. After detection, this design has the advantages of fast identification speed, high accuracy, stable transportation and high efficiency.

Automated vehicles are rapidly invading our everyday mobility reality. Systems of lower automation levels are already installed in many private cars’ models – some also at more advanced levels – while automated shuttles are in operation in several cities across Europe and beyond. Moreover, automation is also becoming a reality in several rail and maritime operations, along with drones’ applications. In this context, a crucial parameter for the success of such applications is the acceptance of users, either as passengers, drivers or operators of these vehicles, or as stakeholders in a decision-making position for the deployment of such vehicles. To achieve this, training is essential in order to make users accustomed to the new functionalities and operation modes, while making them aware of the benefits and gains resulting from the introduction of such technologies. Drive2theFuture Horizon 2020 project aims to prepare “drivers”, travelers and vehicle operators of the future to accept and use connected, cooperative and automated transport modes and the industry of these technologies to understand and meet their needs and wants. Among its other activities, an e-learning tool has been developed, including courses for all transport modes and for different user groups, with the aim to train the future users of automated mobility means. The tool is structured in a way that the user or the trainer can choose the desired course or group of courses and form a training session customized to their needs and purposes. Different means of visualization are offered, including texts, pictures, real life and simulator videos, etc. Moreover, quiz feature is included, to assess the user’s acquired knowledge after completing each course. The tool has been used and assessed in six pilot sites across Europe (Italy, Austria, Belgium, Germany and Denmark) addressing road, rail, maritime and air mobility. The contents of the training courses include Human Machine Interface (HMI), general knowledge on transport automation, conspicuity issues, in-vehicle and remote operation, safety and security issues and many more; moreover, they address not only private vehicle users but also operators of bus, train, vessel as well as drones. In this paper the development of the Drive2theFuture e-learning tool will be presented.

Transportation is essential for economic and social development, and vehicle flow data can be used for safety monitoring, pollution analysis, and traffic flow management. Unfortunately, traffic management and control centres do not always comply with codified standards, making it difficult to obtain up-to-date data. This paper analyses open traffic datasets and Italian public traffic data sources available online, providing a knowledge base for transportation managers and researchers. Open traffic datasets are dimensionality-reduced and clustered. An event with 209,135 visitors is used to benchmark the public data sources, the time series of traffic flows are decomposed and a regression tree is used to identify different periods. The results suggest that the available Italian sensor grid is not fine enough to identify all incoming and outgoing traffic, more infrastructure investments are required or the available measurements should be coupled with other evaluation approaches capable of extending the punctual data through mathematical means.

For a centralized path planning in the multi-agent path finding (MAPF), especially for road vehicles using traffic rules, a prioritized planning algorithm is one of the key methods that deal with real-time problems. The time used for planning is limited, especially when a number of agents are present, and a suboptimal solution has to be found. If possible, the previous solution should be reused for the replanning. Anytime Dynamic A* (AD*) can both replan the path when the environment is changed dynamically and is able to return a safe, but potentially suboptimal solution in case where a maximum cycle time is exceeded. A prioritized order selection is based on the path length to the goal. To model heterogeneous traffics with vehicles and pedestrians, a combination of the bicycle and pedestrian obstacle reciprocal collision avoidance algorithms (B-ORCA and PORCA) is used to realize a naturalistic interaction among the multi-agent system and the dynamic environment. The number of agents and of dynamic obstacles is randomly generated and the time used for planning is analyzed in view of the limited time available in the simulations. In this work, the path planning of up to three agents can be executed in real-time in MATLAB.

