VEHITS 2022 Abstracts

Area 1 - Connected Vehicles

Full Papers

Paper Nr:	26
Title:	Lane Departure Warning System using Standard GPS Technology and V2V Communication
Authors:	Md T. Hossain, Shahnewaz Chowdhury and M. I. Hayee
Abstract:	Lane departure warning system (LDWS) has significant potential to reduce crashes. Generally, an LDWS uses various image processing techniques or global positioning system (GPS) technology with lane-level resolution maps. However, these are expensive to implement and have performance limitations, such as harsh weather or irregular lane markings can drastically reduce their performances. Previously, we developed an LDWS which generated road reference heading (RRH) from a vehicle’s past travel trajectories acquired by GPS to detect unintentional lane departure. However, when a vehicle travels for the first time on a given road, it does not have any past trajectory to generate the RRH needed to detect unintentional lane departure. To overcome this limitation, we have augmented our previously developed LDWS by adding a vehicle to vehicle (V2V) communication feature to it, which can acquire the required RRH from a nearby vehicle via V2V communication. We have extensively tested the V2V communication feature of our current LDWS in the field to evaluate its performance in real-time. Test results show that the RRH of a given road can be successfully transferred from one vehicle to another on demand, and the LDWS can detect each unintentional lane departure accurately in a timely manner.
Download

Short Papers

Paper Nr:	25
Title:	Decentralized Platoon Management and Cooperative Cruise Control of Autonomous Cars with Manoeuvre Coordination Message
Authors:	Reza Dariani, Giovanni Lucente and Julian Schindler
Abstract:	Recent development of Vehicle-to-Vehicle (V2V) technologies enables the vehicles to communicate with each other and coordinate their manoeuvres. With such technologies an Advanced Driving Assistance System (ADAS) such as Adaptive Cruise Control (ACC) can be pushed to another level in conditional and highly automated vehicles, i.e. a network of cooperative connected vehicles in the form of Cooperative ACC (CACC) or even a platoon. In this paper, based on V2V communication between automated vehicles by using Manoeuvre Coordination Message (MCM), a decentralized platoon management is designed and implemented to manage the platooning state of each vehicle and when the vehicles are in a platoon or joining one, a cruise controller is designed and implemented to guarantee the desired headway to a preceding vehicle.
Download

Area 2 - Intelligent Transport Systems and Infrastructure

Full Papers

Paper Nr:	48
Title:	Optimizing Multi-Quay Berth Allocation using the Cuckoo Search Algorithm
Authors:	Sheraz Aslam, Michalis P. Michaelides and Herodotos Herodotou
Abstract:	Proper utilization of port resources and efficient berth planning play a crucial role in minimizing port congestion and overall handling costs. Therefore, this study focuses on efficient berth planning in maritime container terminals composed of multiple quays. In particular, this study addresses the Multi-Quay Berth Allocation Problem (MQ-BAP), where a continuous berthing layout is considered along with dynamic ship arrivals and practical constraints such as safety time windows and safety distances between ships. Since MQ-BAP is an NP-hard problem, this study proposes a metaheuristic-based approach, the Cuckoo Search Algorithm (CSA) for solving the problem. A comparative study is also performed using real data instances collected from the Port of Limassol, Cyprus, against a genetic algorithm solution proposed in the recent literature, as well as the optimal exact solution implemented using MILP. The results of the experiments show the effectiveness of our proposed CSA approach in handling real-world berth allocation in ports with multiple quays while also considering practical constraints.
Download

Short Papers

Paper Nr:	3
Title:	Critical Vehicle Detection for Intelligent Transportation Systems
Authors:	Erkut Akdag, Egor Bondarev and Peter H. N. De With
Abstract:	An intelligent transportation system (ITS) is one of the core elements of smart cities, enhancing public safety and relieving traffic congestion. Detection and classification of critical vehicles, such as police cars and ambulances, passing through roadways form crucial use cases for ITS. This paper proposes a solution for detecting and classifying safety-critical vehicles on urban roadways using deep learning models. At present, a large-scale dataset for critical vehicles is not publicly available. The appearance scarcity of emergency vehicles and different coloring standards in various countries are significant challenges. To cope with the mentioned drawbacks and to address the unique requirements of our smart city project, we first generate a large-scale critical vehicle dataset, combining images retrieved from various sources with the support of the YOLO vehicle detection model. The classes of the generated dataset are: fire truck, police car, ambulance, military police car, dangerous truck, and standard vehicle. Second, we compare the performance of the Vision in Transformer (ViT) network against the traditional convolutional neural networks (CNNs) for the task of critical vehicle classification. Experimental results on our dataset reveal that the ViT-based solution reaches an average accuracy and recall of 99.39% and 99.34%, respectively.
Download

Paper Nr:	15
Title:	Identifying Vehicle Preferences and System Requirements of Potential Users of Shared Mobility Systems (SMS)
Authors:	Maryna Pobudzei, Katharina Wegner and Silja Hoffmann
Abstract:	Shared mobility systems (SMS) enable short-term on-demand access to mobility without the costs and responsibilities that come with vehicle ownership. A careful investigation of the motivation, values, and barriers that different socio-demographic groups have towards SMS may shed light on the gaps that mobility providers may still need to fill in order to attract broader population groups. The objective of this paper is an investigation of the conditions under which potential users would adopt sharing services and which vehicles they would prefer in the context of SMS. We explore (i) the willingness of individuals to use SMS, (ii) the preferences of potential users regarding types of vehicles in SMS, and (iii) requirements towards the features and design of SMS. We study the characteristics of potential users and non-users of SMS. Furthermore, we associate socio-demographic and travel behavior attributes of potential users to their SMS preferences and requirements. These effects might be a valuable source of knowledge for tailored system designs and setups for SMS providers. By working with audience segmentation, SMS communicators may develop persuasive messages customized for each group.
Download

Paper Nr:	16
Title:	Demand-responsive Scheduling in Railway Transportation
Authors:	Christoph Grüne and Stephan Zieger
Abstract:	Rural rail transportation can contribute significantly to achieving climate goals and encountering mobility challenges, especially by reactivating currently disused railway lines. Rural areas are mainly characterised by their dispersed demands. Thus, small highly automated rail vehicles could be operated on-demand and thus service-oriented. The operation of those networks is complex and the economic efficiency must be correspondingly high. Therefore, optimised resource planning is necessary. The paper focuses on the planning of a-priori known transport requests. The paper presents a formulation for the underlying Integer Programming mathematical model that optimises travel times and number of vehicles used under consideration of railway specific constraints such as headway times and deadlock prevention. The modelling goes beyond existing Dial-a-Ride approaches and adds the necessary routing constraints for rail systems as well as energy management constraints for potential refuelling or recharging. The potential for application of the approach is evaluated in a computational study. A validation scenario shows in an exemplary manner on the one hand how the constraints affect routing on a single track railway line and on the other hand how solving the model with a black-box solver such as Gurobi is handled for this scenario. On a real-world railway line, it can be shown that the Integer Programming solver is able to induce meaningful results for limited input sizes. Further potential improvements are discussed as well.
Download

