VEHITS 2017 Abstracts


Area 1 - Connected Vehicles

Full Papers
Paper Nr: 11
Title:

IEEE 802.11 Systems in the Automotive Domain: Challenges and Solutions

Authors:

Alaa Mourad, Mohamad Omar Al Kalaa, Hazem Refai and Peter Adam Hoeher

Abstract: Customer demand for infotainment systems has garnered great attention from car manufacturers. System features have become a decisive factor when choosing among car models. As consumers become more dependent on their portable electronic devices (e.g., mobile phones, tablets), they expect to have seamless integration of their devices inside their cars. This allows them to use the same features supported by their phones in the cars. Car manufacturers aim to make their infotainment systems user-friendly. A key factor to achieve this goal is facilitating a wireless connection between mobile phones and car computers. IEEE 802.11 systems are the most popular candidate to provide high data rate connections utilizing the unlicensed industrial, scientific and medical (ISM) radio band. However, due to the limited available spectrum and the high density of devices inside the car, the achieved throughput could be strongly affected by interference and coexistence challenges. Furthermore, strong interference between the networks in different cars plays a crucial role in the automotive domain. This paper highlights the interference problem between IEEE 802.11 systems in cars. Two solutions in the 802.11n standard, namely transmission power control (TPC) and multiple input multiple output (MIMO) techniques, are discussed. Results show that both techniques could improve system performance. Transmission power control is essential to control radiation to surrounding environment.
Download

Short Papers
Paper Nr: 28
Title:

Distributed Transmit Power Control for Beacons in VANET

Authors:

Forough Goudarzi and Hamed S. Al-Raweshidy

Abstract: In vehicle to vehicle communication, every vehicle broadcasts its status information periodically in its beacons to create awareness for surrounding vehicles. However, when the wireless channel is congested due to beaconing activity, many beacons are lost due to packet collision. This paper presents a distributed congestion control algorithm to adapt beacons transmit power. The algorithm is based on game theory, for which the existence of the Nash Equilibrium (NE) is proven and the uniqueness of the NE and stability of the algorithm is verified using simulation. The proposed algorithm is then compared with other congestion control mechanisms using simulation. The results of the simulations indicate that the proposed algorithm performs better than the others in terms of fairness, bandwidth usage, and the ability to meet the application requirements.
Download

Paper Nr: 36
Title:

Cooperative Communication Network for Adaptive Truck Platooning

Authors:

Razvan Andrei Gheorghiu, Valentin Iordache and Angel Ciprian Cormos

Abstract: Truck platooning represents a solution to increase energy efficiency of the freight road transport. This method assumes very little distance between trucks so that overall aerodynamic quotient is improved. However, this requires a specific and dedicated infrastructure, due to the fact that the total length of the convoy may be considerable, which has a negative impact on the general traffic: other vehicles need a lot of space (and time) to overtake the platoon and this can only be done on highways with more than two lanes / direction. This means that in most cases (national roads and less wide highways) platoons cannot be formed and this method cannot be implemented. To resolve this situation, in this article we have proposed a solution for dynamic platoon formation, based on vehicle-to-vehicle communications, that will allow other vehicles to gradually overtake the vehicles forming the platoon. For this, a communication technology proposal has been made to ensure the identification of vehicles that are obstructed by the platoon. We have also made a series of laboratory measurements to test the validity of the proposed solution and, in the end, presented our conclusions.
Download

Paper Nr: 40
Title:

Acquisition of Relative Trajectories of Surrounding Vehicles using GPS and SRC based V2V Communication with Lane Level Resolution

Authors:

Zhiyuan Peng, Shah Hussain, M. I. Hayee and Max Donath

Abstract: Due to the anticipated benefits of connected vehicle technology, the Intelligent Transportation Systems Joint Program Office (ITSJPO) of the US Department of Transportation continues to emphasize the need for dedicated short range communication (DSRC) based vehicle-to-vehicle (V2V) and/or vehicle-to-infrastructure (V2I) communication to enhance driver safety and traffic mobility. To take full advantage of connected vehicle technology in most safety applications, precise vehicle positioning information is needed in addition to V2V communication. Many techniques, such as vision- or sensor-based systems and differential GPS receivers, can obtain the precise absolute position of a vehicle at the expense of cost and complexity. However, some critical safety applications such as merge-assist or lane-change-assist systems require only the relative positions of surrounding vehicles with lane-level resolution so that a given vehicle can differentiate the vehicles in its own lane from the vehicles in adjacent lanes. We have adopted a simple approach to acquire accurate relative trajectories of surrounding vehicles using standard GPS receivers and DSRC-based V2V communication. Using this approach, we have conducted field tests to successfully acquire relative trajectories of vehicles traveling in multiple lanes towards a merging junction with an accuracy less than half of the lane width. The achieved accuracy level of the relative trajectory was sufficient to differentiate vehicles traveling in adjacent lanes of a multiple-lane freeway.
Download

Paper Nr: 61
Title:

An Experimental Model for In-vehicle Networks and Subsystems

Authors:

Bogdan Groza, Horatiu Gurban and Pal-Stefan Murvay

Abstract: We pursue an experimental setup that gathers various in-vehicle networks and subsystems that are critical from a security perspective. As cyber-attacks to cars have become a reality, the model comes handy for both research and engineering education. The usefulness of this empirical model stems from both being helpful in creating a realistic view on the security of automotive systems and for creating security awareness. We do congregate in our setup various communication buses, e.g., CAN, LIN and FlexRay, and bring connectivity between several low and high-end automotive-grade development boards that are linked to off-the-shelf in-vehicle components, e.g., an instrument cluster and an infotainment unit, etc. The setup serves as a concise and practical representation of in-vehicle subsystems, network topologies and highlights security implications.
Download

