Keywords: Modeling, Control and Optimization of Transportation Systems, Rail Transportation, Automotive Control
Abstract: In this paper the railway vehicle is modeled by a seventeenth-degrees-of freedom full vehicle model to investigate the elastic vibrations of the railway vehicles's car body subjected to the excitations from vertical track irregularities. These irregularities are represented by the power spectral density functions which are authenticated for the stochastic real track data collected from the Konya-Polatli railway line in Turkey. The car body floor is modelled as a structure consisting of a plate and its connecting components by introducing artificial springs at the joint points. The model can express the complicated elastic vibrations with fewer degrees of freedom and at a lower computational cost than the detailed finite element model. To suppress the vertical vibration of the flexible-bodied railway vehicle secondary suspension control design based on affine parameter dependent model has been built with a single objective function and the solutions are obtained via Hinfinity optimization. The numerical results show that the complicated mode shapes can successfully be expressed analytically and the simulation studies illustrate that the active system is effective in reducing both the flexible and rigid modes of the car body and improving the ride comfort.

Keywords: Rail Transportation, Formal methods in transportation, Safety and Security in transportation systems
Abstract: European Train Control System (ETCS) is the signalling and control component of the European Rail Traffic Management System (ERTMS). This system is essential to guarantee the safe and interoperable operation of trains. To enhance the competitiveness of rail transport services, the introduction of innovative solutions are under study in view of the evolution of ETCS. In this context, the adoption of Global Navigation Satellite System (GNSS) for train localization is investigated as a technology which can ensure an undeniable added value for railways. Yet, a main challenge is to provide safety evidence permitting the certification of these new systems. In particular, the classical safety analysis approaches show limitations in dealing with the complexity of such systems. Therefore, more adapted safety and performance analysis techniques have to be elaborated. In this paper, a model-based approach, adapted for the evaluation of GNSS-based localisation systems in railway, is presented. Considering the safety-critical aspect of the localisation function in railways, formal methods which are based on rigorous mathematical foundations are adopted in the present work. Concretely, a set of formal models are elaborated to ensure a modular representation of trains dynamics in the context of GNSS-based localization. Namely, probabilistic timed automata formalisms are adopted to this aim. Such notations allow for considering stochastic and dynamic aspects, so as to reflect reality in a trustworthy way. The safety and performance properties to be checked can then be formulated by means of temporal logics. Finally, the analysis of such features can be achieved by means of model-checking and simulation techniques. This evaluation phase yields both qualitative and quantitative results and allows for assessing the impact of various parameters and functional choices on both safety and performance. UPPAAL-SMC engine was used to set the tooling chain of our approach, and an illustration considering specific operational test cases is provided.

Keywords: Rail Transportation, Public Transportation, Scheduling and optimization of transportation systems
Abstract: The real-time Railway Traffic Management Problem (rtRTMP) is the problem of detecting and solving time-overlapping conflicting request done by multiple trains on the same track resources. It typically consists in taking retiming, reordering or rerouting train actions in such a way that the propagation of disturbances in the railway network is minimized. The rtRTMP is an NP-Hard problem and finding good strategy to simplifying its solution process is paramount to obtain good quality solutions in a short computation. Solving the Train Routing Selection Problem (TRSP) aims to do so, by limiting the number of routing variables through a pre-processing that selects the most promising routing alternatives among the available ones for each train in order to reduce the size of rtRTMP instances. This paper studies the performance of an Ant Colony Optimization (ACO) algorithm for the same problem. An integer linear programming formulation for the TRSP is presented and solved using a commercial software, and it is considered as a benchmark. Computational experiments are performed on two practical case studies of the French railway infrastructure: the line near the city of Rouen and the Lille terminal station area. ACO and the commercial solver perform comparably only on small instances and both are able to find optimal solutions. However, on larger instances, the ACO algorithm outperforms the commercial software, both in terms of computation time and solution quality.