Paper Nr:	37
Title:	A Microsimulation Modeling of Pedestrian Characteristics in Bangkok Transit System Case Study
Authors:	Jumrus Pitaksringkarn and Suhail Shaik
Abstract:	Although there are many international standards of walkway design, walking behaviors are different in each country/region. To determine the pedestrian characteristics the concept of the social force model, which is analogous to resolving forces in Newtonian mechanics was adopted. Behavioral data related to pedestrian walking speed were collected by using a digital camera at BTS (Bangkok Transit System) station and manually extracted needed factors like pedestrian speed, density and others. After completing the calibration and validation process using a VISSIM microsimulation technique, pedestrian walking speed is analyzed on the basis of density. The analysis shows that the walking speed of pedestrians is 75.07 m/min, which is slower than the U.S. pedestrians. It is also found that the walking speed and the body size directly affect the pedestrian flow rate. A similar traffic microsimulation model has also been applied to analyze the pedestrian capacity that is calibrated by adjusting pedestrian speed. Due to the smaller body size of Asians compared to Americans, the flow rate observed in this study is higher. In particular, the pedestrian capacities per one-meter width of uni-direction and bi-direction are 91 peds/m/min and 78 peds/m/min, respectively.
Download

Paper Nr:	39
Title:	Concept of Smart Infrastructure for Connected Vehicle Assist and Traffic Flow Optimization
Authors:	Shiva Agrawal, Rui Song, Akhil Kohli, Andreas Korb, Maximilian Andre, Erik Holzinger and Gordon Elger
Abstract:	The smart infrastructure units can play a vital role to develop smart cities of the future and in assisting automated vehicles on the road by providing extended perception and timely warnings to avoid accidents. This paper focuses on the development of such an infrastructure unit, that is specifically designed for a pedestrian crossing junction. It can control traffic lights at the junction by real-time environment perception through its sensors and can optimize the flow of vehicles and passing vulnerable road users (VRUs). Moreover, it can assist on-road vehicles by providing real-time information and critical warnings via a v2x module. This paper further describes different use-cases of the work, all major hardware components involved in the development of smart infrastructure unit, referred to as an edge, different sensor fusion approaches using the camera, radar, and lidar mounted on the edge for environment perception, various modes of communication including v2x, system design for backend and requirement for safety and security.
Download

Paper Nr:	12
Title:	Automation Potentials in Public Transport based on a Depot Model
Authors:	Nathalie Brenner, Nicole Rossel and Eric Sax
Abstract:	This paper examines the automation of public transport depots and the associated opportunities. Furthermore, the benefits for public road operations through a step-wise transferability of these depots developments is introduced. To this end, we first analyse which areas of public transport are not yet suited for the unrestricted use of fully automated vehicles, before motivating why depots are well suited for this purpose. In the following, the operations at two different depots and the previous work done so far are presented and abstracted in a generic model. For the description of the model, modeling methods are introduced and a graphical notation, defined by the unified modeling language, is applied. Based on the developed model a structured analysis of which operations may be automated and how savings might be achieved is enabled. Finally, the transferability to the operation on duty is discussed and the need for early inclusion of this consideration is highlighted.
Download

Paper Nr:	30
Title:	A Concept for Collaborative Incident Validation in a Self-organised Traffic Management System
Authors:	Sven Tomforde and Ingo Thomsen
Abstract:	The strong and, in part, further increasing traffic volumes of individual and heavy goods traffic in urban regions lead to a utilisation of the networks close to or above the capacity limit, especially during rush hours. Traffic light control is ideally traffic-dependent, which can be realised either centralised or distributed as a self-organised approach. However, these systems are typically not able to detect disruptions or incidents (such as accidents, road works, etc.) and take them into account in the control logic. A key problem here is that either there is no incident detection in place or it is not reliable enough. In this paper, we discuss the need for collaborative validation of locally detected incidents in a self-organised traffic control system. We show that this can increase the reliability of detection to the point where incident-dependent switching becomes possible.
Download

Paper Nr:	53
Title:	Intersection-centric Urban Traffic Flow Clustering for Incident Detection in Organic Traffic Control
Authors:	Ingo Thomsen and Sven Tomforde
Abstract:	The current trend of high and even increasing traffic volumes in urban areas is unbroken. This puts high strain on urban road networks, which is aggravated by unforeseen traffic incidents. To mitigate this, the Organic Traffic Control offers a resilient, decentralised traffic management system. With the additional ability to take incidents into under consideration, its performance could increase. To promote this we have previously presented a density-based approach for clustering traffic flows in order to detect traffic disturbances. In this work we assess this approach in more detail. However, the fundamental shortcomings could not be refuted.
Download

Area 3 - Intelligent Vehicle Technologies

Full Papers

Paper Nr:	2
Title:	Exploring NR-V2X Dynamic Grant Limitations for Aperiodic Traffic
Authors:	Brian McCarthy and Aisling O’Driscoll
Abstract:	The recent 3GPP NR-V2X standard (Rel. 16) has largely built upon its precursor Cellular-V2X (Rels. 14 & 15) but has introduced new approaches for dealing with application traffic exhibiting aperiodic arrival rates in the sidelink. This is vital as safety services based on ETSI Cooperative Awareness Messages (CAMs) and Decentralised Environmental Notification Messages (DENM) exhibit such characteristics. It is further envisaged that future vehicular services will also exhibit high aperiodicity to support increased autonomy. In this paper we quantitatively evaluate the reasons why the Sensing based Semi-Peristent Scheduling (SB-SPS) mechanism performs poorly when scheduling aperiodic traffic. We then provide the first in-depth evaluation of the NR-V2X Dynamic Grant mechanism in contrast to schemes that parameterise the existing C-V2X SPS algorithm and evaluate the performance of alternative dedicated scheduling mechanisms specifically designed for aperiodicity. This paper highlights that the level of aperiodicity exhibited by the application model greatly impacts scheduling performance, both for the default SB-SPS and dedicated approaches. As such we conclude that a novel aperiodic scheduling mechanism must be devised, or more promisingly, an approach to enable application traffic to mimic periodic characteristics allowing it to co-exist with the existing scheduling approach.
Download