Paper Nr: 71
Title:

An ADAS Design based on IoT V2X Communications to Improve Safety - Case Study and IoT Architecture Reference Model

Authors:

Yakusheva Nadezda, Gian Luca Foresti and Christian Micheloni

Abstract: Several technologies are used today to improve safety in transportation systems. The development of a system for drivability based on both V2V and V2I communication is considered an important task for the future. V2X communication will be a next step for the transportation safety in the nearest time. A lot of different structures, architectures and communication technologies for V2I based systems are under development. Recently a global paradigm shift known as the Internet-of-Things (IoT) appeared and its integration with V2I communication could increase the safety of future transportation systems. This paper brushes up on the state-of-the-art of systems based on V2X communications and proposes an approach for system architecture design of a safe intelligent driver assistant system using IoT communication. In particular, the paper presents the design process of the system architecture using IDEF modeling methodology and data flows investigations. The proposed approach shows the system design based on IoT architecture reference model.
Download

Paper Nr: 24
Title:

Designing Wireless Automotive Keys with Rights Sharing Capabilities on the MSP430 Microcontroller

Authors:

Bogdan Groza, Tudor Andreica and Pal-Stefan Murvay

Abstract: We explore the ultra-low-power microcontroller MSP430 from Texas Instruments as potential platform for developing vehicle keys. Radio frequency (RF) keys are still a relevant research subject as they are a common target for adversaries while automotive manufacturers show an increased interest in adding new functionalities to traditional keys while keeping them inexpensive. MSP430 is a low-cost, ultra-low-power, 16-bit capable microcontroller which can handle some cryptographic primitives that can be further used for designing secure authentication protocols. In this work we do explore the design and implementation options for a protocol that can be deployed in a car-sharing scenario where multiple users can share or gain access rights to the same vehicle. Due to inherent constraints of our platform, we keep the protocol simple and rely on inexpensive symmetric key primitives while still providing advanced options, e.g., rights sharing capabilities.
Download

Area 2 - Intelligent Transport Systems and Infrastructure

Full Papers
Paper Nr: 3
Title:

A Dynamic Cooperative Traffic Control (DCTC) for the Reduction of Time Delay

Authors:

Jinjian Li, Mahjoub Dridi and Abdellah El-Moudni

Abstract: This paper proposes a cooperative and dynamic traffic control method to reduce the time delay for all the vehicles in an isolated intersection based on the vehicle-to-infrastructure connection. The originality is shown by the following processes. Firstly, once the vehicle enters the communication zone, it sends its arrival time range to the intersection. Secondly, the control center applies Artificial Bee Colony to optimize the passing sequence with the dynamic group of the compatible trajectories under the related safety constraints. At last, each vehicle plans its speed profile to meet the optimal entrance time and speed in the intersection calculated from the passing sequence by the control center. A series of simulations are executed under the traffic volume from 100 to 500 (veh/h/l). The comparison of simulation results with other papers proves that the proposed method is very effective and all the vehicles can finish their entire trip with a near free-flow speed.

Paper Nr: 64
Title:

Sensor Fusion for Semantic Place Labeling

Authors:

Roman Roor, Jonas Hess, Matteo Saveriano, Michael Karg and Alexandra Kirsch

Abstract: In order to share knowledge about road situations vehicle-to-vehicle (V2V) communication is used. Autonomous driving vehicles are able to drive and park themself without driver interactions or presence, but are still inefficient about the drivers needs as they don’t anticipate the users’ behaviour. For instance, if a user wants to stop for quick grocery shopping, there is no need looking for long term parking in far distance, a short-term parking zone near the grocery shop would be adequate. To enable autonomous cars to make such decisions, they could benefit from awareness of their drivers’ context. Knowledge about a users’ activities and position may help to retrieve context information. To be able to describe the meaning of a visited place for user, we introduce a variant of semantic place labeling based on various sensor data. Data sourced by, e.g. smartphones or vehicles, is taken into account for gathering personalized context information, including Bluetooth, motion activity, status data and WLAN, and also to compensate for potential inaccuracies. For the classification of place types, over 80 features are generated for each stop. Thereby, geographic data is enriched with point of interest (POI)-information from different location-based context providers. In our experiments, we classify semantic categories of locations using parameter optimized multi-class and smart binary classifiers. An overall accuracy of 88.55% correctly classified stops is achieved using END classifier. A classification without GPS data yields an accuracy of 85.37%, demonstrating that alternative smartphone data can largely compensate for inaccurate localizations based on the fact of 88.55% accuracy, where GPS data was used. Knowing the semantics of a location, the provided context can be used to further personalize autonomous vehicles.
Download

Short Papers
Paper Nr: 6
Title:

Learning Classifier Systems for Road Traffic Congestion Detection

Authors:

Matthias Sommer and Jörg Hähner

Abstract: The increase in mobility leads to a higher number of kilometres driven per vehicle and more delay due to congestion which poses a recent and future problem. Congestion generates growing environmental pollution and more car accidents. We apply machine learning concepts to the task of congestion detection in road traffic. We focus on the extended classifier system XCSR, an evolutionary rule-based on-line learning classifier system. Experiments with real-world detector data demonstrate high accuracy of XCSR for congestion detection on interstates.
Download

Paper Nr: 32
Title:

Adapting Signal Timings to Automated Incident Alarms within a Self-organised Traffic Control System

Authors:

Matthias Sommer and Jörg Hähner

Abstract: Intersection management, routing, and congestion avoidance are key factors for improved mobility and better road network utilisation. Organic Traffic Control (OTC) is a self-organising traffic management system for urban road networks. Its main features are the self-adaptive traffic-responsive signalisation of intersections, the coordination of traffic light controllers, and dynamic route guidance of traffic streams. This paper aims at presenting how the automatic and fully distributed incident detection within OTC works and how OTC makes use of these incident alarms for the automated adaptation of signalisation.
Download

Paper Nr: 35
Title:

Implementation and Evaluation of an On-Demand Bus System

Authors:

Sevket Gökay, Andreas Heuvels, Robin Rogner and Karl-Heinz Krempels

Abstract: This work aims to develop and evaluate a dynamic bus system which abandons the concepts of a traditional bus service like bus line, bus station and timetable. The resulting system supports bringing customers from any location to any location, has a fleet of buses the routes of which are updated repeatedly as requests arrive and are accepted, and employs time windows in order to guarantee the desired pick-up and drop-off times of customers. We propose a technical realization and evaluate its effectiveness by running simulations in which traditional and dynamic systems are compared. Even though the operational cost and financial efficiency from a bus service provider’s perspective is not the focus of this evaluation, the preliminary results show that both the provider and the customers might benefit from an on-demand dynamic system. We also hint at the feasibility of such a system in not only low-demand rural areas, but also high-demand urban regions.
Download

Paper Nr: 41
Title:

Highway Reservation Strategy: Analytical Modeling Approach

Authors:

Peng Su, B. Brian Park and Sang H. Son

Abstract: Inspired by the success of reservation systems in airlines industries, and the Connected Vehicle technology supporting vehicular communications, this paper investigated a highway reservation and developed a mathematical optimization formulation to solve the optimal trip scheduling plan for a traffic network. The performance was quantified by total monetary cost of travel time and applicable early arrival time or late arrival time. In the two numerical case studies with an assumption of 100% compliance of the users to the reservation system’s scheduling, the system cost was 24.1% and 21.7% lower than those of the two corresponding user equilibrium solutions. The reservation system effectively redistributed the peak hour demand to the non-peak hours by limiting the reservation maximum flow rate of the reservation links.
Download

Paper Nr: 72
Title:

Design of Next Generation Smart Surface Transportation System

Authors:

Francis Chang and Hari K. Garg

Abstract: Transportation systems of the future need to be adaptive, adoptive, and responsive in order to meet the diverse challenges and ever-evolving demands. Conventional method of adding more resources on the road does not enhance its utility, rather it creates traffic congestion. Optimization of the usage of existing resources has been found to be one of the most effective solution to manage traffic congestion. The method we propose consists in increasing the occupancy rate of each vehicle and utilize other untapped resources in existing infrastructure. The resource optimization problem studied in this paper is NP hard, due to the vehicle routing and resource matching problem. In this paper, we are focused on developing a Multi-Objective Evolutionary Algorithm to optimize the use of taxi service not just as a carrier for people but also as a transport system for parcel delivery. Preliminary experiment with real-world data shows that our approach is able to quickly produce satisfactory solutions and the algorithm is able to provide an average of 17.7% improvement over conventional methods.
Download

Paper Nr: 19
Title:

Simultaneous Traffic Flow and Macro Model Estimation for Signalized Junctions with Multiple Input Lanes

Authors:

Luana Chetcuti Zammit, Simon G. Fabri and Kenneth Scerri

Abstract: A novel algorithm is presented for macro model estimation of the dynamics of traffic flow in a junction having multiple input lanes for each turning direction. The proposed algorithm jointly estimates the states describing the traffic flow under different traffic conditions, together with model parameters and their uncertainties of the measurement and process noise. Use is made of the Expectation-Maximization methodology with a sliding window over time in order to obtain quasi real-time estimation.
Download

Paper Nr: 47
Title:

The Impact of Over-bright Highway Billboards on Driving Behavior

Authors:

Lanfang Zhang, Junfeng Zhang, Yangzexi Liu and Jingqiu Guo

Abstract: There is an increase in highway billboards and the findings of how billboards impact on drivers’ visual attention have not been clear. According to a focus group study, one of the major concerns is excessive brightness of billboards, particularly at night. Participants were recruited to drive an instrumented vehicle during day and night conditions. A prototype of the evaluation framework was developed, which integrates eye adjustments, fixation and saccade, vehicle tactical maneuvering, as well as individual characteristics. The information of fixation point distribution, distraction, changes in pupil area, blinking frequency, and lane position change were collected. The analysis reveals the distracting nature of billboards and their tendency to cause visual discomfort. The results indicate that billboards with high luminance likely pose a safety risk. The need for continued research is also discussed.