Keywords: Human factors in traffic and transportation control, Design, control and monitoring of autonomous transportation systems, Rail Transportation
Abstract: As it had already been observed in other domains, such as aircraft or automotive sectors, the development of fully automated driving systems in the mainline railway sector faces multiple technical and safety barriers. Before such an advanced system can be overcome, systems with intermediate and adaptive levels of automation must be considered and studied. In this context, human operators maintain a crucial role for the train driving activity and their interactions with technical systems and other agents must remain among the main focuses of the conception phase. These interactions are considered through a thorough Human-Machine cooperation model. The objective of this paper is to present a conception and evaluation method implementing this model in the development of assistance systems for cooperation with human operators. The method is currently being applied for train remote driving as part of the TC-Rail project, where the aim of the study is to focus on Human-Factors aspects. A second phase of development is currently in progress and has been complemented by the results of a first phase. Along with the conception method, the state of this second phase, as well as use cases for future tests that implement it, are presented in this paper.

Keywords: Safety and Security in transportation systems, Rail Transportation, Modeling, Control and Optimization of Transportation Systems
Abstract: A new paradigm based on the concept of virtual coupling of train sets is being elaborated to provide innovative solutions so as to increase efficiency, operational flexibility, line capacity, competitiveness among market players and quality of consumer experience. Train-to-Train (T2T) and Train-to-Ground (T2G) wireless communications will be the backbone for the implementation of the virtual coupling functionalities. In the present paper, we perform a model-based dependability analysis of the wireless communication system under virtual coupling operation. Namely, Stochastic Colored Petri Net (SCPN) models are developed to depict the exchanges of the various information needed under virtual coupling operation. Dependability evaluation is then performed by means of simulation. In particular, the impact of various communication parameters is scrutinized while taking into account different operational scenarios. The obtained results allow the identification of the most impacting aspects on dependability analysis and provide valuable inputs to support the technological choices in terms of communication to implement virtual coupling.

Keywords: Scheduling and optimization of transportation systems, Rail Transportation
Abstract: This paper tackles the real-time Railway Traffic Management Problem (rtRTMP). It is the problem of finding an optimal choice for the train schedules and routes to reduce the delays of trains due to conflicts. We present a new Constraint Based Scheduling (CBS) formulation of the rtRTMP. This new formulation is based on the concept of conditional time-interval variables provided in the Ilog CP-optimizer library. A time-interval variable is the time interval in which an activity is executed, but it can also be a specific value ``perp'' meaning the activity is non-executed. The new formulation exploits this new kind of variables and specific constraint propagation algorithms which contribute to the efficiency of the solution methods. The formulation has been validated with experiments on a large set of instances. The experimental results demonstrate the effectiveness of this new CBS model and show its good performance compared with the state-of-the art RECIFE-MILP algorithm.

Keywords: Artificial intelligence in transportation, Planning and management of public transportation, Modeling, Control and Optimization of Transportation Systems
Abstract: With rapid emergence of high-performance computing platforms, the availability of client big data and new machine learning techniques, the application domain of platform-based mobility services supports the research of new optimization techniques for discrete combinatorial optimization problems. Within this research field, particularly large-scale transportation domain specific problems, e.g. multi-vehicle-request matching and collaborative vehicle fleet routing problems are of high interest. In this contribution we present our novel combinatorial Deep Reinforcement Learning for solving symmetric and asymmetric multi-vehicle-request weighted assignment or matching problems by learning and predicting an efficient solution heuristic automatically. The solved assignment problem is characterized by defining different node classes for vehicles, requests and service stations. Our results contain algorithm benchmarks based on reproducible artificial data and statistical evaluations towards solution accuracy and efficiency with respect to different problem complexities. We contribute additional comparisons between different algorithms and heuristics such as naive Greedy, k-Regret and exact (globally optimal) solutions with the simplex method by the Mixed-Integer Programming (MIP) solver Cplex. Further, we compare the results with our model with respect to solution accuracy and efficiency. We conclude that our proposed model solves the presented problem setting globally optimal up to an upper graph complexity bound defined via node degree. Furthermore, our results show that our proposed method outperforms all other algorithms with respect to the solution time required.