Paper Nr:	10
Title:	A Robust Modified Hybrid A*-based Closed-loop Local Trajectory Planner for Complex Dynamic Environments
Authors:	Chinnawut Nantabut and Dirk Abel
Abstract:	In the research field of autonomous driving, planning safe and effective trajectories is a key issue, which also requires reliable detection of objects in the environment. This publication introduces a new approach to compute safe trajectories for automated road vehicles quickly and robustly, also considering reliable object detection for static and dynamic objects. For this purpose, the Hybrid A* algorithm modified with Weighted A* is used to accelerate the planning of a collision-free path because the weight w can make the heuristic term h become more important and make the tree much more narrow in the direction of the goal. Afterwards, PID- as well as Stanley controllers are utilized to realize reliable trajectories. This combined algorithm is extended with the L-Shape fitting algorithm to detect objects in the environment. The entire approach is evaluated for unstructured and semistructured environments using simulations of an automated vehicle with a realistic interaction of dynamic obstacles in the presence of model and sensor uncertainties, guarantees a real-time capability of 1 s, and results in collision-free vehicle movement. The whole algorithm, which yields very promising results, will be transferred to a C++ framework and tested with flexible test vehicles in real environments in the future.
Download

Paper Nr:	13
Title:	Evaluating the Quality of Lane Change Event Detection: Effect of Situational Variables
Authors:	Merlijne Geurts, Jeroen Hogema, Emilia Silvas, Jan Souman, Ashfaqur Rahman and Johannes Hiller
Abstract:	To develop safe automated driving functions, knowing road-user’s lane change behaviour is critical. This detection problem may depend on multiple aspects such as road conditions, location, and weather. To understand the effect of these situational variables, this work introduces a lane change detection algorithm and assessed its performance under various light conditions, road types and weather conditions. The algorithm was developed in L3Pilot: a large-scale European pilot project on level 3 automation. In the current study, the algorithm was tested with data from a Dutch Field Operational Test on SAE Level 2 systems. The algorithm was assessed against manually annotated video recordings. New is that validation was executed with Dutch Field Operational Test data of different participants and vehicles, distinguishing three situational variables factors. These were day vs night, motorways vs trunk roads and dry vs rain. A bootstrap procedure was used to assess the statistical significance of differences among the conditions. The conclusion is that the algorithm in combination with the provided data is effective in detecting lane changes when data is collected on a sample of Dutch motorways, irrespective of light and precipitation conditions. However, the quality of the sensor signals was worse on trunk roads, yielding significantly worse lane change detection performance (for all light and precipitation conditions).
Download

Paper Nr:	14
Title:	Ad-datasets: A Meta-collection of Data Sets for Autonomous Driving
Authors:	Daniel Bogdoll, Felix Schreyer and J. M. Zöllner
Abstract:	Autonomous driving is among the largest domains in which deep learning has been fundamental for progress within the last years. The rise of datasets went hand in hand with this development. All the more striking is the fact that researchers do not have a tool available that provides a quick, comprehensive and up-to-date overview of data sets and their features in the domain of autonomous driving. In this paper, we present ad-datasets, an online tool that provides such an overview for more than 150 data sets. The tool enables users to sort and filter the data sets according to currently 16 different categories. ad-datasets is an open-source project with community contributions. It is in constant development, ensuring that the content stays up-to-date.
Download

Paper Nr:	17
Title:	Battery Thermal Management Systems for EVs and Its Applications: A Review
Authors:	Haosong He, Vishal Saini and Xiangjie Chen
Abstract:	Electric vehicles (EVs) are a viable alternatives to achieve zero greenhouse gas emission goals. However, the prime clean power source choice- Lithium-ion battery is sensitive to temperature, thus requires a battery thermal management system (BTMS) to secure its performance and safety. Nowadays, most commercial EVs implement liquid BTMS because the liquids are expected to have high heat transfer efficiency with both cooling or heating capabilities. This paper firstly reviews the adverse effects of temperature on the battery performance from three aspects: high temperature, low temperature and temperature difference. Then three commercialised BTMSs: air cooling BTMS, liquid cooling BTMS, and refrigerants BTMS, are introduced, and the main advantages and disadvantages for each BTMS strategy are discussed. Finally, this paper presents main BTMS applications the BTMS applications for EVs on market.
Download

Paper Nr:	23
Title:	Traffic Light Control using Reinforcement Learning: A Survey and an Open Source Implementation
Authors:	Ciprian Paduraru, Miruna Paduraru and Alin Stefanescu
Abstract:	Traffic light control optimization is nowadays an important part of a smart city, given the advancement of sensors, IoT, and edge computing capabilities. The optimization method targeted by our work follows a general trend in the community: dynamically switching traffic light phases depending on the current traffic state. Reinforcement learning was lately adopted in the literature as it has been shown to outperform previous methods. The primary goal of our work is to provide an overview of the state of the art of reinforcement methods for traffic signal control optimization. Another topic of our work is to improve over existing tools that combine the field of reinforcement learning with traffic flow optimization. In this sense, we seek to add more output capabilities to existing tools to get closer to the domain-specific problem, to evaluate different algorithms for training strategies, to compare their performance and efficiency, and to simplify efforts in the research process by providing ways to more easily capture and work with new data sets.
Download

Paper Nr:	38
Title:	Tuning and Costs Analysis for a Trajectory Planning Algorithm for Autonomous Vehicles
Authors:	Abdallah Said, Reine Talj, Clovis Francis and Hassan Shraim
Abstract:	Trajectory planning is an essential issue for autonomous vehicles navigation. It represents a decision-making level that considers several constraints to be respected to navigate safely and comfortably in a dynamic environment. This paper presents a reactive trajectory planning, which consists to generates several candidate trajectories. Then, selecting the best trajectory among candidates is based on different criteria, each described by a cost function. Indeed, the algorithm aims to minimize a global cost function, a combination of several costs, to determine the best trajectory. The main objective of this work is to study the algorithm’s sensitivity against parameter tuning and to find a generic range of weighting coefficients for the cost function of the planning algorithm to make the algorithm as reliable as possible against various driving conditions.
Download

Paper Nr:	40
Title:	Determining the Workload of Driving Scenarios using Ratings to Support Safety and Usability Assessments
Authors:	Paul Green
Abstract:	How long will it take a driver to take over if the automation fails? Is a particular driver interface too distracting? How comparable are the workloads from 2 studies that involve different roads and traffic? The answer to these driving safety related questions depends upon the workload drivers experience, which should be calculable from data or descriptions of road geometry and traffic. For this purpose, 24 subjects rated the workload of 200 driving scenarios on a 0 to 100 scale. Those scenarios were combinations of road type (urban, rural, expressways, residential streets), traffic, road geometry, the lane driven, and other factors (e.g., 4-lane, straight rural road with 8-foot paved shoulder and 8-foot grass strip beyond that). Finding 1: Those ratings were found to be reliable and well correlated (r=0.75) with ratings collected using the anchored-clip rating method. Finding 2: Workload was predicted by an additive model that used a table of values provided herein. (For example, for urban roads, add 9 points to the base rating for heavy traffic, but 12 points for expressways.) In fact, traffic consistently had the largest effect on workload ratings, with the difference between no traffic and heavy traffic being 50 %.
Download