Paper Nr: 48
Title:

Field Implementation of Eco-driving and Eco-signal System

Authors:

Byungjin Ko, Saerona Choi, Byungkyu Brian Park and Sang H. Son

Abstract: This paper proposed an integrated system between an eco-driving algorithm and an eco-signal control based on vehicle-to-everything (V2X) communication, and evaluated the system’s environmental benefits. The system calculates eco-speeds using vehicle information (e.g., current locations, vehicle speeds, and acceleration profiles) and signal information. In addition, the system controls current signal phase to improve fuel consumptions if a vehicle can pass the intersection by green time extension. We conducted field tests with three scenarios to evaluate the system using dedicated short-range communication (DSRC) devices and an external device that is able to collect vehicle specific information (e.g., speed and fuel consumption) within controller area network (CAN).
Download

Paper Nr: 55
Title:

Forecasting Public Transportation Capacity Utilisation Considering External Factors

Authors:

Fabian Ohler, Karl-Heinz Krempels and Sandra Möbus

Abstract: Using a forecast of the public transportation capacity utilisation, the buses can be adapted to the demand to avoid overfull buses leading to delays. An efficient utilisation of the buses at disposal can improve customer satisfaction as well as economic efficiency. The basis for our forecasts provide fragmentary measurements of passengers boarding and alighting buses at stops over the year 2015. In an attempt to improve the accuracy of the forecast, several external factors (e. g. weather, holidays, cultural events) were incorporated. We tackle the problem of forecasting public transportation capacity utilisation by forecasting the number of boarding and alighting passengers. Then we use these to adjust previous passenger count and the result as input for next forecast. Using multiple linear regression, support vector regression, and neural networks we evaluate different ways to model the external factors. Best results were achieved by neural networks with a median absolute error of ≈4.16 in the forecast passenger count. They were able to keep more than 80% of the forecasts within a tolerance of 10 passengers. Since the error in the forecasts does not accumulate along the trips, chaining the forecasts in the described way is a viable approach.
Download

Area 3 - Intelligent Vehicle Technologies

Full Papers
Paper Nr: 1
Title:

Scenario Interpretation based on Primary Situations for Automatic Turning at Urban Intersections

Authors:

David Perdomo Lopez, Rene Waldmann, Christian Joerdens and Raúl Rojas

Abstract: Even for a human driver, urban intersections represent probably the most difficult scenarios, in which the driver could be overloaded by understanding the traffic rules, predicting the intention of other objects, etc. The complexity of these scenarios makes the task of automated driving at intersections a very difficult challenge. Thus, we propose an approach that aims to reduce the complexity of the scenario interpretation by breaking down the problem into a set of primary situations linked over time. Based on the combination of four primary situations, the scenario interpretation should enable the corresponding planning that guides the ego vehicle along a driving corridor.
Download

Paper Nr: 7
Title:

Shallow Networks for High-accuracy Road Object-detection

Authors:

Khalid Ashraf, Bichen Wu, Forrest N. Iandola, Matthew W. Moskewicz and Kurt Keutzer

Abstract: The ability to automatically detect other vehicles on the road is vital to the safety of partially-autonomous and fully-autonomous vehicles. Most of the high-accuracy techniques for this task are based on R-CNN or one of its faster variants. In the research community, much emphasis has been applied to using 3D vision or complex R-CNN variants to achieve higher accuracy. However, are there more straightforward modifications that could deliver higher accuracy? Yes. We show that increasing input image resolution (i.e. upsampling) offers up to 12 percentage-points higher accuracy compared to an off-the-shelf baseline. We also find situations where earlier/shallower layers of CNN provide higher accuracy than later/deeper layers. We further show that shallow models and upsampled images yield competitive accuracy. Our findings contrast with the current trend towards deeper and larger models to achieve high accuracy in domain specific detection tasks.
Download

Paper Nr: 20
Title:

Road Estimation and Fuel Optimal Control of an Off-Road Vehicle

Authors:

Jörgen Albrektsson and Jan Åslund

Abstract: This paper explores the possibility to use optimal control to establish a Pareto front of fuel consumption vs cycle time for a transport mission with an articulated hauler. The Pareto front can be utilised to optimise the hauler transport mission on its own or as a part in a larger optimal control problem involving several construction machines working together on a site transporting material at a set production rate. While rolling resistance is a major energy consumer in an articulated hauler’s transport, the effect of varying rolling resistance is included in the developed optimisation algorithm. A method utilising Extended Kalman Filter, Rauch-Tung-Striebel smoothing and sensor fusion is formulated in order to calculate the road related data needed in the optimisation algorithm. A potential fuel efficiency improvement, verified by computer simulations, of up to 9% was found in the example transport mission where the optimal gear and speed trajectory were followed instead of driving towards a mean speed target to achieve an equal cycle time for the transport mission.
Download

Paper Nr: 23
Title:

Dynamic Map Update Protocol for Highly Automated Driving Vehicles

Authors:

Florian Jomrich, Aakash Sharma, Tobias Rückelt, Daniel Burgstahler and Doreen Böhnstedt

Abstract: Highly automated driving vehicles are currently subject of strong research efforts to enable novel mobility experiences. To achieve this goal a high definition street map is required. It provides the vehicles with centimetre accurate references to all geographic objects in its surrounding. So this street map enables driving capabilities of the automated vehicle in terms of safety and comfort for the passengers that could not be obtained while only relying on the cars own inbuilt sensor equipment. This high definition street map has to ensure the accuracy and timeliness of its data, necessary for the task of highly automated driving, at any time. Therefore those maps have to be constantly provided with updates from a remote server. This paper describes a protocol based mainly on preselection of contextual relevant map data to provide a car in an efficient way with such a continuous stream of updates. The capabilities of the protocol have been evaluated on a map database of Berlin. The obtained results verify that it achieves a significant decrease in transmission data and processing time, compared to existing map update approaches.
Download

Paper Nr: 30
Title:

Short-Term Traffic Prediction under Both Typical and Atypical Traffic Conditions using a Pattern Transition Model

Authors:

Traianos-Ioannis Theodorou, Athanasios Salamanis, Dionysios D. Kehagias, Dimitrios Tzovaras and Christos Tjortjis

