Showing papers in "IEEE Intelligent Transportation Systems Magazine in 2014"

Making Bertha Drive?An Autonomous Journey on a Historic Route

Abstract: 125 years after Bertha Benz completed the first overland journey in automotive history, the Mercedes Benz S-Class S 500 INTELLIGENT DRIVE followed the same route from Mannheim to Pforzheim, Germany, in fully autonomous manner. The autonomous vehicle was equipped with close-to-production sensor hardware and relied solely on vision and radar sensors in combination with accurate digital maps to obtain a comprehensive understanding of complex traffic situations. The historic Bertha Benz Memorial Route is particularly challenging for autonomous driving. The course taken by the autonomous vehicle had a length of 103 km and covered rural roads, 23 small villages and major cities (e.g. downtown Mannheim and Heidelberg). The route posed a large variety of difficult traffic scenarios including intersections with and without traffic lights, roundabouts, and narrow passages with oncoming traffic. This paper gives an overview of the autonomous vehicle and presents details on vision and radar-based perception, digital road maps and video-based self-localization, as well as motion planning in complex urban scenarios.

Insurance Telematics: Opportunities and Challenges with the Smartphone Solution

Abstract: Smartphone-based insurance telematics or usage based insurance is a disruptive technology which relies on insurance premiums that reflect the risk profile of the driver; measured via smartphones with appropriate installed software. A survey of smartphone-based insurance telematics is presented, including definitions; Figure-of-Merits (FoMs), describing the behavior of the driver and the characteristics of the trip; and risk profiling of the driver based on different sets of FoMs. The data quality provided by the smartphone is characterized in terms of Accuracy, Integrity, Availability, and Continuity of Service. The quality of the smartphone data is further compared with the quality of data from traditional in-car mounted devices for insurance telematics, revealing the obstacles that have to be combated for a successful smartphone-based installation, which are the poor integrity and low availability. Simply speaking, the reliability is lacking considering the smartphone measurements. Integrity enhancement of smartphone data is illustrated by both second-by-second lowlevel signal processing to combat outliers and perform integrity monitoring, and by trip-based map-matching for robustification of the recorded trip data. A plurality of FoMs are described, analyzed and categorized, including events and properties like harsh braking, speeding, and location. The categorization of the FoMs in terms of Observability, Stationarity, Driver influence, and Actuarial relevance are tools for robust risk profiling of the driver and the trip. Proper driver feedback is briefly discussed, and rule-of-thumbs for feedback design are included. The work is supported by experimental validation, statistical analysis, and experiences from a recent insurance telematics pilot run in Sweden.

Efficient Allocation of Electric Vehicles Charging Stations: Optimization Model and Application to a Dense Urban Network

Abstract: The deployment of Electric Vehicles (EVs) needs an optimized and cost-effective implementation of charging stations. As a decision support tool for network design, we define a methodology to allocate charging stations in a real network. This study uses trip OD matrix information from household travel survey coupled with a dynamic vehicle model to evaluate EVs consumption based on realistic trips (urban drive cycles). These trips are computed based on routing tools and supplied with elevation information. This enables an accurate characterization of energy needs in the Lyon Metropolitan Area. All these parameters are used as inputs of an integer linear optimization program for the location of charging stations. The methodology is based on an adaption of the classic fixed charge location model with a p-dispersion constraint. The results indicate that this methodology can help the future implementation of charging stations at an urban scale.

Energy Optimal Real-Time Navigation System

Abstract: The rapid development of Mobile Internet and Smart Devices and advent of a new generation of Intelligent Transportation Systems (ITS) increase information about present driving conditions and make its prediction possible. Real time traffic information systems (TIS) like SYTADIN help in route to destination planning and traffic state prediction. Energy-optimal routing for electric vehicles creates novel algorithmic challenges where the computation complexity and the quality of information on traffic state are the main issues. This complexity is induced by the possible negative values of edge energy as well as the variability of route and vehicle variables which render the standard algorithms unsuitable. In this paper the authors present an Energy Optimal Real Time Navigation System (EORTNS), implemented on Samsung Galaxy Tab, capable of calculating the route to destination based on information flow obtained from SYTADIN. As an application example the authors propose a real time energy management for a Hybrid Electrical Vehicle (HEV) composed of batteries and Super-Capacitors (SC). The EORTNS is not only capable of energy optimal route to destination calculation with respect to traffic state but also operates the On-Board power splitting between batteries and Super-Capacitors.