Paper Nr:	43
Title:	Energy Demand Prediction in Hybrid Electrical Vehicles for Speed Optimization
Authors:	Daniel Fink, Sean Shugar, Zygimantas Ziaukas, Christoph Schweers, Ahmed Trabelsi and Hans-Georg Jacob
Abstract:	Targeting a resource-efficient automotive traffic, modern driver assistance systems include speed optimization algorithms to minimize the vehicle’s energy demand, based on predictive route data. Within these algorithms, the required energy for upcoming operation points has to be determined. This paper presents a model-based approach, to predict the energy demand of a parallel hybrid electrical vehicle, which is suitable to be used in speed optimization algorithms. It relies on separate models for the individual power train components, and is identified for a real test vehicle. On route sections of 5 to 7 km the averaged root mean square error for the state of charge prediction results to 0.91% while the required amount of fuel can be predicted with an averaged root mean square error of 0.05 liters.
Download

Paper Nr:	50
Title:	Identifying Scenarios in Field Data to Enable Validation of Highly Automated Driving Systems
Authors:	Christian Reichenbächer, Maximilian Rasch, Zafer Kayatas, Florian Wirthmüller, Jochen Hipp, Thao Dang and Oliver Bringmann
Abstract:	Scenario-based approaches for the validation of highly automated driving functions are based on the search for safety-critical characteristics of driving scenarios using software-in-the-loop simulations. This search requires information about the shape and probability of scenarios in real-world traffic. The scope of this work is to develop a method that identifies predefined logical driving scenarios in field data, so that this information can be derived subsequently. More precisely, a suitable approach is developed, implemented and validated using a traffic scenario as an example. The presented methodology is based on qualitative modelling of scenarios, which can be detected in abstracted field data. The abstraction is achieved by using universal elements of an ontology represented by a domain model. Already published approaches for such an abstraction are discussed and concretised with regard to the given application. By examining a first set of test data, it is shown that the developed method is a suitable approach for the identification of further driving scenarios.
Download

Paper Nr:	63
Title:	Deterministic Operating Strategy for Multi-objective NMPC for Safe Autonomous Driving in Urban Traffic
Authors:	Mostafa Emam and Matthias Gerdts
Abstract:	In this paper, we introduce a deterministic operating methodology based on finite-state automata to employ multi-objective Nonlinear Model Predictive Control (NMPC) in autonomous driving applications. We begin with discussing the system’s dynamical behavior and the proposed constraints to guarantee safe driving. Then, we examine a typical urban scenario and dissect it into a set of interacting sequences, so that we develop and fine-tune separate MPC-based controllers for each of these sequences. Finally, we introduce a Finite-State Machine (FSM) that analyzes the current driving situation and accordingly selects the appropriate controller to compute the optimal control action. This approach is numerically simulated and tested with the software OCPID-DAE1 and results show its success in accordance with multi-objective NMPC.
Download

Short Papers

Paper Nr:	4
Title:	A Vision-based Lane Detection Technique using Deep Neural Networks and Temporal Information
Authors:	Chun-Ke Chang and Huei-Yung Lin
Abstract:	With the advances of driver assistance technologies, more and more people begin to pay attentions on traffic safety. Among various vehicle subsystems, the lane detection module is one of the important parts of advanced driver assistance system (ADAS). Traditional lane detection techniques use machine vision algorithms to find straight lines in road scene images. However, it is difficult to identify straight or curve lane markings in complex environments. This paper presents a lane detection technique based on the deep neural network. It utilizes the 3D convolutional network with the incorporation of temporal information to the network structure. Two well-known lane detection network structures, PINet and PolyLaneNet, are improved by integrating 3D ResNet50. In the experiments, the accuracy is greatly improved for the applications to a variety of different complex scenes.
Download

Paper Nr:	5
Title:	On Ethical Considerations Concerning Autonomous Vehicles
Authors:	Konstantina Marra, Ilias Panagiotopoulos and George Dimitrakopoulos
Abstract:	Autonomous vehicles are studied in terms of technology and economics, but there is also a social component to be discussed. Whereas technical challenges are being resolved and great progress is being made in their design, social and ethical issues arise, with legal and philosophical aspects, which must be addressed. Following this trend, the present study focuses on exploring peoples’ views concerning ethical dilemmas related to the behaviour of autonomous vehicles in road accidents. In addition, liability issues in cases of such accidents are examined. On this basis, a questionnaire based survey is conducted, aiming at investigating the views of future owners of autonomous vehicles on liability and on the decisions, which such vehicles should make in the event of an unavoidable road accident. The above is achieved through a series of thought experiments, which reveal how potential consumers solve different versions of the Trolley- problem in two cases: with and without the option of equal treatment. The present analysis treats the risk of accidents as inevitable and tries to prevent public reactions which could stall the adoption of autonomous vehicles, by revealing peoples’ perceptions of morality, which in the future could contribute to creating more ethical and trustworthy autonomous vehicles.
Download

Paper Nr:	7
Title:	A Data-Driven Methodology for Pre-Flight Trajectory Prediction
Authors:	Gaetano Zazzaro, Francesco Martone, Gianpaolo Romano, Antonio Vitale and Edoardo Filippone
Abstract:	This paper presents a data-driven methodology, named P4T, for the trajectory prediction from long to short term before scheduled time of flight, developed within the framework of the PIU4TP project. The methodology is aimed to support the Network Manager in the air traffic flow and capacity management, allowing the optimization of flight distribution among sectors and flight routes, the anticipation of air traffic flow requests and the identification in advance of potential conflicts. The proposed approach applies machine learning and data mining techniques to perform data analysis and to correctly identify, from historical data, the aircraft expected behaviour, in terms of flight path selection. The main peculiarity of this approach is the exploitation of the uncertainties on current forecasts of some relevant mission and aircraft parameters to compute trajectory prediction outcomes enriched with associated probabilistic information. The preliminary validation of the methodology using simulated data highlighted very promising results.
Download

Paper Nr:	8
Title:	Towards Depth Perception from Noisy Camera based Sensors for Autonomous Driving
Authors:	Mena Nagiub and Thorsten Beuth
Abstract:	Autonomous driving systems use depth sensors to create 3D point clouds of the scene. They use 3D point clouds as a building block for other driving algorithms. Depth completion and prediction methods are used to improve depth information and inaccuracy. Accuracy is a cornerstone of automotive safety. This paper studies different depth completion and prediction methods providing an overview of the methods’ accuracies and use cases. The study is limited to low-speed driving scenarios based on standard cameras and Laser sensors.
Download