Abstract: One of the most challenging goals of the modern Intelligent Transportation Systems comprises the accurate and real-time short-term traffic prediction. The achievement of this goal becomes even more critical when the presence of atypical traffic conditions is concerned. In this paper, we propose a novel hybrid technique for short-term traffic prediction under both typical and atypical conditions. An Automatic Incident Detection (AID) algorithm, based on Support Vector Machines (SVM), is utilized to check for the presence of an atypical event (e.g. traffic accident). If such an event occurs, the k-Nearest Neighbors (k-NN) non-parametric regression model is used for traffic prediction. Otherwise, the Autoregressive Integrated Moving Average (ARIMA) parametric model is activated for the same purpose. In order to evaluate the performance of the proposed model, we use open real world traffic data from Caltrans Performance Measurement System (PeMS). We compare the proposed model with the unitary k-NN and ARIMA models, which represent the most commonly used non-parametric and parametric traffic prediction models. Preliminary results show that the proposed model achieves larger accuracy under both typical and atypical traffic conditions.
Download

Paper Nr: 44
Title:

A Taxonomy and Systematic Approach for Automotive System Architectures - From Functional Chains to Functional Networks

Authors:

Johannes Bach, Stefan Otten and Eric Sax

Abstract: Technological advances enable realization of increasingly complex customer features in the automotive sector. Traffic jam pilot or predictive energy management depict examples of recently introduced features that span across different conventional vehicle domains. The increased interconnectivity and functional complexity impose new requirements on the automotive systems engineering practice. The resulting challenge is to develop integrated approaches that combine the established procedures with innovative techniques. To address this challenge, we present a comprehensive taxonomy for existing automotive features. Based on this characterization, established industrial and new research approaches for logical system architectures are consolidated. We introduce levels of hierarchy in the logical system architecture to facilitate systems engineering of innovative functions and highly distributed features. The systematic approach provides a novel rationale for the evolution from functional chains to functional networks in the automotive industry.
Download

Paper Nr: 46
Title:

On the Performance of a One-way Car Sharing System in Suburban Areas: A Real-world Use Case

Authors:

Haitam M. Laarabi, Chiara Boldrini, Raffaele Bruno, Helen Porter and Peter Davidson

Abstract: In recent years, one-way car sharing systems have gained momentum across the world with their promise to encourage more sustainable urban mobility models. However, economic viability of car sharing is still uncertain due to high investment cost for station and fleet deployment, as well as high operation cost for fleet management and rebalancing. Furthermore, existing car sharing are typically confined to city centres with significant business and residential concentrations. In this study, we evaluate the performance of a novel one-way car sharing system that will be deployed in a suburban area of the city of Lyon using a detailed multi-agent and multi-modal transport simulation model. Data from a recent large-scale household travel survey is used to determine the travel demands on different transportation alternatives. We analyse the impact of different coverage constraints on the system capacity in terms of number of trips and vehicle availability. We also investigate the potential of user-based relocation strategies to increase the efficiency of the car sharing service. The model shows that: (i) the car sharing system is most sensitive to the infrastructure and fleet sizes, and (ii) user-based relocation does not have a significant impact on the total number of car sharing trips.
Download

Paper Nr: 49
Title:

An Interaction Framework for a Cooperation between Fully Automated Vehicles and External Users in Semi-stationary Urban Scenarios

Authors:

Mohsen Sefati, Denny Gert, Kai Kreisköther and Achim Kampker

Abstract: Automated vehicles are becoming gradually available in restricted environments and are planned to be available for more challenging situations in the near future. Fully automated vehicles (FAVs) will have no drivers and still need to cooperate and interact with other road users outside the vehicle. In this work we propose an interaction framework, which makes it possible for external users to interfere with the FAV guidance in an abstract level via communicating a desired maneuver. The external user can be assumed as a road participant, who shares drivable areas with the FAV, or an operating person such as delivery person, who wants to guide a delivery vehicle remotely. The application area of this framework is the low velocity range, which can be also assumed as semi-stationary environments. The proposed framework explores the percepted static environment and identifies all possible paths with respect to vehicle dynamics, safety and comfort parameters. These paths are processed in order to build a set of meaningful candidates for the further steps. For this goal we have proposed two different methods based on a modified RRT algorithm and a skeletonization of the freespace. In order to extract possible drivable maneuvers out of the current scene, the candidate paths are assigned to predefined maneuver classes and selected with respect to their length and reasonableness. The set of meaningful and drivable maneuvers will be communicated to the user in form of an abstract and simplified catalogue. With this framework we provide both the FAV and the external user with a mutual understanding about the scene and avoid the possible ambiguity in goal understanding. The proposed framework is validated with sensor data from real scenarios.
Download

Short Papers
Paper Nr: 31
Title:

Automatic Driver Sleepiness Detection using Wrapper-Based Acoustic Between-Groups, Within-Groups, and Individual Feature Selection

Authors:

Dara Pir, Theodore Brown and Jarek Krajewski

Abstract: This paper presents performance results, time complexities, and feature reduction aspects of three wrapper-based acoustic feature selection methods used for automatic sleepiness detection: Between-Groups Feature Selection (BGFS), Within-Groups Feature Selection (WGFS), and Individual Feature Selection (IFS) methods. Furthermore, two different methods are introduced for evaluating system performances. Our systems employ Interspeech 2011 Sleepiness Sub-Challenge’s “Sleepy Language Corpus” (SLC). The two tasks of the wrapper-based method, the feature subset evaluation and the feature space search, are performed by the Support Vector Machine classifier and a fast variant of the Best Incremental Ranked Subset algorithm, respectively. BGFS considers the feature space in Low Level Descriptor (LLD) groups, an acoustically meaningful division, allowing for significant reduction in time complexity of the computationally costly wrapper search cycles. WGFS considers the feature space within each LLD and generates the feature subset comprised of the best performing individual features among all LLDs. IFS regards the feature space individually. The best classification performance is obtained by BGFS which also achieves improvement over the Sub-Challenge baseline on the SLC test data.
Download