This paper mainly introduces a set of high-speed railway earthquake early warning test system based on LabVIEW, which serves for the indoor prototype test of high-speed railway earthquake early-warning system, which is used to simulate wave generation instead of seismic sensors. From the perspective of indoor prototype simulation, a high-speed railway earthquake early warning (EEW) test system based on virtual instrument (VI) technology is developed. Through the test system, seismic wave and non-seismic interference wave are simulated, generated and sent, so as to carry out test technology research on the current high-speed railway EEW system in China. Based on the virtual instrument development platform LabVIEW, the high-speed railway earthquake warning test system is developed. The function of the test system is verified by an example, and the consistency between the original waveform and the acquisition waveform is analyzed. The results show that the amplitude accuracy of the test system is 0.005 ± 0.002 gal and the acceleration peak time is no difference, that is, the high-speed railway EEW test system based on VI technology is accurate and reliable.

In this paper, we present an innovative approach to passenger flow monitoring for light rail transportation networks. We propose a distributed system based on two main concepts. On each vehicle in the transportation network, a set of sensors is used to count people at a given place. On a cloud-based server, a data synchronization and storage system aggregates the data sent from all vehicles and provides a global view of the transportation network. The contribution, with respect to the state of the art, of our approach is twofold. First, the proposed distributed architecture is able to reduce the system global cost via its flexibility and ease of deployment, since the main part of the system is onboard each vehicle and not fixed at stations or track sections. Second, the novel vision-based passenger counting approach guarantees high levels of reliability in the estimation of the number of people in a given area, and the ability to provide real-time data on the global transportation network. Experimental results demonstrate the validity and the advantages of the proposed approach, paving way to future uses of the system as the base of additional network optimization modules for the global light rail transportation.

Scene Text Recognition (STR) enables the Advanced Driver Assistance System (ADAS) to recognize text in natural context, such as object labels, instructions, and text-based traffic signs. STR helps self-driving cars make informed decisions such as which direction to take, how fast to go, and what to do next. Traffic signs are categorized into three categories: traffic lights based on symbols and texts, and additional traffic. Traffic signs recognition is a very important task in ADAS, although many researchers have had impressive success with symbol-based traffic signs, there are very few researchers working on the other types of signs due to the difficulties they encounter, chief among which is the lack of publicly available datasets. In addition to the many factors that make text-traffic signs difficult to recognize, including complex backgrounds, noise, lightning conditions, different fonts, and geometric distortions in the signs. In this paper, we will survey some modern and effective methods of scene text recognition and discuss some of the problems they face, taking a closer look at the problem of text recognition of traffic signs in the first place.

Following a regulatory change in Europe which mandates that car manufacturers include an “eCall” system in new vehicles, many car manufacturers are adding additional services on top, so that more and more cars become connected vehicles and act like IoT sensors. In the following study, we analyse the maturity level of this new technology to build insurance products that would take vehicle usage into account. For this, the connectivity of recent cars a-priori eligible has been first tested. Then, an ad-hoc platform has been designed to collect driving data. In particular, 4 cars have been connected to this platform for periods of over one month. Our results highlight that, while this technological innovation appears very promising in the future, the pricing, the lack of uniformity of data collected and the enrollment process are currently three pain points that should be addressed to offer large-scale opportunities. In the meantime, this technology might still be used for high value use cases such as the insurance of luxurious cars.

Small and medium-sized (SME) logistics hubs are characterized by a variety of customer relationships, different services offered, and diverse organizational interfaces. Increased requirements for workflows that run smoothly, at best digitally, are often met by using individual IT systems at hubs like inland intermodal terminals. In this context, the development and introduction of systems are rarely characterized by a uniform strategy, but by short-term requirements and interim solutions. This paper aims to develop an IT reference model for SME inland terminals. The focus is on supporting the independent and structured further development of processes and IT landscapes by the terminals. The paper is based on a project, which was carried out in exchange with experts and involved parties as well as based on a literature analysis to highlight SME- and branch-specific issues. Modeling the current situation creates a basis for identifying weaknesses and target landscapes. Reference process models assist with the systematic mapping and analysis of IT and process landscapes and hold opportunities to identify potentials to increase productivity, reduce costs and avoid redundancies. It consists of many process models, tools, and recommendations for action, which together comprise a “help for self-help” approach. Implications for making process models more flexible to respond to external demands were considered.