Paper Nr:	11
Title:	Introducing a Novel ROS-based Cooperative Autonomous Vehicles Planning Simulation Framework, CAVPsim
Authors:	R. Ghahremaninejad and S. Bilgen
Abstract:	Emerging full stack autonomous driving software packages promise rapid development on autonomous driving deployment studies. However, considering the increasing importance of cooperation among vehicles, the absence of the Cooperative Autonomous Vehicle (CAV) research focus in those works draws attention. In this paper, we review some CAV simulation frameworks and introduce a novel ROS based CAV Planning simulation framework, CAVPsim. The framework has three main components: vehicle, communication, and computation models. We verify the integration of these three components, and we show, via a simple scenario, that cooperation of communicating autonomous vehicles can be effectively simulated on CAVPsim.
Download

Paper Nr:	22
Title:	Testing an Eco-Cooperative Adaptive Cruise Control System in a Large-scale Metropolitan Network
Authors:	Hao Chen and Hesham A. Rakha
Abstract:	This study implements and tests an Eco-Cooperative Adaptive Cruise Control at Intersections (Eco-CACC-I) system in a large-scale metropolitan network to quantify the system-level performance considering different vehicle powertrains, connected automated vehicle (CAV) market penetration rates, and congestion levels. Specifically, three vehicle powertrains are considered in this study, including internal combustion engine vehicles (ICEVs), battery electric vehicles (BEVs) and hybrid electric vehicles (HEVs). This study integrates the Eco-CACC-I controller with different fuel/energy consumption models, so that the controller can compute energy-optimized solutions to assist ICEVs, BEVs and HEVs traverse signalized intersections. A simulated traffic network in the Greater Los Angeles Area including the downtown LA and the immediate vicinity is used to implement and test the Eco-CACC-I controller. In particular, 1,606 arterial links that are either directly upstream or downstream 457 coordinated adaptive traffic signal controllers are used to test the Eco-CACC-I controller. The test results demonstrate that the controller produces positive impacts on saving fuel/energy consumption, reducing travel time and delays on urban networks for different combinations of CAV market penetration and congestion levels.
Download

Paper Nr:	24
Title:	Design and Validation of a Multi-objective Automotive State Estimator for Unobservable and Non-linear Vehicle Models
Authors:	Thijs Devos, Matteo Kirchner, Jan Croes, Jasper De Smet and Frank Naets
Abstract:	This paper presents a novel automotive state estimation approach aiming to provide reliable results for multi-objective estimation applications. Because single-objective estimators typically feature simple, dedicated models, they often lack accuracy for highly dynamically coupled systems such as vehicles. Therefore, this approach features a more complex, system-level, non-linear vehicle model containing more accurate physics. Based on the assumption that the estimator targets a specific number of quantities of interest, an extensive observability analysis is performed to ensure stable estimator operation. Firstly, a novel algorithm to detect unobservable estimator states is presented, followed by a methodology for detailed analysis on which estimator states are decoupled using the linearized Jacobians. It is shown that if the unobservable states are partially decoupled and have no dependency towards the quantities of interest, an observable transformation can be carried out which stabilizes the estimator during operation ensuring reliable and interpretable results for the quantities of interest. The methodology is validated using an experimental vehicle case for which sensor selection was performed and demonstrates the estimator performance as well as potential limitations for unobservable vehicle states.
Download

Paper Nr:	28
Title:	Parallel Parking: Optimal Entry and Minimum Slot Dimensions
Authors:	Jiri Vlasak, Michal Sojka and Zdeněk Hanzálek
Abstract:	The problem of path planning for automated parking is usually presented as finding a collision-free path from initial to goal positions, where three out of four parking slot edges represent obstacles. We rethink the path planning problem for parallel parking by decomposing it into two independent parts. The topic of this paper is finding optimal parking slot entry positions. Path planning from initial to entry position is out of scope here. We show the relation between entry positions, parking slot dimensions, and the number of backward-forward direction changes. This information can be used as an input to optimize other parts of the automated parking process.
Download

Paper Nr:	36
Title:	Situational Collective Perception: Adaptive and Efficient Collective Perception in Future Vehicular Systems
Authors:	Ahmad Khalil, Tobias Meuser, Yassin Alkhalili, Antonio F. Anta, Lukas Staecker and Ralf Steinmetz
Abstract:	With the emerge of Vehicle-to-everything (V2X) communication, vehicles and other road users can perform Collective Perception (CP), whereby they exchange their individually detected environment to increase the collective awareness of the surrounding environment. To detect and classify the surrounding environmental objects, preprocessed sensor data (e.g., point-cloud data generated by a Lidar) in each vehicle is fed and classified by onboard Deep Neural Networks (DNNs). The main weakness of these DNNs is that they are commonly statically trained with context-agnostic data sets, limiting their adaptability to specific environments. This may eventually prevent the detection of objects, causing safety disasters. Inspired by the Federated Learning (FL) approach, in this work we tailor a collective perception architecture, introducing Situational Collective Perception (SCP) based on dynamically trained and situational DNNs, and enabling adaptive and efficient collective perception in future vehicular networks.
Download

Paper Nr:	44
Title:	Pedestrian Activity Recognition from 3D Skeleton Data using Long Short Term Memory Units
Authors:	Qazi H. Jan, Yogitha S. Baddela and Karsten Berns
Abstract:	The pace of advancement in the realm of autonomous driving is quickening, raising concerns and escalating expectations for pedestrian safety, intelligence, and stability. In dynamic and uncertain contexts, some scenarios necessitate distinguishing pedestrian position and behavior, such as crossing or standing. The ability to recognize a pedestrian is a critical component of autonomous driving success. Before making an appropriate response, the vehicle must detect the pedestrian, identify their body movements, and comprehend the significance of their actions. In this paper, a detailed description of the architecture for 3D activity recognition of a pedestrian using Recurrent Neural Networks (RNN) is presented. In this work, a custom dataset that was created from an autonomous vehicle of RRLAB at the Technische Universität Kaiserslautern is employed. The information was gathered for behaviors such as parallel crossing, perpendicular crossing, texting, and phone calls, among others. On the data, models were trained, and Long-Short Term Memory (LSTM), a recurrent neural network has shown to be superior to Convolution Neural Networks (CNN) in terms of accuracy. Various investigations and analyses have revealed that two models trained independently for upper and lower body joints produced better outcomes than one trained for all joints. On a test data, it had a 97 percent accuracy for lower body activities and an 88-90 percent accuracy for upper body activities.
Download