License Plate Recognition: A Brief Tutorial

Abstract: In this paper we present a brief tutorial on the well-studied, but not fully solved, problem of LPR(license plate recognition). The main goal is to provide the young researcher with sufficient information about this topic and possible solutions giving emphasis on image processing techniques.

Agile Urban Parking Recommendation Service for Intelligent Vehicular Guiding System

Abstract: Nowadays, Intelligent Transportation Systems (ITS) technologies are exploring a wide range of services such as freeway management, crash prevention & safety, driver assistance, and infotainment of drivers and/or passengers. In this paper, an agile urban parking recommendation service for vehicular intelligent guiding system is designed to facilitate city citizens with fully efficient, real-time and precise parking lot guiding suggestions for the sustainability of the future green city. The system offers drivers a friendly parking lot recommendation sequence and saves driver's time circling around by the accurate prediction of the successful parking probability in each parking lot. The proposed cost model constructs an optimal recommendation sequence considering successful parking probability and time to reach the parking lot. Through the collection and analysis of realistic records from parking lots in Taipei city, a prediction algorithm is developed to estimate the successful parking probability by using current available space counts. Extensive experiments are conducted to demonstrate the effectiveness of the prediction algorithm.

Optimization of Charging Stops for Fleet of Electric Vehicles: A Genetic Approach

Abstract: Electrification of transport is one of the approach to improve transport efficiency and sustainability. The current cost of transport associated with electrical vehicles is mainly related to the cost of acquisition and maintenance of batteries. Finding an efficient way of managing the available energy allows reducing the size of the batteries and thus the cost associated with transport. Recently taxi services and urban delivery companies are introducing electric vehicles in their fleet. Available route planners do not consider properly the characteristics and charging stop requirements of EV fleets in decision making which results in non-optimal routing solution. The proposed work addresses the problem of finding the routes for a fleet of electric vehicles which will not only consider the battery limit of the vehicle, but also the concurrent use of charging stations along the route. The proposed solution computes routes for the fleet of vehicles that minimizes the associated cost which is a combination of travel time, charging time and the energy consumption along the route and is based on an evolutionary genetic algorithm with learning strategy. The results demonstrate that, the proposed algorithm finds a feasible solution in a reasonable amount of time and distributes the vehicles amongst the charging station to minimize the concurrency. The stated problem is non-polynomial and while genetic algorithm allows to efficiently explore large solution spaces, the work also presents some approximations and some strategies that allow to reduce the computational requirements and to find a solution in reasonable time.

Intersection-Based Road User Tracking Using a Classifying Multiple-Model PHD Filter

Abstract: -The number of fatal accidents involving pedestrians and bikers at urban intersections is still increasing. Therefore, an intersection-based perception system provides a dynamic model of the intersection scene to the vehicles. Based on that, the intersection perception facilitates to discriminate occlusions which is expected to significantly reduce the number of accidents at intersections. Therefore this contribution presents a general purpose multi-sensor tracking algorithm, the classifying multiple-model probability hypothesis density (CMMPHD) filter, which facilitates the tracking and classification of relevant objects using a single filter. Due to the different motion characteristics, a multiple-model approach is required to obtain accurate state estimates and persistent tracks for all types of objects. Additionally, an extension of the PHD filter to handle contradictory measurements of different sensor types based on the Dempster-Shafer theory of evidence is proposed. The performance of tracking and classification is evaluated using real world sensor data of a public intersection.

Managing the Charging of Electrical Vehicles: Impacts on the Electrical Grid and on the Environment

Abstract: Electric vehicles are seen as an option to reduce greenhouse emissions, directly related with the electricity generation mix and with the time of charging due to the variations of the generation sources during the day. At the same time, with their widespread adoption the increase in the demand for electricity to charge these vehicles could pose significant challenges to the electrical grid in terms of additional load due to unmanaged charge strategies. In order to mitigate these problems, the charging of the electrical vehicles must be managed. This paper presents the development of a system architecture to dynamically control the charging of electric vehicles to maintain the proper operation of the local distribution grid and minimize the environmental impact. The hardware consists of two modules, a meter and controllable plugs both with communication capabilities, while the software consists in a forecast and scheduler module. The forecast module calculates the load based on the power consumption behavior and uses the renewable generation forecast to assign the best time slot to charge the vehicle. The system aims to minimize the load peaks and flatten the load profile, while minimizing the environmental impacts. Based on the user preferences, system characteristics, consumption and renewable generation forecast, the system will assign the most suitable time slot to charge the electric vehicle. For the case of multiple electric vehicles, the system will schedule their charge based on a calculated priority level, in order to maintain a reliable operation of the local electrical grid.

