VEHITS 2023 Abstracts

Area 1 - Connected Vehicles
Full Papers Short Papers
Area 2 - Intelligent Transport Systems and Infrastructure
Full Papers Short Papers
Area 3 - Intelligent Vehicle Technologies
Full Papers Short Papers
Area 4 - Data Analytics
Short Papers
Area 5 - Smart Mobility and Sustainable Transport Services
Short Papers

Area 1 - Connected Vehicles

Full Papers
Paper Nr: 29
Title:

Hybrid Optimal Traffic Control: Combining Model-Based and Data-Driven Approaches
Authors:

Urs Baumgart and Michael Burger
Abstract: We study different approaches to use real-time communication between vehicles, in order to improve and to optimize traffic flow in the future. A leading example in this contribution is a virtual version of the prominent ring road experiment in which realistic, human-like driving generates stop-and-go waves. To simulate human driving behavior, we consider microscopic traffic models in which single cars and their longitudinal dynamics are modeled via coupled systems of ordinary differential equations. Whereas most cars are set up to behave like human drivers, we assume that one car has an additional intelligent controller that obtains real-time information from other vehicles. Based on this example, we analyze different control methods including a nonlinear model predictive control (MPC) approach with the overall goal to improve traffic flow for all vehicles in the considered system. We show that this nonlinear controller may outperform other control approaches for the ring road scenario but intensive computational effort may prevent it from being real-time capable. We therefore propose an imitation learning approach to substitute the MPC controller. Numerical results show that, with this approach, we maintain the high performance of the nonlinear MPC controller, even in set-ups that differ from the original training scenarios, and also drastically reduce the computing time for online application.
Download
Paper Nr: 54
Title:

V2X Tolling System for C-ITS Environments
Authors:

Emanuel Vieira, Tiago Dias, João Almeida, Ana V. Silva, Joaquim Ferreira and Lara Moura
Abstract: Electronic Toll Collection (ETC) has several decades of history worldwide. Vehicle-to-everything (V2X) communication technology is a more recent innovation but has been a central topic in the ITS community for more than a decade now. However, V2X technology adoption in vehicles has been limited and applications are mostly related to safety use cases. In this paper, V2X-based tolling applications are studied, as well as their feasibility, and how these applications could be enablers of a more massive V2X adoption in vehicles. V2X Tolling standards and solutions from SAE and ETSI are explored. A novel solution is presented, followed by a comparison with previous proposals and standards. Finally, preliminary results from the proposed system are presented and analyzed.
Download
Short Papers
Paper Nr: 3
Title:

V2X Communication Test Tool for Scenario-Based Assessment of Truck Platooning
Authors:

Jacco van de Sluis and Jan de Jongh
Abstract: The EU-funded ENSEMBLE project ∗ designs, realizes, tests and validates novel multi-brand platooning technology for trucks in a consortium consisting of all European truck OEMs, first-tier suppliers, branch organisa-tions and academic and research institutes. This paper describes the project’s approach towards (intermediate) testing of the V2X communications, specifically focusing at Hardware-in-the-Loop (HiL) testing through the use of a custom V2X Test Tool developed in ENSEMBLE. The tool enables scenario-based assessment of truck platooning with the newly defined platooning protocol and (pre-standard) V2V messages. Next to V2V message conformance testing, it offers V2X communication functional testing and performance testing capabilities for different platooning scenarios. The V2X Test Tool is used for verification and validation of platooning solutions, and facilitates the next steps of testing truck platooning at proving grounds and in real-life environments.
Download
Paper Nr: 47
Title:

Enhancing Vulnerable Road User Awareness of Intelligent Transport Systems Through Relay and Aggregation of Collective Perception Messages with Road Side Units
Authors:

Vincent A. Wolff
Abstract: The Collective Perception Service (CPS) allows connected vehicles to gain a more comprehensive picture of their environment by sharing information about the dynamic state of objects with other vehicles and infrastructure. Objects detected by on-board sensors are shared through Vehicle-to-Vehicle (V2V) or Vehicle-to-Infrastructure (V2I) communication. However, the range of V2V communication is limited, and Road Side Units (RSUs) can be deployed to enhance the range and attenuate the negative effects of V2V signal propagation. We enhance the vehicular network by RSUs to aggregate and forward Collective Perception Messages (CPMs) received from neighboring vehicles, thus improving the overall environmental perception and the perception of Vulnerable Road Users (VRUs) in particular. Our simulation results, based on the ETSI ITS-G5 standard, demonstrate the effectiveness of the CPS in an urban intersection scenario, showing the positive impact of additional V2I communication and the deployment of RSUs on vehicular perception of VRUs. The addition of RSUs results in a significant improvement in VRU perception, while packet loss on the network channel increases moderately.
Download
Paper Nr: 24
Title:

Optimizing CAV Driving Behaviour to Reduce Traffic Congestion and GHG Emissions
Authors:

Saad Roustom and Hajo Ribberink
Abstract: This study was conducted to identify an optimal driving behaviour of connected and automated vehicles (CAV) that can reduce traffic congestion and GHG emissions under different traffic demand levels. The study employed traffic simulations at the meso scale for the City of Ottawa, Canada, to assess traffic performance and used correlation models to estimate GHG emissions. Aggressive CAVs showed the greatest potential to enhance traffic performance and reduce GHG emissions under all traffic demand levels. The results show that Aggressive CAVs can increase highway capacity and lower vehicle travel time in comparison to Driver Operated Vehicles (DOVs) or CAVs with a less aggressive driving style. The findings of the study indicate that CAVs with aggressive driving behavior can play a crucial role in enhancing traffic performance and in helping to mitigate the adverse impact of transportation on the environment. The results of this study aim to encourage regulatory bodies to adopt effective CAV-related policies that can enhance traffic performance and reduce GHG emissions.
Download
Paper Nr: 56
Title:

How to Model Privacy Threats in the Automotive Domain
Authors:

Mario Raciti and Giampaolo Bella
Abstract: This paper questions how to approach threat modelling in the automotive domain at both an abstract level that features no domain-specific entities such as the CAN bus and, separately, at a detailed level. It addresses such questions by contributing a systematic method that is currently affected by the analyst’s subjectivity because most of its inner operations are only defined informally. However, this potential limitation is overcome when candidate threats are identified and left to everyone’s scrutiny. The systematic method is demonstrated on the established LINDDUN threat modelling methodology with respect to 4 pivotal works on privacy threat modelling in automotive. As a result, 8 threats that the authors deem not representable in LINDDUN are identified and suggested as possible candidate extensions to LINDDUN. Also, 56 threats are identified providing a detailed, automotive-specific model of threats.
Download
Paper Nr: 59
Title:

Using DSRC Road-Side Unit Data to Derive Braking Behavior
Authors:

Rahul Sengupta, Tania Banerjee, Yashaswi Karnati, Sanjay Ranka and Anand Rangarajan
Abstract: With the increasing deployment of Connected Vehicle Technology (via DSRC/CV2X), public traffic authorities are presented with a potential treasure trove of valuable data for analysis. However, several practical limitations exist that pose unique challenges in this publicly-collected data such as lack of vehicle re-identification due to privacy measures, sparsity of data, limited range of transmission, noise in recorded trajectories etc. In this paper, we analyze trajectories for braking behaviors of Connected Vehicle Road-side Unit (RSU) data. The dataset consists of trajectories collected from a dense urban grid consisting of 25 intersections along 4 high-volume arterials, for a period of 1 year. We begin by providing a brief description of the data collection and processing modalities. We then present a tool to perform exploratory analytics on the data with a focus on anomalous trajectories with hard-braking events. We show the benefits of such a tool for public traffic authorities to gain insights into the performance and safety aspects of urban arterials, and to guide policy decisions.
Download

Area 2 - Intelligent Transport Systems and Infrastructure

Full Papers
Paper Nr: 4
Title:

Incident-Aware Distributed Signal Systems in Self-Organised Traffic Control Systems
Authors:

Sven Tomforde, Yanneck Ohl and Ingo Thomsen
Abstract: Traffic congestion is a major contributor to carbon dioxide emissions and causes air pollution which poses various health risks. In response to such challenges, traffic management systems are becoming increasingly intelligent and adaptive. Particularly self-organised approaches such as the Organic Traffic Control (OTC) system offer additional advantages such as efficiency, scalability, and robustness. In addition to the local and traffic-dependent switching of traffic signals, a central task of such a system is the coordinated adaptation of traffic lights by means of Progressive Signal Systems. In this paper, we present a novel approach for establishing decentralised PSSs that takes into account recognised incidents and thus proactively ensures optimised traffic flows. We develop three different strategies and evaluate them using realistic simulations.
Download
Short Papers
Paper Nr: 9
Title:

Distributed Collaborative Incident Validation in a Self-Organised Traffic Control System
Authors:

Ingo Thomsen, Torben Brennecke and Sven Tomforde
Abstract: The continuous trend of raising traffic volumes in urban areas causes waiting times and exhaust emissions. As one promising response to these challenges, increasingly intelligent and adaptive traffic management systems are being developed. For instance, self-organised approaches such as the Organic Traffic Control offer advantages in terms of scalability and robustness compared to traditional systems. This can be increased by taking locally detected incidents into account. To improve the accuracy of automatically detected incidents and to allow for integration in the traffic control strategies, this paper proposes algorithms for the validation of potential incidents. This is done by incorporating respective insights of varying levels from neighbouring intersections and consequently determining a neighbour-supported view of local incident information.
Download
Paper Nr: 19
Title:

Context-Aware Travel Support During Unplanned Public Transport Disturbances
Authors:

Åse Jevinger, Emil Johansson, Jan A. Persson and Johan Holmberg
Abstract: This paper explores the possibilities and challenges of realizing a context-aware travel planner with bidirectional information exchange between the actor and the traveller during unplanned traffic disturbances. A prototype app is implemented and tested to identify potential benefits. The app uses data from open APIs, and beacons to detect the traveller context (which train or train platform the traveller is currently on). Alternative travel paths are presented to the user, and each alternative is associated with a certainty factor reflecting the reliability of the travel time prognoses. The paper also presents an interview study that investigates PT actors’ views on the potential use for actors and travellers of new information about certainty factors and travellers’ contexts, during unplanned traffic disturbances. The results show that this type of travel planner can be realized and that it enables travellers to find ways to reach their destination, in situations where the public travel planner only suggests infeasible travel paths. The value for the traveller of the certainty factors are also illustrated. Additionally, the results show that providing actors with information about traveller context and certainty factors opens up for the possibility of more advanced support for both the PT actor and the traveller.
Download
Paper Nr: 20
Title:

Analytical Model for Winter Road Maintenance Efficiency Determination
Authors:

Liva Deksne, Viesturs Pavlovs, Dainis Dosbergs and Martins Zviedris
Abstract: Analytical model to increase the Winter Road Maintenance (WRM) cost-efficiency has been developed. It supports the planned WRM decision-support system and is a crucial element to plan, develop and maintain a cost-efficient WRM system. The model emphasizes the indirect costs of WRM, and the importance level of data sources used to define winter road conditions in a certain area. Multiple measurements of data provided by data sources are carried out and are used as the main WRM cost-influencing factor. The model determines steps and guidelines for the calculation of the WRM costs and the impact of data sources used to define road and driving conditions.
Download
Paper Nr: 26
Title:

Instance Segmentation and Detection of Children to Safeguard Vulnerable Traffic User by Infrastructure
Authors:

Shiva Agrawal, Savankumar Bhanderi, Sumit Amanagi, Kristina Doycheva and Gordon Elger
Abstract: Cameras mounted on intelligent roadside infrastructure units and vehicles can detect humans on the road using state-of-the-art perception algorithms, but these algorithms are presently not trained to distinguish between human and adult. However, this is a crucial requirement from a safety perspective because a child may not follow all the traffic rules, particularly while crossing the road. Moreover, a child may stop or may start playing on the road. In such situations, the separation of a child from an adult is necessary. The work in this paper targets to solve this problem by applying a transfer-learning-based neural network approach to classify child and adult separately in camera images. The described work is comprised of image data collection, data annotation, transfer learning-based model development, and evaluation. For the work, Mask-RCNN (region-based convolutional neural network) with different backbone architectures and two different baselines are investigated and the perception precision of the architectures after transfer-learning is compared. The results reveal that the best performing trained model is able to detect and classify children and adults separately in different road scenarios with segmentation mask AP (average precision) of 85% and bounding box AP of 92%.
Download
Paper Nr: 34
Title:

A Path-Depended Passenger Flow Forecasting Model for Metro Rail Systems Using LSTM Neural Network
Authors:

Jaison P. Mulerikkal, Deepa M. Dixon and Sajanraj Thandassery
Abstract: The primary goal of this work is to develop a framework for short term passenger flow prediction for metro rail transport systems. A reliable prediction of short-term passenger flow could greatly support metro authorities’ decision process. Both inflow and outflow of the metro stations are strongly associated with the travel demand within metro networks. Sequestered station-wise analysis ignores the spatial correlations existing between the stations. This paper tries to merge the spatial with the temporal by employing an indirect method of computing flow through O-D estimates for the same. Path-depended station-pairs of O-D flow are considered for employing a customized LSTM network. Experimental results indicate that the proposed passenger flow prediction model is capable of better generalization on short-term passenger flow than standard models of learning compared. This work also establishes that O-D prediction provides an indirect estimation procedure for passenger flow. The specific use case for this work is Kochi Metro Rail Limited (KMRL). A highlight of the work is that the whole analytics and modelling procedures are written on a customized scalable big-data platform (Jaison Paul Data Analytics Platform) JP-DAP which was developed prior to this work.
Download
Paper Nr: 41
Title:

Approaches to Automatic Road Traffic Incident Detection and Incident Forecasting
Authors:

Sören Striewski, Ingo Thomsen and Sven Tomforde
Abstract: Traditional traffic light controllers are unable to respond to variations in traffic demand as they generally rely on fixed-time signalisation with predefined sequences. This work presents two algorithms, one for incident detection and one for congestion forecasting. The Extended California Algorithm (ECA), an incident detection algorithm, addresses flaws in the established California Algorithm. The congestion forecast algorithm detects occurrences when traffic exceeds the capacity of the accessible roads by comparing the present dynamic road capacity with the anticipated future traffic flow. Both are then compared with the established California algorithm.
Download
Paper Nr: 45
Title:

On the Adjacency Matrix of Spatio-Temporal Neural Network Architectures for Predicting Traffic
Authors:

Sebastian Bomher and Bogdan Ichim
Abstract: We present in this paper some experiments with the adjacency matrix used as input by three spatio-temporal neural networks architectures when predicting traffic. The architectures were proposed in (Chen et al., 2022), (Li et al., 2018) and (Yu et al., 2018). We find that the predictive power of these neural networks is influenced to a great extent by the inputted adjacency matrix (i.e. the weights associated to the graph of the available traffic infrastructure). The experiments were made using two newly prepared datasets.
Download
Paper Nr: 46
Title:

An Infrastructure-Based Trust Management Framework for Cooperative ITS
Authors:

Rihab Abidi, Nabil Sahli, Wassim Trojet, Nadia Ben Azzouna and Ghaleb Hoblos
Abstract: Intelligent Transportation Systems (ITSs) have been exploited by developed countries to enhance the quality of transportation services. However, these systems are still facing major bottlenecks to be addressed such as the data density, precision and reliability of perceived data and computational feasibility of the nodes. Trust management is a mechanism applied to secure the vehicular networks. However, most of the proposed trust models that are applied to Vehicular Ad-hoc NETwork (VANET) do not address all the aforementioned challenges of ITS. In this paper, we present a comprehensive framework of trust management specifically designed for ITS applications. The proposed framework is an infrastructure-based solution that relies on Smart Road Signs (SRSs) to assess the trustworthiness of traffic data and nodes of the network. The idea of the framework is to use autonomous SRSss that are able to collect raw data and evaluate it in order to alert the drivers with reliable traffic information in real time. We adopt a hierarchical architecture that exploits a two-level trust evaluation to ensure accuracy, scalability, security and high reactivity of ITS applications. A discussion of the framework and its strengths is presented.
Download
Paper Nr: 48
Title:

Aggregating Pairwise Information Over Optimal Routes
Authors:

Grzegorz Herman and Grzegorz Gawryał
Abstract: Public transport planning is a complex task in which many factors must be considered. One of these factors is route profitability, highly dependent on the demand for a given connection. Computing such demands quickly in a potentially changing environment is crucial in suggesting and comparing multiple alternative routes. In this preliminary paper, we propose a mathematical model for this problem, adequate for transport modes with intermediate stops on their routes. We analyze similar problems in the literature, provide some efficient algorithms with good theoretical bounds, and evaluate them on real-life road networks. We also pose open research questions related to further generalization, improvement, and better understanding of the problem.
Download
Paper Nr: 51
Title:

Simulation Environment for Traffic Control Systems Targeting Mixed Autonomy Traffic Scenarios
Authors:

Christopher Link, Kevin Malena, Sandra Gausemeier and Ansgar Trächtler
Abstract: The development of autonomous vehicles and their introduction in urban traffic offer many opportunities for traffic improvements. In this paper, an approach for a future traffic control system for mixed autonomy traffic environments is presented. Furthermore, a simulation framework based on the city of Paderborn is introduced to enable the development and examination of such a system. This encompasses multiple elements including the road network itself, traffic lights, sensors as well as methods to analyse the topology of the network. Furthermore, a procedure for traffic demand generation and routing is presented based on statistical data of the city and traffic data obtained by measurements. The resulting model can receive and apply the generated control inputs and in turn generates simulated sensor data for the control system based on the current system state.
Download
Paper Nr: 58
Title:

Unlocking the Wheel: Insights into Shared Micromobility Perceptions and Adoption on Campus
Authors:

Maryna Pobudzei, Ilona Wichmann and Silja Hoffmann
Abstract: Prior to implementing a shared micromobility system, it is crucial to carefully consider its design and features. Through consulting with stakeholders, system designers must determine the types of vehicles to be included in the shared fleet, which should align with local usage patterns. Additionally, shared micromobility planners must develop an operational concept that reflects local application scenarios. This study examines attitudes and opinions towards shared micromobility, as well as usage intentions and purposes for different types of shared micromobility vehicles such as pedal bikes, e-bikes, e-cargo bikes, e-scooters, e-mopeds, and e-cabin scooters. Additionally, we investigate preferences for free-floating and station-based shared mobility systems. This research links these findings to demographic characteristics, attitudes, and travel behavior. The analysis contributes to the field by understanding perceptions towards shared micromobility, characterizing potential users and non-users, and identifying preferences for certain operational concepts and types of shared vehicles. These insights can be used to design and implement a customized and user-centered shared micromobility system.
Download
Paper Nr: 27
Title:

Generation of Concrete Parameters from Logical Urban Driving Scenarios Based on Hybrid Graphs
Authors:

Christoph Glasmacher, Hendrik Weber, Michael Schuldes, Nicolas Wagener and Lutz Eckstein
Abstract: Safety assurance of highly automated driving functions is a major challenge in today‘s research and requires the development of new validation methods. Scenario-based testing is a promising approach to handle the variety of possible situations efficiently. Due to the limited availability of real-world derived scenarios, they are increasingly generated synthetically. Whereas actual approaches to generate concrete parameters are mostly either knowledge- or data-driven, we propose a methodology to combine these approaches. We model the correlation of parameters in real-world data as multivariate probability functions by using copulas. In addition, we establish modular causal and constraint relations combining Bayesian networks and constraint graphs to add semantic knowledge about parameters and their interactions. Thereby, road user behavior and physical equations are represented. The application of our generation method on urban intersections shows the capability to sample high-dimensional parameter spaces with limited input data. Hereby, it offers the opportunity to create realistic scenarios to extend the database for scenario-based assessment.
Download
Paper Nr: 52
Title:

Impacts of Connected Automated Vehicles on Large Urban Road Network
Authors:

Qiong Lu, Alessio Tesone and Luigi Pariota
Abstract: As an essential component of the Cooperative Intelligent Transportation System (C-ITS), Connected Automated Vehicles (CAVs) are anticipated to play a significant role in the development of the future mobility service. This paper investigates the impacts of different penetration of CAVs on the urban road network. The investigation is carried out in a vast urban network with Simulation of Urban MObility (SUMO), a microscopic traffic simulator. The estimated factors of the network are network maximum flow, critical density, average speed, congestion duration, and roadway over-saturation degree. The Macroscopic Fundamental Diagram (MFD) has been used to estimate the maximum flow and critical density. In a simulation way, it substantiated that a road network could have less scattered MFDs, even if the traffic flow is distributed heterogeneously. The congestion duration and over-saturation degree are used to check traffic congestion. The simulation results show that applying 100% CAVs can contribute about a 13.55% increase in maximum flow. A similar trend can be found in the critical density for different CAV penetration rates. In a similar congestion situation, the network with 100% CAV driving in can carry more than 130% of the original travel demand. In terms of congestion level, even a low CAV penetration rate may significantly improve the traffic condition.
Download

Area 3 - Intelligent Vehicle Technologies

Full Papers
Paper Nr: 5
Title:

Integrated Optimization of Vehicle Trajectories and Traffic Signal Timings
Authors:

Hao Chen and Hesham A. Rakha
Abstract: This research develops a bi-level optimizer that provides energy-optimal control for vehicles and traffic signals. The first level optimizes the traffic signal timings to minimize the total energy consumption of approaching vehicles. The traffic signal optimization can be easily implemented in real-time traffic signal controllers and overcomes the shortcomings of the traditional Webster method, which overestimates the cycle length when the traffic volume-to-capacity ratio exceeds 50 percent. The lower-level optimizer is the vehicle speed controller, which calculates the optimal vehicle brake and throttle levels to minimize the energy consumption of individual vehicles. The proposed integrated controller is first tested on an isolated signalized intersection, and then on an arterial network with multiple signalized intersections to investigate the performance of the proposed controller under various traffic demand levels. The test results demonstrate that the proposed integrated controller can greatly improve energy efficiency producing fuel savings of up to 17.7%. It can also enhance traffic mobility by reducing traffic delays by up to a 47.2% and reducing vehicle stops by up to 24.8%.
Download
Paper Nr: 6
Title:

Towards Building a Naturalistic Cycling Dataset Capturing Bicycle/Car Interactions
Authors:

Fahd Alazemi, Karim Fadhloun, Hesham Rakha and Archak Mittal
Abstract: As machine learning and computer vision techniques and methods continue to advance, the collection of naturalistic traffic data from video feeds is becoming more and more feasible. That is especially true for the case of bicycles, for which the collection of naturalistic data is not achievable in the traditional vehicle approach. This study describes a research effort that aims to extract naturalistic cycling data from a video dataset for use in safety and mobility applications. The used videos come from a dataset collected in a previous Virginia Tech Transportation Institute study in collaboration with SPIN in which continuous video data at a non-signalized intersection on the Virginia Tech campus was recorded. The research team applied computer vision and machine learning techniques to develop a comprehensive framework for the extraction of naturalistic cycling trajectories. In total, this study resulted in the collection and classification of 619 bicycle trajectories based on their type of interactions with other road users. The results confirm the success of the proposed methodology in relation to extracting the locations, speeds, and accelerations of the bicycles at a high level of precision. Furthermore, preliminary insights into the acceleration and speed behavior of bicyclists around motorists are determined. The resulting dataset will be made available to the research community once the required approvals have been obtained from the study sponsors.
Download
Paper Nr: 11
Title:

Visual Looming from Motion Field and Surface Normals
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. In this paper we derive novel solutions for obtaining visual looming quantitatively from the 2D motion field resulting from a six-degree-of-freedom motion of an observer relative to a local surface in 3D. We also show the relationship between visual looming and surface normals. We present novel methods to estimate visual looming from spatial derivatives of optical flow without the need for knowing range. Simulation results show that estimations of looming are very close to ground truth looming under some assumptions of surface orientations. In addition, we present results of visual looming using real data from the KITTI dataset. Advantages and limitations of the methods are discussed as well.
Download
Paper Nr: 12
Title:

Towards Effective Traffic Signal Safety and Optimization Using Fisheye Video
Authors:

Rahul Sengupta, Tania Banerjee, Ke Chen, Yashaswi Karnati, Sanjay Ranka and Anand Rangarajan
Abstract: Most traffic authorities across the US usually collect high-resolution (10 Hz) loop detector and signal state data and video data. The multiple modalities of data that are readily available can be utilized for better traffic operations management and improving safety. In this work, we show that the fusion of widely deployed loop detector data with trajectory information collected through video cameras can augment intersection safety and operational efficiency analysis. The additional information that can be extracted from the object’s (vehicle and pedestrian) trajectory derived from video data when fused with signal state data leads to several interesting safety analyses. Data analysis shows a significant variance in turn-movement counts, pedestrian behaviors, vehicle composition, etc., temporally (hour-of-day, day-of-week, etc.) and spatially (approach-wise). We present a simulation-based approach for customizing signal timing plans based on the traffic behavior at the intersections at various times. When used to drive simulations in demand generation, we show that the fused data calibrating the simulation parameters can lead to potential improvements in existing signal timing plans that match reality and can greatly help improve intersection safety and operational efficiency by providing planners with data-driven insights.
Download
Paper Nr: 14
Title:

3D Object Detection for Autonomous Driving: A Practical Survey
Authors:

Álvaro Ramajo-Ballester, Arturo de la Escalera Hueso and José María Armingol Moreno
Abstract: Autonomous driving has been one of the most promising research lines in the last decade. Although still far off the sought-after level 5, the research community shows great advancements in one of the most challenging tasks: the 3d perception. The rapid progress of related fields like Deep Learning is one the reasons behind this success. This enables and improves the processing algorithms for the input data provided by LiDAR, cameras, radars and such other devices used for environment perception. With such growing knowledge, reviewing and structuring the state-of-the-art solutions becomes a necessity in order to correctly address future research directions. This paper provides a comprehensive survey of the progress of 3D object detection in terms of sensor data, available datasets, top-performing architectures and most notable frameworks that serve as a baseline for current and upcoming works.
Download
Paper Nr: 15
Title:

25Gbps Automotive Ethernet ECU PCB: MDI Design Implementation and Insertion Loss Characterization
Authors:

Jamila J. Borda, Kirsten Matheus and Friedel Gerfers
Abstract: Physical Layer (PHY) Signal Integrity (SI) aspects of an Automotive Ethernet communication channel are characterized using Radio Frequency (RF) parameters. With increasing Automotive Ethernet data rates, communication channel signal attenuations (i.e., Insertion Loss (IL)) are significantly worsened. At 25Gbps data rate, the communication in cars faces various electrical limits and all components (i.e., segments) of the communication channel have to be optimized in order to reach the expected performance requirements. One such component is the Electronic Control Unit (ECU) Printed Circuit Board (PCB) Media Independent Interface (MDI). Consequently, for such high-speed links, ECU PCB electrical and material properties have an impact on the overall IL. Considering the stringent Automotive Ethernet channel electrical requirements, this study proposes and characterizes ECU PCB MDI design concepts for a 25Gbps in-vehicle Ethernet connectivity. Furthermore, the design concepts are manufactured on test boards to characterize the corresponding MDI signal IL budget. The characterizations are conducted using RF test bench measurement and a defined simulation approach. Lastly, in relation to test bench measurements, this study investigates and characterizes to what extent simulations can serve as either an alternative or a coexisting option for in-vehicle 25Gbps MDI IL characterizations, validations, and qualifications.
Download
Paper Nr: 39
Title:

Towards a Topological Map-Matching Algorithm for Solid Waste Collection Systems
Authors:

Carola A. Blazquez, Roberto León and Luis Delgado
Abstract: Global Navigation Satellite Systems (GNSS) such as Global Positioning Systems (GPS) are employed in different Intelligent Transportation Systems (ITS) applications to determine vehicle routes. However, the map-matching problem emerges when GPS measurements are assigned to incorrect road segments on a digital map due to the complexities of the road network and errors from different sources when capturing GPS data. This study presents a Topological Map-Matching Algorithm (TMMA) for determining correct waste collection vehicle routes using GPS measurements in an offline context to help improve solid waste collection services and compute proper performance measures. The TMMA is applied to a real-world case study with ten waste collection routes in the commune of Renca in Santiago, Chile. Overall, results indicate that the accuracy of the algorithm is greater than 90%, and small percentages of false negative cases with unsnapped GPS data points are obtained for most vehicle routes. The sensitivity analysis suggests that larger buffer sizes and higher speed tolerances yield the best solution quality and execution times.
Download
Paper Nr: 55
Title:

Does the Intelligent Driver Model Adequately Represent Human Drivers?
Authors:

Zeyu Mu, Fatemeh Jahedinia and B. B. Park
Abstract: The Intelligent Driver Model (IDM) is one of the widely used car-following models to represent human drivers in mixed traffic simulations. However, the standard IDM performs too well in energy efficiency and comfort (acceleration) compared with real-world human drivers. In addition, many studies assessed the performance of automated vehicles interacting with human-driven vehicles (HVs) in mixed traffic where IDM serves as HVs based on the assumption that the IDM represents an intelligent human driver that performs not better than automated vehicles (AVs). When a commercially available control system of AVs, Adaptive Cruise Control (ACC), is compared with the standard IDM, it is found that the standard IDM generally outperforms ACC in fuel efficiency and comfort, which is not logical in an evaluation of any advanced control logic with mixed traffic. To ensure the IDM reasonably mimics human drivers, a dynamic safe time headway concept is proposed and evaluated. A real-world NGSIM data set is utilized as the human drivers for simulation-based comparisons. The results indicate that the performance of the IDM with dynamic time headway is much closer to human drivers and worse than the ACC system as expected.
Download
Short Papers
Paper Nr: 1
Title:

Traffic Data Evaluation for Automated Driving Handover Scenarios
Authors:

Eugenia Rykova, Juri Golanov, Jonas Vogt, Daniel Rau and Horst Wieker
Abstract: At the current stage of automated vehicle development, the control handover from the system to a human driver (and back) is inevitable. It is essential to distinguish between situations in which the handover is possible and in which it could be dangerous and is therefore highly undesirable. We evaluated traffic situations based on two modalities: own vehicle state and traffic objects. To assess the former, supervised machine learning was applied, reaching an accuracy of 80.3% and specificity of 77.8% with Multilayer perceptron Classification. Traffic objects data were subject to different clustering techniques. The final grouping was done according to manually elaborated rules, resulting in a range of situation complexity scores. Improving the discriminative power of vehicle state classification, including driver’s state and weather information, and predicting situation complexity are to be addressed in future research.
Download
Paper Nr: 21
Title:

ASIMS: Acceleration Spectrograms Based Intelligent Mobility System for Vehicle Damage Detection
Authors:

Sara Khan, Mehmed Yüksel and Andre Ferreira
Abstract: Every vehicle is susceptible to several types of small physical damage such as dents and scratches. These damages can be seen as cosmetic damages as they impact the vehicle’s visual and value but do not alter its main functions. Vehicle owners, insurance companies, and the car-rental/taxi-service companies are especially keen to detect the events that generate these kinds of damages. The ability to detect impact events is valuable to monitor the occurrence of possible damages to the vehicles. In this paper, we present a novel acceleration spectrogram-based Machine Learning (ML) approach for dynamic (real-time) small vehicle damage detection using inertial sensors. Inertial sensors are low-resource consumption sensors, which makes the proposed solution economical. Conventionally, inertial sensors are used in the airbag control system but they are not developed to detect impacts that generate minor damages. Most of the previous work on small impact detection either uses smartphone inertial data which is not accurate or focuses on static damage detection based on image sensory inputs. Our intelligent impact and damage detection ML-based system uses autoencoders as an automatic feature extractor using acceleration spectrograms and classifies the sensory encoded feature representation into damage or non-damage. It can achieve an accuracy of 0.8. This approach sets the stage for various potential research directions in damage detection.
Download
Paper Nr: 28
Title:

Development of a Smartphone App for Lane Departure Warning
Authors:

Nafisa Z. Tasnim, Attiq U. Zaman and M. I. Hayee
Abstract: Unintentional Lane departure is a significant safety risk. Currently, available commercial lane departure warning systems use vision-based or GPS technology with lane-level resolution. These techniques have their own performance limitations and are complex and expensive to implement, inhibiting their widespread market penetration. We have previously developed a lane departure detection (LDD) algorithm using standard GPS technology. Our algorithm acquires the trajectory of a moving vehicle in real-time from a standard GPS receiver and compares it with a road reference heading (RRH) to detect any potential lane departure. The necessary RRH is obtained from one or more past trajectories on that road using our previously developed RRH generation algorithm. Our previous field tests have shown that our lane departure detection and warning technique is robust enough to detect unintentional lane departures successfully. Due to its robustness and simplicity, we have now developed a smartphone app for this technique incorporating our previously developed LDD and RRH generation algorithms to detect a lane departure and issue a warning to the driver in real-time using an audible alarm. We have developed the app database structure and have completed programming the algorithms for the app. We are currently in the testing phase. The smartphone app is being prepared for both iOS and Android phones, however, the Android app will be available before the iOS app.
Download
Paper Nr: 30
Title:

SAFR-AV: Safety Analysis of Autonomous Vehicles Using Real World Data: An End-to-End Solution for Real World Data Driven Scenario-Based Testing for Pre-Certification of AV Stacks
Authors:

Sagar Pathrudkar, Saadhana B. Venkataraman, Deepika Kanade, Aswin Ajayan, Palash Gupta, Shehzaman S. Khatib, Vijaya S. Indla and Saikat Mukherjee
Abstract: One of the major impediments in deployment of Autonomous Driving Systems (ADS) is their safety and reliability. The primary reason for the complexity of testing ADS is that it operates in an open world characterized by its non-deterministic, high-dimensional and non-stationary nature where the actions of other actors in the environment are uncontrollable from the ADS’s perspective. This leads to a state space explosion problem and one way of mitigating this problem is by concretizing the scope for the system under test (SUT) by testing for a set of behavioral competencies which an ADS must demonstrate. A popular approach to testing ADS is scenario-based testing where the ADS is presented with driving scenarios from real world (and synthetically generated) data and expected to meet defined safety criteria while navigating through the scenario. We present SAFR-AV, an end-to-end ADS testing platform to enable scenario-based ADS testing. Our work addresses key real-world challenges of building an efficient large scale data ingestion pipeline and search capability to identify scenarios of interest from real world data, creating digital twins of the real-world scenarios to enable Software-in-the-Loop (SIL) testing in ADS simulators and, identifying key scenario parameter distributions to enable optimization of scenario coverage. These along with other modules of SAFR-AV would allow the platform to provide ADS pre-certifications.
Download
Paper Nr: 33
Title:

Naturalistic Driving Studies Data Analysis Based on a Convolutional Neural Network
Authors:

Jamal Raiyn and Galia Weidl
Abstract: The new generation of autonomous vehicles (AVs) are being designed to act autonomously and collect travel data based on various smart devices and sensors. The goal is to enable AVs to operate under their own power. Naturalistic driving studies (NDSs) collect data continuously from real traffic activities, in order not to miss any safety-critical event. In NDSs of AVs, however, the data they collect is influenced by various sources that degrade their forecasting accuracy. A convolutional neural network (CNN) is proposed to process a large amount of traffic data in different formats. A CNN can detect anomalies in traffic data that negatively affect traffic efficiency and identify the source of data anomalies, which can help reduce traffic congestion and vehicular queuing.
Download
Paper Nr: 35
Title:

Towards a Robust Traffic Scene Representation in Cooperative Connected Automated Mobility
Authors:

David Yagüe-Cuevas, Pablo Marín-Plaza, María Paz-Sesmero and Araceli Sanchis
Abstract: The relevance of methodologies able to exchange data between software modules in charge of controlling an autonomous vehicle have been increasing accordingly to the interests in the industry. The information managed by these systems needs to be represented in such a way the autonomous vehicle is able to produce safe behaviours as well as reliable control outputs when deployed in real-world environments. The efforts to define these data structures entail the first step in the path towards a fully autonomous platform. In this work, a representation of this nature is proposed, together with the flow of information of a layered modular software architecture which aims to operate an autonomous vehicle from low level actuators to high level behaviours.
Download
Paper Nr: 37
Title:

Night Fatigue Driving Detection Technology Using Infrared Images and Convolutional Neural Networks
Authors:

Huei-Yung Lin and Kai-Chun Tu
Abstract: Traffic accident is one of top ten causes of death, and fatigue driving is one of the major reasons. It usually reduces the driver’s concentration and reaction speed, and is especially dangerous in some situations at night. This works presents a real-time driving fatigue monitoring system. The proposed network architecture with Unbalanced Local CNNs can effectively draw attentions to different face regions according to driver’s states due to fatigue. Based on SlowFast, the recognition accuracy of our method on the IR image datasets is greatly improved compared to the original model. Moreover, an adversarial learning mechanism is incorporated to extract the common features of daytime RGB and nighttime IR images to increase the overall robustness. The experiments carried out on public datasets and road scene images have demonstrated the effectiveness of the proposed technique. The code is available at https://github.com/KaiChun-Tu/slowfastDrowsyDriver
Download
Paper Nr: 42
Title:

When Is an Automated Driving System Safe Enough for Deployment on the Public Road? Quantifying Safety Risk Using Real-World Scenarios
Authors:

Olaf Op den Camp, Erwin de Gelder and Jeroen Broos
Abstract: To ensure the safe and responsible deployment of vehicles equipped with Automated Driving Systems (ADSs) onto the public road, a safety assessment of such vehicles should be passed successfully. The assessment results should be unambiguous, easily understood by experts in the field, and explainable to authorities and the general public. An important metric in such a framework is the residual safety risk. The concept of risk is widely understood, and basing the safety assessment on that concept helps to come to a fair and acceptable assessment process. In this paper, we propose a method how to determine estimates for the residual safety risk, and how this safety risk estimate relates to the requirements posed by the UNECE that an activated ADS shall not cause any collisions that are reasonably foreseeable and preventable.
Download
Paper Nr: 50
Title:

Implementing Remote Driving in 5G Standalone Campus Networks
Authors:

Michael Klöppel-Gersdorf, Adrien Bellanger, Tobias Füldner, Dirk Stachorra, Thomas Otto and Gerhard Fettweis
Abstract: While there have been enormous advances in automated driving functions in the recent years, there are still circumstances where automated driving is not feasible or not even desired. Teleoperation is one approach to keep the vehicle mobile in such situations, with remote driving being one mode of teleoperation. In this paper we describe a 5G remote driving environment based on a 5G Standalone campus network, explaining technological and hardware choices. The paper is completed with experiences from practical trials, showing that remote driving using the proposed environment is feasible on a closed area. The achieved velocities are similar to that of a direct human driver.
Download
Paper Nr: 31
Title:

Framework and Algorithms for Data Analytics, Semantic Querying and Realistic Modelling of Traffic
Authors:

Sagar Pathrudkar, Guido Schroeer, Vijaya S. Indla and Saikat Mukherjee
Abstract: Infrastructure elements would be crucial in enabling autonomous mobility at scale to provide centrally shared insights and possibly planning and control. Infrastructure mounted multi-sensor perception systems observe traffic and generate data in object list format which typically consists of timestamped vehicle trajectories and metadata about the vehicles, ie, their type, dimensions, etc. Such data is huge in volume and its analysis is difficult due to the spatiotemporal sequential nature of the data. In this work, we present framework and algorithms to semantically model and analyze this data in the context of map geometry to gain statistics and insights at an actionable level of abstraction. We start with algorithms to process common 2D-HDmap formats to extract map features - roads, lanes, junctions, etc. We then present meaningful traffic KPIs and statistics that describe traffic patterns. We finally describe methods to abstract the traffic patterns and driving behaviors into parametrized functions for various applications.
Download
Paper Nr: 43
Title:

3D Mask-Based Shape Loss Function for LIDAR Data for Improved 3D Object Detection
Authors:

R. Park and C. Lee
Abstract: In this paper, we propose a 3D shape loss function for improved 3D object detection for LIDAR data. As the LiDAR (Light Detection And Ranging) sensor plays a key role in many autonomous driving techniques, 3D object detection using LiDAR data has become an important issue. Due to inaccurate height estimation, 3D object detection methods using LiDAR data produce false positive errors. We propose a new 3D shape loss function based on 3D masks for improved performance. To accurately estimate ground ROI areas, we first apply an adaptive ground ROI estimation method to accurately estimate ground ROIs and then use the shape loss function to reduce false positive errors. Experimental shows some promising results.
Download
Paper Nr: 53
Title:

Comparative Structural Analysis of Hydrodynamic Interaction of Full-Submerged Tandem Archimedes Screws of Rotary-Screw Propulsion Units of Snow and Swamp-Going Amphibious Vehicles with the Water Area in Running and Mooring Modes
Authors:

Svetlana Karaseva, Aleksey Papunin, Vladimir Belyakov, Vladimir Makarov, Dmitry Malahov and Anton Klyushkin
Abstract: The paper deals with the issues of analysis of thrust and torque of structural elements of rotary-screw propulsion units of snow and swamp-going amphibious vehicles of tandem design when operating on water. For a wide range of propulsors with three variants of the helix angle, the contribution of various elements of Archimedes screws to the overall efficiency of the propulsor is analyzed. A comparative analysis of the hydrodynamics of rotary-screw propulsion units in running and mooring modes is given.
Download
Paper Nr: 57
Title:

Deep Driving with Additional Guided Inputs for Crossings in Pedestrian Zones
Authors:

Qazi H. Jan, Jan A. Kleen and Karsten Berns
Abstract: Deep Neural Networks are being used in different applications to solve complex tasks with high precision. One application, also the focus of this paper, is end-to-end driving. Generally, in an end-to-end approach, a neural network learns to directly feed values to actuators based on sensor inputs. This paper uses an End-to-end approach with images and additional direction inputs:left, right and straight for imposing a certain direction at unstructured and arbitrary intersections of pedestrian zones. Expecting high precision for predicted steering in pedestrian zones could be uncertain due to the atypical structures of intersections. Findings for increased accuracy are done using direction inputs with three variants of two approaches: Single and parallel model. Depth information was included to overcome shadow problems from RGB in simulation, but it resulted in worsening the drive, and hence removed in further experiments. The experiments are performed in simulation to verify the utility of the proposed approaches and narrow down the best models for actual hardware. From the experiments, it is seen that parallel model with front images have performed best. The model drove well along the paths and followed the given input direction from the user at the crossings. To maintain the length of this paper, only results for parallel structures are discussed.
Download
Paper Nr: 60
Title:

Examination of the Relationship Between Smartphone Dependency and Driving Behaviour in Young Drivers: Preliminary Analysis
Authors:

Won S. Chen, James Boylan and Denny Meyer
Abstract: The smartphone has emerged as one of the important necessities in our daily lives. However, smartphone dependency can have negative as well as positive impacts on our overall well-being. Young adults are likely to demonstrate particularly problematic dependency on smartphone use. This is also the age group with a disproportionate contribution to road deaths in Australia (approximately 25% for 17-25 year olds), for reasons such as lack of experience and road awareness, resulting in bad choices or poor assessment of a road situation. The current study aimed to examine the relationship between smartphone dependency and driving behaviour in young people provided with the basic (control group) and extended (intervention group) features of an in-car telematics device. Participants aged between 18-30 were invited to complete the self-reported questionnaires, and an in-car telematics device with basic features was then activated over a 30-day period in their vehicles. At the start of the second 30-day period, half of the participants had their telematics installation extended. A linear mixed model analysis was conducted to allow for the hierarchical structure of the telematics data, with trips nested within drivers. The results suggest that in-car telematics devices can be adopted to improve the driving behaviour of young drivers.
Download