Paper Nr:	46
Title:	How Can Autonomous Road Vehicles Coexist with Human-Driven Vehicles? An Evolutionary-Game-Theoretic Perspective
Authors:	Isam Bitar, David Watling and Richard Romano
Abstract:	The advent of highly automated vehicles in the form of autonomous road vehicles (ARVs) is bound to bring about a paradigm shift in road user interaction, especially that between ARVs and human-driven vehicles (HDVs). Previous literature on the game-theoretic interaction between ARVs and HDVs tends to focus on working out the best possible strategy for a single interaction, i.e. the Nash equilibrium. This position paper sets out to demonstrate the importance and potential impact of applying evolutionary game theoretic principles to what is effectively a dynamic population driven by evolutionary forces – the population of road users. We demonstrate using theoretical scenarios that simply maintaining Nash equilibria does not guarantee evolutionary success. Instead, ARVs must enjoy a demonstrable advantage over other road users when few in numbers. Otherwise, their uptake will slow down and eventually reverse. We argue that the same selection factors which influence the success of living populations in the natural world also influence the success of the different vehicle types and driving styles in the road user population, including ARVs. We demonstrate this by assigning an expected fitness score to each vehicle in a one-to-one interaction, such as at a junction. This fitness score is dependent on driver, rider and economic costs incurred by the vehicle and/or its occupant(s) during interaction. In turn we show that ARV and transport system designers need to ensure that the fitness score of their systems create evolutionary stability.
Download

Paper Nr:	52
Title:	Towards a Scenario Database from Recorded Driving Data with Regular Expressions for Scenario Detection
Authors:	Philip Elspas, Jonas Lindner, Mathis Brosowsky, Johannes Bach and Eric Sax
Abstract:	With increasing capabilities of Advanced Driver Assistance Systems (ADAS) and Automated Driving Systems (ADS) established automotive development processes are challenged. The specification phase faces an open world problem, with an exploding space of different driving situations and various corner cases. Scenario-based development provides a systematic approach to describe the operational design domain of ADAS and ADS with scenarios, that can be used along the development process until system qualification. However, deriving all relevant scenarios, that need to be considered remains an open challenge. Recorded driving data provides a valuable source of real-world scenarios with highest validity. A database with such scenarios can be used to validate requirements early in the specification phase. For system qualification, detected scenarios can be extended with test conditions or can be (re-)simulated. Furthermore, function development can leverage a scenario database for data-driven and machine learning methods. While a scenario database is a common concept most approaches remain abstract and vague in the description. In this work we analyze requirements and expectations on a scenarios database and propose a detailed design and concept. For the necessary scenario detection, we suggest a new method to identify complex pattern in multivariate time series based on regular expressions.
Download

Paper Nr:	55
Title:	A Framework for Robust Remote Driving Strategy Selection
Authors:	Michael Klöppel-Gersdorf and Thomas Otto
Abstract:	In this paper, a framework for assisting Connected Vehicle (CV) is proposed, with the goal of generating optimal parameters for existing driving functions, e.g., parking assistant or Adaptive Cruise Control (ACC), to allow the CV to move autonomously in restricted scenarios. Such scenarios encompass yard automation as well as valet parking. The framework combines Model predictive control (MPC) with particle filter estimators and robust optimization.
Download

Paper Nr:	56
Title:	Analyzing Airplane Detection Performance with YOLOv4 by using Synthetic Data Domain Randomization
Authors:	Houssem-Eddine Benseddik, Ariane Herbulot and Michel Devy
Abstract:	This paper proposes a novel approach to generate a synthetic dataset through domain randomization, to address the problem of real-time airplane detection on airport zones with high accuracy. Most solutions have been employed and developed across satellite images with deep learning techniques. Our approach specifically targets airplane detection on complex airport environment using deep learning approach as YOLOv4. To improve training, a large amount of annotated training data are required for good performance. To address this issue, this study proposes the use of synthetic training data. There is however a large performance gap between methods trained on real and synthetic data. This paper introduces a new method, which bridges this gap based upon Domain Randomization. The approach is evaluated on bounding box detection of airplanes on the FGVC-Aircraft dataset.
Download

Paper Nr:	58
Title:	Analysis of Efficiency of Full-submerged Archimedes Screws of Rotary-screw Propulsion Units of Snow and Swamp-going Amphibious Vehicles
Authors:	Svetlana Karaseva, Vladimir Belyakov, Vladimir Makarov and Dmitry Malahov
Abstract:	The paper presents results of the numerical analysis of propulsive characteristics of full-submerged Archimedes screws of rotary-screw propulsion units of snow and swamp-going amphibious vehicles with the most typical geometric characteristics for this class of vehicles. The received performance curves and the pictures of visualization of interaction between water environment and Archimedes screws with different helix angles are given. The maximum available values of efficiency determinants of Archimedes screws for cruising and mooring modes are determined. The results of comparative analysis of efficiency of Archimedes screws and propellers with the same operation conditions are considered. The ways to increase the efficiency of rotary-screw propulsion units of snow and swamp-going amphibious vehicles according to the results received are designated. The results and the conclusions obtained as part of the study could be used by developers of amphibian with rotary-screw propulsion units to estimate and provide the overwater characteristics.
Download

Paper Nr:	62
Title:	Estimation of Looming from LiDAR
Authors:	Juan D. Yepes and Daniel Raviv
Abstract:	Looming, traditionally defined as the relative expansion of objects in the observer’s retina, is a fundamental visual cue for perception of threat and can be used to accomplish collision free navigation. The measurement of the looming cue is not only limited to vision and can also be obtained from range sensors like LiDAR (Light Detection and Ranging). In this article we present two methods that process raw LiDAR data to estimate the looming cue. Using looming values, we show how to obtain threat zones for collision avoidance tasks. The methods are general enough to be suitable for any six-degree-of-freedom motion and can be implemented in real-time without the need for fine matching, point-cloud registration, object classification or object segmentation. Quantitative results using the KITTI dataset shows advantages and limitations of the methods.
Download

Paper Nr:	64
Title:	Analyzing Driver Behavior Compliance under HoS Regulations
Authors:	Ignacio Vellido-Expósito, Juan Fernández-Olivares, Raúl Pérez and Luis Castillo
Abstract:	World wide spreaded Hours of Service (HoS) regulations constraint drivers’ amount of working and driving time without resting. Transport companies are extremely interested on interpreting what their drivers are doing, based on the raw information of event logs generated by fleets’ onboard devices, considering the terms defined by HoS regulations. This work addresses the problem of analyzing the compliance of a driver wrt HoS, by using AI techniques to classify and label the information of a driver’s log according to HoS terms. The final result is a human-interpretable descriptive model of driver behaviour that leverages the company situational awareness, empowering staff responsible of operations to make better informed decisions.
Download