Keywords: Traffic Models, Artificial intelligence in transportation, Modeling, Control and Optimization of Transportation Systems
Abstract: Microscopic modeling of human driving consists generally in combining both car-following and lane-change models. While the human car-following process has been extensively developed and well modeled, the lane-change behavior is more complex to understand and still remains to be explored. Classical lane-change models are usually rule-based and hand-crafted, that tend to exhibit limited performance. Machine Learning algorithms, particularly Reinforcement Learning (RL) ones, provide an alternative approach and have recently achieved high success in modeling difficult decision-making processes in many fields. We propose in this article a reinforcement learning based model for the human lane-change behavior, with an online calibration of real lane-change decisions, extracted from the NGSIM data-set. In addition, we use the traffic vehicular simulator SUMO (“Simulation of Urban MObility”) to create a numerical simulation environment. The utilization of numerical traffic simulation allows us enriching the data-set, for training the agent to find an optimal policy for lane change. Thus, about 13%additional traffic situations, not present in the real data, are created by the traffic simulation environment. The trained agent is collision-free and human-like who is satisfactory to real data and also to the additional simulated data. Moreover, our RL model can perform up to 95.37%of the real decisions observed in the data-set.

Keywords: Connected and Automated Vehicles, Artificial intelligence in transportation
Abstract: This paper proposes a design method for the coordination of velocity profiles of autonomous vehicles in non-signalized intersection scenarios. The coordination is motivated by the avoidance of vehicle collision and the minimization of their energy loss resulted by stop and go maneuvers in the intersection. Therefore, the coordinated design is formed as an optimal control problem, which is solved through two optimization tasks. A quadratic optimization task with online solution is formed, which provides guarantees on the avoidance of the collision. Moreover, a reinforcement-learning-based optimization task with offline solution is formed, which is able to improve the economy performances of the autonomous vehicles. The optimization tasks are interconnected, i.e. the quadratic optimization with the vehicle model is used as an environment during the training process. The effectiveness of the proposed coordinated control through simulation examples with three number of autonomous vehicles is illustrated.

Keywords: Monitoring of transport systems
Abstract: As far as urban population continuously grows, the need of intelligent transport systems becomes more and more relevant to deal with transport needs for both people and cargo. Automated devices for data capture requires the implementation of analytics techniques in order to provide insights for actual decision-making and policy design. The objective of this paper is twofold. Firstly, this paper reviews academic literature about big data analytics for intelligent transportation systems; and secondly builds upon previous works to propose a simple, yet complete, framework for the design of an architecture to deal with big data analytics in Intelligent Transport Systems (ITS). The outputs of this work will be implemented to analyze transport data for a big city in Colombia.

Keywords: Modeling, Control and Optimization of Transportation Systems, Freeway Traffic Control, Design, control and monitoring of autonomous transportation systems
Abstract: The increasing road traffic congestion has urged researchers to look for solutions to tackle the problem. Many different interventions reduce traffic jams including, optimizing traffic lights, using video surveillance to monitor road conditions, strategic road network resilience, and congestion pricing. This paper uses a nonlinear model for dynamic congestion pricing, considering manual-toll and automatic toll lanes using wireless communication technologies. The model can adjust the traveling demand and improve traffic flow performance by charging more for entering express lanes. We linearize the model about the equilibrium states and propose a reinforcement learning-based adaptive optimal control approach to learn the optimal control gain of the linearized model. Further, we rigorously show that the developed optimal controller can ensure the stability of the original nonlinear closed-loop system by making its output asymptotically converge to zero. Finally, the proposed approach is validated by numerical simulations.

Keywords: Rail Transportation, Safety and Security, Human Factors
Abstract: This paper presents a preliminary study for the assessment of tram safety by managing Advanced Driver Assistance Systems depending on the Grades of Automation. The Grades/Levels of Automation in automotive, aeronautics, maritime and railway systems are presented and compared with each other. Then, according to especially the implication level of a haptic system in each tram driving task, Grades of Automation for trams are proposed. In addition to the haptic system, a visual one that uses a Head-Up Display is defined. These systems are designed to help the tram driver cope with potential hazards by having a defensive driving. Therefore, the proposed Grades of Automation and the driver assistance systems are used in order to propose an experimental method to explore how this automation can affect the tram driver performance and the Human-Machine System safety.

Keywords: Modeling, Control and Optimization of Transportation Systems, Automotive Control, Design, control and monitoring of autonomous transportation systems
Abstract: This paper outlines a novel framework for a cloud-based computational model that supports the connection of autonomous vehicles, road-infrastructure, and humans. Besides serving as a central entity to call autonomous vehicles like the private vehicle, taxi, or bus, this architecture can be used to automate and manage vehicle delivery services. Examining these different application domains, led to a service-oriented cloud architecture that distinguishes between two kinds of services. Domain dependent services for each of the vehicle types and core services, which are imperative for all applications. Since several core services require real-time vehicle-to-cloud communication, we present and evaluate a suitable communication protocol. This cloud architecture is characterized by its modular design in order to enable adaptation to different system requirements. In fact, it has found its application in the UNICARagil project, where four networked and autonomous vehicles are developed.