The use of the powered micro-mobility devices has increased significantly around the world, especially with the development of the new electric transportation system. In this research, a questionnaire survey was conducted to provide policymakers with guidelines to encourage users to use micro-vehicles. The survey explores the usage patterns of micro-mobility vehicles in the Emirate of Abu Dhabi, focusing on the types of infrastructure used and the frequency of usage. The research aims to determine what factors would encourage users to use their devices more frequently, with a focus on safety and convenience. According to the survey results, the vast majority of micro-mobility users in Abu Dhabi are currently riding on off-road paths shared with pedestrians, with only slight variations among different micro-mobility types. It was also found that the most common type of infrastructure used was off-road shared tracks with pedestrians, followed by off-road sign-posted tracks shared with pedestrians. There has been a variation in the usage frequencies of the different infrastructural facilities for micro-mobility ridership. However, the usage frequency of micro-vehicles on-road and off-road signposted lanes is almost the same across all the survey locations in Abu Dhabi. The findings of this paper can be used by policymakers to improve micro-mobility and make them more accessible to people.

The Precedence-Constrained Minimum-Cost Arborescence problem, has been recently proposed. The purpose of the precedence constraints, that are enforced between pairs of vertices, is to prevent certain directed paths to appear in the tree that violate a precedence relationship. In this work we introduce a new mixed integer linear programming model that uses a smaller number of variables and constraints to model the precedence relationships compared to those previously appeared in the literature. Furthermore, two models with a polynomial number of variables and constraints are introduced. It is based on a network-flow formulation to model the connectivity of the arborescence. Extensive computational experiments have been run to validate the new models.

In offshore riser systems, the slug flow can aggravate the instability of pipeline system during pigging processes, resulting in problems, such as increased pressure fluctuations and the excessive load of the slug catcher over a short period. Bypass pig can disperse the slug due to the highly velocity passing through the bypass hole, thus mitigating the impact of the slug flow on the pigging process. This paper established a two-dimensional CFD model to study the effect of different bypass rates and inlet gas velocities on the downstream slug dispersion process in vertical riser. The results showed that increasing the bypass rate and inlet gas velocity can improve the dissipation effect of the bypass pig to the slug, but it is necessary to comprehensively consider the pigging efficiency and the changes of outlet fluid mass flow and liquid holdup. The research results can contribute to preventing pigging accidents as well as determining the pigging technology parameters during pigging processes in marine pipelines.

Intelligent Transportation Systems (ITS) are utilized in car insurance policies known as Usage-Based Insurance (UBI), where driving data is collected using a telematics device to determine driving behavior. This enables offering personalized car insurance fees based on driving performance. Current research focuses on advantages, disadvantages, and privacy aspects of UBI, paying less attention to its user acceptance. In this work, we propose a UBI acceptance model based on an adaptation of the Unified Theory of Acceptance and Use of Technology 2 (UTAUT2) and test it with 585 participants by means of structural equation modeling. We find that social influence and hedonic motivation are the most important predictors of the intention to use UBI, and perceived privacy influences it indirectly. Furthermore, we refine the model with new connections, improving model fit.

The parameters of quality control and quality inspection are considered as important factors affecting market demand, and the “ERC” fairness preference model is introduced to construct a supply chain quality control decision model when the retailer and the manufacturer have fair preferences respectively. Through numerical calculation examples, we further observe the internal relationship between quality control variables and other parameters such as product price and market demand in case of the retailer and the manufacturer with fairness preferences respectively, and suggest to improve product quality by establish cooperative mechanism through supply chain parties. This is an important guide to the overall optimization of the supply chain.

Picking operations inside a warehouse are the major share of the total costs of retailing operations. Optimization and harmonization of operations is therefore crucial in the economy of a successful business. In this paper we consider the case of a leading German grocery retailer company and we adapt to their case a Mixed Integer Linear Program solving the order batching, assignment and pickers routing problems. Improvements to the model are also discussed, Computational experiments are finally presented, validating the different models and ranking them in terms of their applicability to real scenarios.