Paper Nr: 39
Title:

Autonomous Aerial Vehicle - Based on Non-Monotonic Logic

Authors:

José Luis Vilchis Medina, Pierre Siegel and Andrei Doncescu

Abstract: In this article we study the case of an autonomous motor-glider. The aims of the aircraft is to maintain its flight as long as possible, taking advantage of the rising air from the ground, known as thermals, despite of limited energy resources and possible external influences, such as turbulences. The pilot task being to make decisions with incomplete, uncertain or even contradictory information, as well as driving to the desired path or destination. We propose the formulation of a model from the point of view of logical theory, using non-monotonic logic and more specifically default logic, to tackle these problems. Finally, we present the results of a simulation for further application in a glider(reduced model) which use solar cells for power management in embedded system.
Download

Paper Nr: 43
Title:

Empirical Evaluation of Convolutional Neural Networks Prediction Time in Classifying German Traffic Signs

Authors:

Joshua Fulco, Akanksha Devkar, Aravind Krishnan, Gregory Slavin and Carlos Morato

Abstract: This paper discusses the use of Deep Learning and neural networks to identify images which contain road signs to aid in the navigation of autonomous vehicles. Images of 32x32 pixels and 128x128 pixels of the GTSRB dataset were used in training the existing neural network models as well as our novel models. Existing neural network models mentioned in the literature study validate that very high accuracies in image classification are already achieved. Different neural network model architectures were also reviewed to determine which architecture produced the highest accuracy within the most efficient time. Modifications to these architectures were made to produce valid results with a reduced image identification time. Our results of classifying a traffic sign image of 32x32 pixels in 0.6ms is very reliable for real time output. By looking at the image identification times for a 32x32 pixel image and a 128x128 pixel image we observed that size of the image is not the main factor in the increase of the prediction time.
Download

Paper Nr: 45
Title:

Braking Strategy for an Autonomous Vehicle in a Mixed Traffic Scenario

Authors:

Raj Haresh Patel, Jérôme Härri and Christian Bonnet

Abstract: During the early deployment phase of autonomous vehicles, autonomous vehicles will share roads with conventional manually driven vehicles. They will be required to adjust their driving dynamically taking into account not only preceding but also following conventional manually driven vehicles. This paper addresses the challenges of adaptive braking to avoid front-end and rear-end collisions, where an autonomous vehicle is followed by a conventional manually driven vehicle. We illustrate via simulations the consequences of independent braking in terms of collisions, on both autonomous and conventional vehicles, and propose an adaptive braking strategy for autonomous vehicles to coordinate with conventional manually driven vehicles to avoid front and rear-end collisions.
Download

Paper Nr: 53
Title:

Development of a Vibration Measurement Device based on a MEMS Accelerometer

Authors:

Chinedum Anthony Onuorah, Sara Chaychian, Yichuang Sun and Johann Siau

Abstract: This paper proposes a portable and low cost vibration detection device. Enhanced vibration calculation, reduction of error and low storage memory are complementary accomplishments of this research. The device consists of a MEMS capacitive accelerometer sensor and microcontroller unit, which operates based on a novel algorithm designed to obtained vibration velocity, bypassing the usual time-based integration process. The proposed algorithm can detect vibrations within 15Hz - 1000Hz frequencies. Vibration in this frequency range cannot be easily and accurately evaluated with conventional low cost digital sensors. The proposed technique is assessed and validated by comparing results with an industrial grade vibration meter.
Download

Paper Nr: 56
Title:

Integration of Private and Carsharing Vehicles into Intermodal Travel Information Systems

Authors:

Christian Samsel, Markus Christian Beutel, David Thulke, Detlef Kuck and Karl-Heinz Krempels

Abstract: In the last years, intermodal mobility platforms offering combinations of various modal types, like trains, buses, carsharing and ride sharing, have emerged. These platforms often also offer a smartphone-based door-to-door navigation and a sophisticated travel assistance. Unfortunately, these smartphone-based services cannot be used by the travelers as soon as they are driving a car themselves, e.g., a carsharing vehicle or their private car, due to road safety regulations. The driver is essentially disconnected from the service. In addition, modern cars have a lot of configuration options a driver might want to set up. This discourages using shared vehicles in an intermodal itinerary. In this work we identify use cases of how an integration of carsharing vehicles into intermodal travel information systems can enhance travel experience, introduce a system architecture to allow the necessary information exchange and present a preliminary prototype to demonstrate its technical feasibility.
Download

Paper Nr: 60
Title:

The ADAS SWOT Analysis - A Strategy for Reducing Costs and Increasing Quality in ADAS Testing

Authors:

Andreas Haja, Carsten Koch and Lars Klitzke

Abstract: In a remarkably short time, advanced driver assistance systems (ADAS) have become a major driver of innovation in the auto industry: It is expected that autonomous vehicles will profoundly change the very definition of mobility. In addition to mastering technical challenges, increasing automation requires a significant amount of testing and thus a huge investment in test resources. This poses a serious cost factor for existing companies and a high entry barrier for new market entrants. In addition, strong demand for engineers worldwide also makes it difficult to allocate sufficient manpower. Consequently, tests are often performed by teams with limited experience and high staff turnover. To reduce test duration while ensuring high levels of quality and a focus on the most relevant aspects, this paper presents a new method for creating efficient test strategies which builds on the well-known SWOT analysis and extends its use to ADAS-related scenarios. The ADAS SWOT analysis provides a structured process which facilitates the identification of risks and opportunities associated with new technology and assesses its impact on ADAS products from a customer perspective. The method has been tailored to fit the needs of research and advance development and helps increase both product quality and time-to-market.
Download