Paper Nr:	18
Title:	In-depth Crash Causation Analysis of Motorcyclist Crashes
Authors:	Tereza Tmejová, Robert Zůvala and Kateřina Bucsuházy
Abstract:	Motorcyclists as vulnerable road users are likely to be seriously injured during crashes. Realizing the need for mitigating the serious consequences of motorcyclist crashes, this paper aims to investigate and identify the factors contributing to the crash occurrence. The in-depth data used for the purpose of this study allows the detailed analysis of contributory factors and the whole human functional failure chain leading to the crash as well as the crash mechanism. Not only the failure of motorcyclists leading to the crash was analysed, but also the failure of passenger vehicle drivers involved in a collision with a motorcyclist. To define the risk factors of motorcycle-vehicle crashes, the obtained results focused on the motorcycle-vehicle crashes were compared with the two passenger vehicle crashes. The most typical vehicle–motorcycle crash caused by vehicle driver failure is right of way violation. While motorcyclists frequently fail at the diagnosis level (especially incorrect evaluation of a road difficulty), vehicle drivers mostly fail at the detection level, especially in the intersections. Obtained data highlighted the necessity of the educational and preventive activities focused differently on the motorcyclist and vehicle drivers.
Download

Paper Nr:	19
Title:	Driving Events Identification and Operational Parameters Correlation based on the Analysis of OBD-II Timeseries
Authors:	Dimitrios Rimpas and Andreas Papadakis
Abstract:	On board diagnostics, OBD-II, allowsmonitoring and understanding of the engine operations through continuous access to engine sensors, detection and diagnosis of errors. In this work, we select a set of OBD-II parameters, Short-Term Fuel Trim, Manifold Absolute Pressure, Absolute Throttle Position, Revolutions Per Minute, Calculated Engine Load, Engine Coolant temperature, Vehicle Speed, Catalytic Converter Temperature, to create a set of driving timeseries. A subset of the values belongs to an existing OBD-II dataset with automatic transmission, while the other subset has been retrieved from scratch, using OBD-II, with manual transmission and during characterized driving conditions (cruising, idle and accelerations). We have designed and implemented a set of rules, to recognise three driving events, i.e., idle, gear change, and accelerations in both manual and automatic transmission. The frequency of these events in combination with the parameter values have led to the identification of driving style differences and the impact in fuel consumption. In addition, we have investigated the correlation among the (OBD-II) driving operational parameters during the three driving modes (idle, cruising and acceleration) using the catch22 timeseries analysis framework. The implemented mechanisms are extensible, in terms of considered vehicles, for constant parameter monitoring and cloud-based storing, paving the way for transparent engine status, service maintenance history and other added value services.
Download

Paper Nr:	31
Title:	Real Driving on Under-inflated Rear Tire on Horizontal Curves: A Road Experimental Study
Authors:	Yasmany García-Ramírez
Abstract:	An under-inflated tire represents a high risk of accidents for vehicle occupants and other users. Publications have previously been directed toward monitoring tire pressure and its influence on several driving-controlled experiences. However, little has been written about their impact on a real road trip, for example driving on curves, grades, or unfavourable weather conditions. This study aims to evaluate the relationship between the stability variables on the vehicle in curves of the road when driving on the under-inflated rear tire on wet pavement. In this interesting experience, the left rear tire of a pickup truck was under-inflated to 10 psi (33%). The vehicle travelled more than 50 km of a mountain road. As a result, an average reduction in speed (-6.5%) was found in the right curves and an average increase in lateral acceleration (+ 8.5%) in the right curves in relation to the left ones. As a secondary result, the radius of the curve had a statistical relationship on lateral acceleration and the grade had not. The results of this study, would help to create a new indirect pressure method and in accidents reconstructions.
Download

Paper Nr:	35
Title:	An Application of Scenario Exploration to Find New Scenarios for the Development and Testing of Automated Driving Systems in Urban Scenarios
Authors:	Barbara Schütt, Marc Heinrich, Sonja Marahrens, J. M. Zöllner and Eric Sax
Abstract:	Verification and validation are major challenges for developing automated driving systems. A concept that gets more and more recognized for testing in automated driving is scenario-based testing. However, it introduces the problem of what scenarios are relevant for testing and which are not. This work aims to find relevant, interesting, or critical parameter sets within logical scenarios by utilizing Bayes optimization and Gaussian processes. The parameter optimization is done by comparing and evaluating six different metrics in two urban intersection scenarios. Finally, a list of ideas this work leads to and should be investigated further is presented.
Download

Paper Nr:	49
Title:	An Efficient Strategy for Testing ADAS on HiL Test Systems with Parallel Condition-based Assessments
Authors:	Christian Steinhauser, Maciej Boncler, Jacob Langner, Steffen Strebel and Eric Sax
Abstract:	On the way to full automation the number of Advanced Driver Assistance Systems (ADAS) and the system’s Operational Design Domain (ODD) increase. This challenges today’s prevalent requirement-based testing paradigm in the automotive industry, as for each requirement at least one test is derived. While virtual testing offers scalability for large-scale testing, hardware integration-testing has to be performed under real-time constraints. A significant part of the verification on the target hardware is performed on Hardware-in-the-Loop (HiL) test systems. With the limited number of available HiL systems and their execution being bound to real-time constraints, test time becomes a precious resource. In this work we demonstrate a novel test strategy, that unites today’s requirement-based test process with new concepts for more efficient HiL testing. Maintaining traceability throughout the development process is the main goal. The tests are split into stimuli and evaluation, where only the stimuli are executed on the HiL. This enables parallel assessment of multiple functionalities in one test execution. The concept has been implemented in a productive HiL environment at a German car manufacturer and the evaluation shows benefits in test coverage, as well as reduced test runtime. Moreover, it enables scenario based testing of Highly Automated Driving.
Download

Area 4 - Data Analytics

Short Papers

Paper Nr:	27
Title:	Users’ Privacy Concerns and Attitudes towards Usage-based Insurance: An Empirical Approach
Authors:	Juan Quintero and Alexandr Railean
Abstract:	Usage-based Insurance (UBI) is a car insurance model in which the insurance payment calculations are based on driving data such as speed, acceleration, braking, location, etc. Driving data are collected and analysed by the insurer to provide feedback on driving performance, help drivers improve their skills, and possibly apply a discount on their next renewal. So far, UBI research has been focused more on its architecture, benefits, or acceptance, while the users’ perception of such forms of insurance and their privacy concerns received less attention. To fill this gap, we conducted an online survey with 281 participants and analysed their responses using qualitative and quantitative methods. We found that data collection and sharing are the main privacy concerns. Furthermore, we identified potential discounts as the most important feature in favor of adopting UBI, while data collection and unfair ratings are the main reasons to avoid or quit UBI.
Download