Keywords: Connected and Automated Vehicles, Design, control and monitoring of autonomous transportation systems, Automotive Control
Abstract: The paper focuses on the control challenge of intersections related to the appearance of autonomous vehicles on the roads, which established mixed traffic situations with human-driven vehicles or scenarios with only autonomous vehicles. The goal of the research is to control autonomous vehicles by Model Predictive Control method to guarantee the collision-free passage at the intersection. Generally the outcome of a traffic situation can be varied by human-driven vehicles and fully automated vehicles. Therefore the results of the proposed coordination method used for a given intersection scenario is compared to solution of human-driven vehicles. For the comparison the simulation examples were made in VISSIM and CarSim simulation environments.

Keywords: Design, control and monitoring of autonomous transportation systems, Connected and Automated Vehicles, Unmanned traffic management systems
Abstract: A vast number of contemporary studies investigate to resolve traffic congestion in completely autonomous vehicle scenarios. In scenarios when autonomous vehicles approach an intersection at which there are no traffic signals, they are able to drive in a coordinated manner without colliding and minimizing the consumption of fuel or electricity, which results in positive environmental effects. In order to achieve this, a multi-agent management system that includes Vehicle Agents (VAs) and an Intersection Agent (IA) has been used in this paper. In this method, the vehicles will share the area they expect to occupy within the intersection together with their estimated arrival time. The IA, in parallel, arranges reservations on a time-space basis and publicizes the results of reservations to the vehicles. Utilizing this information, individual VAs adjust their speed as efficiently as possible, e.g. reducing their speed or applying an efficient braking strategy, before reaching the intersection zone so that they do not need to stop and can pass through the intersection as quickly as possible. In this paper, the advantages of the proposed system are demonstrated by comparing it with some other types of traffic control systems.

Keywords: Autonomous mobility, Smart Mobility, Electric Vehicles
Abstract: In this paper, we address the core challenges of self-stabilization, obstacle detection, and collision avoidance arising when developing autonomous electric scooters for sharing systems. In particular, we firstly demonstrate how an e-scooter can balance itself by the usage of a reaction wheel combined with a braking mechanism. Secondly, we show how a depth-camera can be utilized to generate a grid map representation of the environment surrounding the e-scooter and how this can be used to design a computationally tractable algorithm which ensures obstacle avoidance as well as path following. Finally, the goal of this paper is to provide a starting point for the development of autonomous e-scooters for sharing systems by combining approaches from various research communities in a common application framework.

Keywords: Design, control and monitoring of autonomous transportation systems, Formal methods in transportation
Abstract: When mobile robots are employed in transportation tasks involving contact with humans, their control software shall guarantee that in every possible circumstance safety and, in general, task requirements are guaranteed. When control models are manually translated into an executable implementation, it becomes cumbersome to provide such guarantees. Model-driven engineering approaches provide an answer to such a problem. Domain-specific models are automatically translated into an executable implementation. Some model-driven engineering approaches exist that are specific to robotics. However, formal guarantees on the correctness of the model and the generated implementation with respect to the requirements are, often, not provided. This paper investigates how a general-purpose modelling language for supervisory controller synthesis (i.e. CIF) can be used to formally model plants and requirements for a robotic navigation task and how it can generate an executable implementation that can be integrated into a leading middleware for robotic applications (i.e. ROS: the Robotic Operating System). The starting point is the modeling of the interface provided by existing navigation components available in ROS. We demonstrate, with simulations and real-life experiments, that the generated supervisory controller is suitable for real-time deployment and guarantees the correctness of the model with respect to the requirements of the navigation task at hand. Results on the reaction time of the supervisory controller show that such reaction time is about twenty times smaller than the one of the same supervisory controller implemented with a conventional framework (i.e. SMACH).