Paper Nr: 73
Title:

Adaptation to the Unforeseen: Can We Trust Autonomous and Adaptive Systems? - (Position Paper)

Authors:

Emil Vassev and Mike Hinchey

Abstract: Autonomous and adaptive systems perform tasks without human intervention and are among the most challenging topics in technology today. Autonomous cars have already appeared on our streets and unfortunately due to some severe accidents they appear to be not as secure as we had hoped them to be. This paper tackles the question of how far we can push the boundary towards achieving such behavior and still provide autonomic operations at least in a certain context with highest safety guarantees to establish trust in autonomous systems.
Download

Paper Nr: 74
Title:

Functionalities and Requirements of an Autonomous Shopping Vehicle for People with Reduced Mobility

Authors:

António Neves, Daniel Campos, Fabio Duarte, Inês Domingues, Joana Santos, João Leão, José Xavier, Luís Matos, Manuel Camarneiro, Marcelo Penas, Maria Miranda, Ricardo Silva and Tiago Esteves

Abstract: This paper concerns a robot to assist people in retail shopping scenarios, called the wGO. The robot’s behaviour is based in a vision-guided approach based on user-following. The wGO brings numerous advantages and a higher level of comfort, since the user does not need to worry about controlling the shopping cart. In addition, this paper introduces the wGOs functionalities and requirements to enable the robot to successfully perform personal assistance while the user is shopping in a safe way. A user satisfaction survey is also presented. Based on the highly encouraging results, some conclusions and guidelines towards the future full deployment of the wGO in commercial environments are drawn.
Download

Paper Nr: 21
Title:

Intelligent Agents for Supporting Driving Tasks: An Ontology-based Alarms System

Authors:

V. Zamora, O. Sipele, A. Ledezma and A. Sanchis

Abstract: This paper presents a rule-based alarm system as part of an ADAS. This work is developed by using a multi-agent framework, and it focuses on the driving safety, in particular, in urban environments. The main point of the proposed system is that it takes decisions based on the fusion of the information from the driver, the vehicle status and the state of the road ahead, and it is designed to alert the driver of the car (without taking control of it) only when the system considers that it is necessary. Five dangerous scenarios are defined, analysed and studied, and a repository of rules is designed to help the driver in that situations. In order to represent the concepts and its relation about the urban traffic environment, the system uses an OWL Ontology based on a previous research and extended in this work.
Download

Paper Nr: 33
Title:

Integration of Vehicle Detection and Distance Estimation using Stereo Vision for Real-Time AEB System

Authors:

Byeonghak Lim, Taekang Woo and Hakil Kim

Abstract: We propose an integrated system for vehicle detection and distance estimation for real-time autonomous emergency braking (AEB) systems using stereo vision. The two main modules, object detection and distance estimation, share a disparity extraction algorithm in order to satisfy real-time processing requirements. The object detection module consists of an object candidate region generator and a classifier. The object candidate region generator uses stixels extracted from image disparity. A surface normal vector is computed for validation of the candidate regions, which reduces false alarms in the object detection results. In order to classify the proposed stixel regions into foreground and background regions, we use a convolutional neural network (CNN)-based classifier. The distance to an object is estimated from the relationship between the image disparity and camera parameters. After distance estimation, a height constraint is applied with respect to the distance using geometric information. The detection accuracy and distance error rate of the proposed method are evaluated using the KITTI datasets, and the results demonstrate promising performance.
Download

Paper Nr: 69
Title:

Application of the Situational Management Methods to Ensure Safety in Intelligent Transport Systems

Authors:

Irina Makarova, Anton Pashkevich, Eduard Mukhametdinov and Vadim Mavrin

Abstract: The article shows directions of intellectualization of vehicles, analyzed issues and ways to improve safety, reliability and sustainability of transport systems. Methods of situational management are shown. They are based on intelligent technologies for improving safety of complex technical systems. Development and application of precedent expert systems is actual for systems with incomplete information and high complexity of object of management. Such systems reflect decisions by analogy, i.e. according to reports of critical situations, which are potentially dangerous for this object. The object-oriented case model describing the dynamics of dangerous conditions object is developed. Measures on prevention, localization and mitigation of dangerous conditions (such as identification of the dangerous conditions, identify their causes, the safety evaluation, forecasting of development scenarios) are envisaged.

Paper Nr: 70
Title:

Self-learning Trajectory Prediction with Recurrent Neural Networks at Intelligent Intersections

Authors:

Julian Bock, Till Beemelmanns, Markus Klösges and Jens Kotte

Abstract: We present the concept and first results of a self-learning system for road user trajectory prediction at intersections with connected sensors. Infrastructure installed connected sensors can assist automated vehicles in perceiving the environment in complex urban scenes such as intersections. An intelligent intersection with connected sensors can measure the trajectories of road users using multiple sensor types and store the trajectories. Our approach uses this information to collect a large dataset of pedestrian trajectories. This dataset is again used to train a pedestrian prediction model with Recurrent Neural Networks. This model learns intersection specific pedestrian movement patterns. Through a self-learning process enabled by the measurements of connected sensors, the system continuously improves the prediction during operation while keeping the dataset preferably small. In this paper, we focus on the prediction of pedestrian trajectories, but as the approach is data-driven, the system could also predict other road users such as vehicles or bicyclists if trained with the respective data.
Download