Area 4 - Data Analytics

Short Papers
Paper Nr: 8
Title:

Traffic Data Analysis from Social Media
Authors:

Aiden Bezzina and Luana Chetcuti Zammit
Abstract: Social networking sites serve a very important role in our daily lives, providing us with a platform where thoughts can be easily shared and expressed. As a result, these networking sites generate endless amount of information about extensive range of topics. Nowadays, through software development, analysing the content of social media is made possible through Application Program Interfaces (APIs). One particular application of content analysis of social networking sites is traffic. Traffic events can be determined from these sites. Thus, social networking sites have the potential to be utilised as a very cost-effective social sensor, whereby social media posts serve as the sensor information. Advancements in the field of machine learning have provided ways and techniques in which social media posts can be exploited/harvested to detect small-scale events, particularly traffic events in a timely manner. This work aims to develop a traffic-based information system that relies on analysing the content of social media data. Social media content is classified as either ‘traffic-related’ or ‘non-traffic-related’. ‘Traffic-related’ events are further classified into various ‘traffic-related’ sub-categories, such as: ‘accidents’, ‘incidents’, ‘traffic jams’, and ‘construction/road works’. The date, time, and the geographical information of each associated traffic event are also determined. To reach these aims, several algorithms are developed: i) An adaptive data acquisition algorithm is developed to make it possible to gather events from social media; ii) Several supervised binary classification algorithms are developed to analyse the content of social media and classify the results as either ‘traffic-related’ events or ‘non-traffic-related’ events; iii) A topic classification algorithm is developed to further analyse the ‘traffic-related’ events and classify them into the sub-categories previously mentioned; iv) A geoparser algorithm is further developed to obtain the date, time and the geographical information of the traffic event. A fully functional, real-time, automated system is developed by interconnecting all the algorithms together. This developed system produces very promising results when applied to Twitter data as a source of information. The results show that social networking sites have the potential to serve as a very efficient method to detect not only small-scale events, such as traffic events, but can also be scaled up to detect large-scale events.
Download
Paper Nr: 44
Title:

From Maps to Models: Computing Velocity Models for Turn Prediction Using OpenStreetMap Data
Authors:

Matthias Graichen and Lisa Graichen
Abstract: Analyzing and modeling behavioral data from driving studies can be challenging and often entails numerous steps of data handling, preparation, and aggregation before the final data modeling and extraction of results can be performed. In research papers, these steps are often described only briefly due to the natural limitation of words and intended focus on the related research questions. However, for smaller research groups or individual researchers without IT experts, the engineering of appropriate data processing pipelines for this type of research can be challenging. To address this issue, this work presents a step-by-step guide on how we tackled one of these challenges in our recent research activities. Our work focused on the implementation of a published algorithm for the prediction of turning maneuvers at intersections, which partly relies on map data for computing path curvature. We describe how we used freely available technologies and which steps were applied for building a data processing pipeline to enrich the recorded driving data with map data obtained via the OpenStreetMap platform and API.
Download

Area 5 - Smart Mobility and Sustainable Transport Services

Short Papers
Paper Nr: 22
Title:

Long-Distance Directional Dial-a-Ride Problems
Authors:

Grzegorz Gutowski and Grzegorz Herman
Abstract: We consider vehicle routing problems that occur in practice in the context of long-distance ride-sharing. On the one hand, the instances of our problems share the helpful property that the passengers travel in roughly the same geographical direction. On the other, the required cost function has ordering-dependent components. For two such problems, we provide heuristic algorithms employing a dynamic programming optimization of a sliding window in appropriate linear orders. In the first, exemplary problem, we route a single vehicle. In the second, we route a fleet of vehicles with a coordinated stopover and exchange of passengers. The size of the sliding window allows for trade-offs between solution qualities and processing times. Both algorithms are effective and efficient on data sets representing actual travel requests from Hoper, a commercial ride-sharing service operated by Teroplan S.A. in Poland.
Download
Paper Nr: 49
Title:

Optimization of Integral Type Cold Plate Heatsink for a 50W SoC in a High-Powered Liquid-Cooled ECU
Authors:

Himanshu Bindal, Joseph Oh, Kenneth Taylor and Hugh Skelton
Abstract: Automotive OEMs are moving towards consolidation of power within limited space. To put things into perspective a normal portable personal computer has a total power consumption of approximately 50W which is subjected to room temperature conditions. Contrary to this, just a single automotive SoC can have 50W of power which needs to be subjected to high ambient temperatures of up to 80° C within a sealed housing. This requires the next generation of ECU cooling solutions. In this study, liquid cooling will be showcased as a potential solution for automotive ECU cooling applications to meet such stringent requirements. A surrogate model has been developed using a reduced order thermal 50 W SoC. An additional 400 W is also applied on the top and bottom surface of the cold plate to account for the power dissipation of other components. The cold plate geometry was modified and analysed at different flow rates to evaluate pressure drop and SoC’s junction temperature by developing a zero-equation turbulent model. An optimized range of operation was also recommended. It was found that in an integral-type cold plate, variation in localized fin density area can be very effective in removing heat without causing a significant pressure drop.
Paper Nr: 38
Title:

Applying Activity-Based Models to Integrate Labeled Preset Key Events in Intra-Day Human Mobility Scenarios
Authors:

Patrik Gonçalves and Harald Baier
Abstract: The generation of synthetic human mobility scenarios is often realized through data-driven or rule-based approaches. They work in a fire-and-forget principle and provide limited support to induce controlled activities in simulated scenarios. However, including controlled preset activities in the generation phase enables the creation of mobility scenarios that include a-priori known outliers or key events. Such mobility test datasets might be used in outlier detection for machine learning algorithms or for inducing non-typical mobility, where models do not exist or are too complex to construct. In this work we propose an activity-based scheduler to include controlled preset key events in the scheduling process of daily human mobility scenarios. Further, with our rule-based approach we can synthesize new activities of a target region even when initial data is unavailable or missing. In addition we propose a hierarchical methodology to iteratively add activities according to their number of constraints and provide a publicly available Python-based implementation. Our validation shows that our approach is able to integrate non-typical behavior in typical mobility scenarios.
Download