Keywords: Traffic Light Control, Intelligent Transportation Systems, Modeling, Control and Optimization of Transportation Systems
Abstract: Traffic density in big cities is an important factor that reduces the quality of human life. With the increasing population of metropolitans and the inability of their infrastructures to handle this density, the traffic density is gradually increasing. As a result, passengers lose time in more traffic and the amount of emissions and hence air pollution also increases. Traffic intersections are one of the most important places that directly affect traffic flow, as they are the intersection points of more than one road. The traffic light is an important solution to change the pass permission for vehicles and pedestrians. It is actually possible to have less traffic density with adaptive changes in lighting periods depending on changing traffic density situations at the intersections. In this paper, a traffic light system at a four-legged junction is controlled by a Fuzzy Logic Controller (FLC) with different input values which are queue length and state input. The recommended method is FLC with state input based on vehicle location. The Simulation of Urban Mobility (SUMO) is used to create and manage the simulation of this control system. Results are compared for the proposed types of Traffic Light Control Systems depend on waiting time and queue length.

Keywords: Modeling, Control and Optimization of Transportation Systems
Abstract: This paper deals with the problem of controlling traffic at motorways bottlenecks in presence of an unknown, time-varying, Fundamental Diagram (FD). The FD may change over time due to traffic composition or to the presence of Connected and Automated Vehicles (CAVs) with varying driving characteristics and penetration rates. A novel methodology, based on Model Reference Adaptive Control, is presented to robustly estimate the time-varying set-points that maximise the bottleneck throughput. The proposed approach is integrated in a control scheme that includes a linear quadratic integral regulator designed to control traffic which comprises a percentage of CAVs. Simulation experiments, based on a first-order multi-lane macroscopic traffic flow model that also considers for the capacity drop phenomenon, are presented to illustrate the effectiveness of the proposed approach.

Keywords: Urban Traffic Systems, Monitoring of transport systems, Sensor Technologies
Abstract: In this paper we propose an estimator of vehicle density in every road section of a large urban traffic network. We assume a limited number of flow and turning ratio sensors can be installed, and that aggregate floating car data (FCD) is available, such that the space-mean speed of each road can be estimated. We propose a method to locate turning ratio sensors, which takes as input previous low-quality estimates of the turn rates, and then assigns to each intersection a weight according to the effect on the total density reconstruction error caused by perturbations between a priori and actual turning ratio values. We evaluate the models and estimator using data from the urban traffic network of Grenoble in France.

Keywords: Traffic Light Control, Urban Traffic Systems, Traffic Models
Abstract: Model Predictive Control (MPC) has shown promising results in the control of urban traffic networks, but unfortunately it has one major drawback. The, often nonlinear, optimization that has to be performed at every control time step is computationally too complex to use MPC controllers for real-time implementations (i.e. when the online optimization is performed within the control time interval of the controlled network). This paper proposes an effective parametrized MPC approach to lower the computational complexity of the MPC controller. Two parametrized control laws are proposed that can be used in the parametrized MPC framework, one based on the prediction model of the MPC controllers, and another is constructed using Grammatical Evolution (GE). The performance and computational complexity of the parametrized MPC approach is compared to a conventional MPC controller by performing an extensive simulation-based case study. The simulation results show that for the given case study the parametrized MPC approach is real-time implementable while the performance decreases with less than 3% with respect to the conventional MPC controller.

Keywords: Modeling, Control and Optimization of Transportation Systems, Traffic Models, Urban Traffic Systems
Abstract: Previous studies through simulation and empirical data have shown that a Network Macroscopic Fundamental Diagram (NMFD) exists and can be used for designing network optimal perimeter control strategies. These control strategies rely on well defined NMFDs, which highly depend on the homogeneity of the traffic condition in the network. However, it is known that traffic dynamics change drastically during the day in different zones in a large-scale network, and different control strategies might lead to heterogeneous traffic distribution across the urban network. One potential direction is re-partitioning the network to maintain the well defined NMFDs. However, re-partitioning the network changes each sub network's size, such that it makes the well-defined NMFDs unpredictable. This paper provides a model predictive control-based optimization approach for perimeter control using real-time partitioning to avoid this problem and utilize re-partitioning techniques. Results show that the proposed method can be used in a heterogeneous network to improve control performance by redistributing accumulations via re-partitioning over time. Our results, which are compared to no control and the traditional model predictive control, yield that the proposed method is superior to the others.