Area 4 - Sustainable Transport

Full Papers
Paper Nr: 12
Title:

Validation and Control Strategy to Reduce Fuel Consumption for RE-EV

Authors:

Wonbin Lee, Wonseok Choi, Hyunjong Ha, Jiho Yoo, Junbeom Wi, Jaewon Jung and Hyunsoo Kim

Abstract: In this study, a control strategy of the target RE-EV was analysed using BMW i3 test data from Downloadable Dynamometer Database (D3) at Argonne National Laboratory. In addition, vehicle model was developed based on AVL Cruise and MATLAB/Simulink and validation of the developed model was carried out. Using the simulation and test data, a control strategy which operates the engine on the optimal operation line was proposed to reduce the fuel consumption. The performance of the engine control strategy was evaluated for the city and highway driving cycle.
Download

Short Papers
Paper Nr: 2
Title:

An Agent Trading on Behalf of V2G Drivers in a Day-ahead Price Market

Authors:

Ibrahem A. Almansour, Enrico H. Gerding and Gary Wills

Abstract: Due to the limited availability of fuel resources, there is an urgent need for converting to use renewable sources efficiently. To achieve this, power consumers should participate actively in power production and consumption. Consumers nowadays can produce power and consume a portion of it locally, and then could offer the rest of the power to the grid. Vehicle-to-grid (V2G) which is one of the most effective sustainable solutions, could provide these opportunities. V2G can be defined as a situation where electric vehicles (EVs) offer electric power to the grid when parked. We developed an agent to trade on behalf of V2G users to maximize their profits in a day-ahead price market. We then ran the proposed model in three different scenarios using an optimal algorithm and compared the results of our solution to a benchmark. We show that our solution outperforms the benchmark strategy in the proposed three scenarios 49%, 51%, and 10% respectively in terms of profit.
Download

Paper Nr: 15
Title:

Optimal Control of Plug-in Hybrid Electric Vehicle based on Pontryagin’s Minimum Principle Considering Driver’s Characteristic

Authors:

Kyusik Park, Hanho Son, Kyunggook Bae, Yoonuk Kim, Hyunhwa Kim, Jeongseok Yun and Hyunsoo Kim

Abstract: In this study, an optimal control was investigated for a power split type plug-in hybrid electric vehicle (PHEV) considering the driver’s characteristic. Using the dynamic model of the PHEV powertrain, Hamiltonian was defined and the optimal co-state was obtained for Pontryagin’s minimum principle (PMP) control. The PMP control was performed for a normal driver who was selected based on extended driving style questionnaire (EDSQ), and the battery SOC behaviour and equivalent fuel economy were evaluated. It was found that the equivalent fuel economy by the PMP control is improved compared with the existing charge depleting/charge sustaining (CD/CS) control and the battery SOC decreased faster as the sportiness of the driver increased.
Download

Paper Nr: 29
Title:

Derivation of Real Driving Emission Cycles based on Real-world Driving Data - Using Markov Models and Threshold Accepting

Authors:

Roman Liessner, Robert Fechert and Bernard Bäker

Abstract: The European Union has decided to bring the Real Driving Emissions (RDE) law into force in 2016. From this point onward, the air pollutants a vehicle emits under real driving conditions will be measured by means of a so-called Portable Emissions Measurement System (PEMS) and then used as the basis for licensing. Compared to the emission values presently determined in the New European Driving Cycle (NEDC), a significant rise can be expected. This change is on the one hand caused by a substantially more dynamic driving style prescribed by RDE regulations, and on the other hand by considerably larger variations of ambient conditions. A trend of development resulting from this conversion is the creation of test cycles conforming to RDE regulations, which enable vehicle development to adhere to the new licensing regulations. The validity of a RDE drive is gradually verified based on multiple criteria before respective emission values are determined at the end of the process. The contribution at hand presents a new approach for generating RDE substitute cycles. At first, the criterion of driving dynamics will be focussed upon. To realize this, combinatorics of a large set of real driving data will be used to generate substitute cycles, which will exhibit driving dynamics as high as possible. This specification achieves universal, vehicle independent limitation cycles featuring high emission levels. By using the described limitation cycles, a first vehicle examination concerning the fulfilment of RDE regulations is made possible.
Download

Paper Nr: 68
Title:

Global Energy Management for Propulsion, Thermal Management System of A Series-parallel Hybrid Electric Vehicle

Authors:

Xiaoxia Sun, Chunming Shao, Guozhu Wang, Rongpeng Li, Danhua Niu and Jun Shi

Abstract: Energy management in vehicles is a relevant issue, especially in the case of hybrid electric vehicle. In this paper, a global energy management for propulsion, thermal management system of a series-parallel hybrid electric vehicle is studied. An adaptive controllable thermal management system suitable for series-parallel hybrid electric vehicle is presented. According to the vehicle structure and schematic, a multi-disciplined coupled model of a series-parallel hybrid electric vehicle combined with propulsion system model and thermal management system model is proposed. The coupled model is explored with the hybrid modeling method which combines experiment modeling and theory modeling. According to the coupled model, the energy flow, distribution and heat characteristics of components are studied. Then the vehicle driving cycle simulation is explored to evaluate the validity of the relative models. Results show that the coupled simulation model can be used to analysis the mechanical, electrical and thermal interactions between the internal combustion engine, gearboxes, electrical machines, power electronics, controlling system and so on. It also can predict the dynamic response of the series-parallel hybrid electric vehicle heat source components.
Download