Paper Nr:	34
Title:	Predicting Multiple Traffic Features using a Spatio-Temporal Neural Network Architecture
Authors:	Bogdan Ichim and Florin Iordache
Abstract:	In this paper we present several experiments done with a complex spatio-temporal neural network architecture, for three distinct traffic features and over four time horizons. The architecture was proposed in (Zhao et al., 2020), in which predictions for a single traffic feature (i.e. speed) were investigated. An implementation of the architecture is available as open source in the StellarGraph library (CSIRO's Data61, 2018). We find that its predictive power is superior to the one of a simpler temporal model, however it depends on the particular feature predicted. All experiments were performed with a new dataset, which was prepared by the authors.
Download

Paper Nr:	47
Title:	A Data-driven Energy Estimation based on the Mixture of Experts Method for Battery Electric Vehicles
Authors:	Patrick Petersen, Thomas Rudolf and Eric Sax
Abstract:	Battery electric vehicles (BEVs) are an immediate solution to the reduction of greenhouse gas emissions. However, BEVs are limited in their range by the battery capacity. An accurate estimation of BEV’s range and its energy consumption have become a significant factor in eliminating customers “range anxiety”. To overcome range anxiety, advanced algorithms can predict the remaining capacity, estimate the range and inform the driver. Algorithms need to consider various influencing factors for their range estimation. A crucial part for an accurate range estimation is the energy consumption modeling itself. Thus, machine learning-based approaches are highly investigated which are able to learn nonlinear relations between relevant features and the energy consumption. In this paper, we propose a data-driven approach for the energy estimation of BEVs by utilizing ensemble learning to achieve a feature-specific estimation. In this paper, we trained neural networks on different road types independently. We improve the overall estimation by combining models via the mixture of experts method compared to a monolithic trained neural network. The results demonstrate that specialized neural networks for the energy estimation of BEVs are beneficial for the energy estimation. This approach contributes to reducing range anxiety and therefore helping toward elevated adoption of BEVs.
Download

Paper Nr:	57
Title:	in-Car Entertainment via Group-wise Temporary Mobile Social Networking
Authors:	Mario A. Cimino, Antonio Di Tecco, Pierfrancesco Foglia, Raffaele Giannessi, Jacopo Malvatani, Cosimo A. Prete and Giulio Rossolini
Abstract:	Next generation cars will increase the passengers’ time for fun and relax, as well as the number of unknown passengers traveling together. A key functionality to improve the users’ experience is that of Temporary Mobile Social Networking (TMSN): where passengers form, for a limited-time, a mobile social group with common interests and activities, using their already available social network accounts. The goal of TMSN is to automatically redesign the users’ profiles and interfaces into a group-wise passengers’ profile and a common interface, by reducing isolation and enabling socialization. In this paper, a TMSN-inspired music selection is proposed and developed via the Spotify music streaming service. Early results are promising and encourage further developments towards the concept of in-car entertainment.
Download

Paper Nr:	29
Title:	A Bayesian Network for the Analysis of Traffic Accidents in Peru
Authors:	Willy Ugarte, Manuel Alcantara-Zapata, Leibnihtz Ayamamani-Choque, Renzo Bances-Morales and Cristian Cabrera-Sanchez
Abstract:	Traffic accidents are a problem that affects the State and society, because they cause material damage, injuries and even the death of a person. This has led countries such as China, Switzerland and Australia to carry out studies using Bayesian networks to determine the main causes and, based on them, propose measures to reduce the number of traffic accidents. Following this trend, we, without having any expert knowledge on the subject, decided to analyze the data of traffic accidents on the Pan-American Highway in Lima, Peru. This analysis was done by means of directed graph learning with the Hill Climbing Search, Chow-Liu, K2, BIC and BDEU. In addition, we used a Bayesian estimator to calculate the conditional probability distribution for our dataset. This dataset contains observations from the years 2017 to 2019 and approximately 16 km of this highway. Our results show that it is possible to identify the possible causes of excess accidents in specific areas of the Pan-American Highway in certain shifts i.e., 32% of fatal accidents occur between 12 am and 7 pm in the Rimac district and of these 20% are due to pedestrians on the highway.
Download

Area 5 - Smart Mobility and Sustainable Transport Services

Full Papers

Paper Nr:	41
Title:	Smart Mobility Support for Vehicle-based Tourism: Theoretical and Technological Foundations
Authors:	Sergey Mikhailov, Alexey Kashevnik, Alexander Smirnov and Vladimir Parfenov
Abstract:	Vehicle-based tourism becomes more and more important in the era of the pandemic. Tourism management is an important challenge for the tourist region development. The construction of a personalized attraction visiting route for tourists with personal vehicles has a great impact on the tourist flows. The authors propose theoretical and technological foundations for smart mobility support of vehicle-based tourists. We propose to predict tourist preferences by using deep neural networks for the prediction model’s implementation and demonstrated 70-80% accuracy in training on completed tourist trips to St. Petersburg, Russia. The tourist route attractiveness prediction was used to assess the constructed route quality. The attraction attractiveness and attendance prediction together with potential tourist trajectory prediction were used for attraction selection process personification. The obtained results can be used in smart mobility support systems to improve the travel experience.
Download

Paper Nr:	59
Title:	Low-emission Commuting with Micro Public Transport: Investigation of Travel Times and CO2 Emissions
Authors:	Marcel Ciesla, Victoria Oberascher, Sven Eder, Stefan Kirchweger, Wolfgang E. Baaske and Gerald Ostermayer
Abstract:	The omnipresent trend towards sustainable mobility is a major challenge, especially for commuters in rural areas. The use of micro public transport systems is expected to significantly reduce pollutant emissions, as several commuters travel the first mile together with a single pick-up bus instead of their own car. In this paper, different aspects of such a micro public transport system are analyzed. The main findings of the investigations should be how the travel times of commuters change and how many CO2 emissions can be saved if some of the commuters use public transport instead of their own vehicle.
Download

Short Papers

Paper Nr:	61
Title:	Shared Automated Mobility: The Legal and Governance Considerations
Authors:	Malcolm Falzon and Odette Lewis
Abstract:	Automated vehicle technology is a fast-growing phenomenon which has, in recent years, found itself at the forefront of research projects being carried out in jurisdictions all over the world, and is a vital component to the modern revolution of the transport sector in the race against climate change. However, attaining a world with driverless cars and digital infrastructure, which eliminates the role of the driver, requires a detailed study from multiple aspects, including from a legal and governance perspective. A holistic, proportionate, and harmonised approach towards a dedicated body of legislation, which strikes the right balance between safeguarding consumers and a free market, is crucial to reaping the full potential of this technology, as the demand for alternative mobility solutions increases. This paper considers the legal impacts, which automated vehicles are expected to have on mobility, analysing in particular the challenges posed, the adequacy of existing legal systems, and the improvements that need to be made, on the basis of international research, with a particular focus on Malta. Project MISAM (Malta’s Introduction of Shared Autonomous Mobility) was launched specifically for the purpose of assessing the viability of enabling the use of automated vehicles in Malta, including from a legal and governance perspective.
Download