A Comparison of Detrending Models and Multi-Regime Models for Traffic Flow Prediction

Abstract: Short-term traffic flow prediction received considerations from different fields, because of its essentialness in traffic engineering and its theoretical difficulties. In this paper, we studied two important approaches of traffic flow prediction: detrending methods and multi-regime methods. First, we compared their differences in modeling philosophy and compared their merits as well as shortcomings. Then, we tested several representative prediction models of these two approaches on the openly accessible PeMS traffic flow database to find their merits and shortcomings. The obtained results threw some interesting light on how to select the appropriate traffic prediction models in practices.

A Framework for Supporting Network Continuity in Vehicular IPv6 Communications

Abstract: The appearance of recent standards about cooperative ITS architectures towards a reference communication stack has been an inflection point in the research about vehicular networks. The ISO Communication Access for Land Mobiles (CALM) and the ETSI European ITS communication architecture have paved the way towards real and interoperable vehicular cooperative systems. Within these convergent proposals, IPv6 communications are recognized as a key component to enable traffic efficiency and infotainment applications. The proper operation of these applications and the achievement of value-added ITS services require an uninterrupted network connectivity. This paper addresses this problem by proposing a novel communication stack to support the provision of continuous and secure IPv6 vehicular communications. The solution follows the ISO/ETSI guidelines for the development of cooperative ITS systems and is based on standardized technologies such as Network Mobility (NEMO) protocol to provide an integral management of IPv6mobility. The solution integrates IEEE 802.21 media independent handover services for optimizing the handover process. While the support to the handover optimization offered by the proposed ITS communication stack is demonstrated through a mobility use case, a real testbed supporting most of the communications features is developed to validate and assess the real performance of the stack design.

Integration of Drive-by-Wire with Navigation Control for a Driverless Electric Race Car

Abstract: This article presents the design and implementation of a drive-by-wire system and a navigation control system for an autonomous Formula SAE race car. The result is the development of a platform for research into autonomous driving which can be easily replicated. Drive-by-wire actuators for acceleration, braking and steering of the vehicle are discussed, as well as the embedded low-level control system. The high-level navigation system features sensor fusion of a 6-dof IMU with a standard GPS and the integration of an automotive LIDAR. Operation of the vehicle is via a multi-threaded program with asynchronous IO and is based upon recording and driving waypoints. In addition to independent safety interlocks, active safety systems are an integral part to both the drive-by-wire and navigation systems.

Green Move: A Platform for Highly Configurable, Heterogeneous Electric Vehicle Sharing

Abstract: Vehicle sharing in urban areas has the potential to be the answer to some of the main issues that hinder the spreading of electric vehicles, in particular for what concerns the high upfront costs of the vehicles, combined with their still limited range, which can induce phenomena such as range anxiety. For its potential to be realized, vehicle sharing must be tailored to the multiform needs of its users by offering a wide range of support services that can be selected based on the user preferences. In this paper we present the platform for vehicle sharing developed in the Green Move project, which allows services to be dynamically loaded and unloaded on vehicles, and describe a pair of prototype applications to illustrate its benefits.

Estimating Required Probe Vehicle Re-identification Requirements for Characterizing Link Travel Times

Abstract: In the 1970s a framework was developed by Oppenlander to determine the sample size required for travel time estimation studies. This framework is still recommended today. This paper develops a new framework to improve upon the ideas set forth by Oppenlander. This new framework is based upon the Kullback-Leibler divergence. It allows for travel time studies to be evaluated in a more comprehensive way. Travel time estimation methods can now be evaluated on their ability to estimate travel time distributions instead of only the mean travel time. Also, this framework can be used on any travel time distribution whereas the Oppenlander framework was only properly suited for Gaussian distributions. The Kullback-Leibler divergence also allows for comparing both ID matching (i.e., small sample sizes with no erroneous travel times) and signature matching (i.e., large sample sizes mixed with some erroneous travel times) travel time estimation algorithms to be evaluated, while the Oppenlander framework was best suited for the ID matching algorithms. In this paper the Kullback-Leibler comparison framework for travel time studies is developed. The framework is then used to provide a comparison of an example ID matching and an example signature matching algorithm to demonstrate how both can be evaluated in a single framework. Finally, conclusions are made about the usefulness of the Kullback-Leibler comparison framework.

Parking Assistance System for Leaving Perpendicular Parking Lots: Experiments in Daytime\/Nighttime Conditions

Abstract: -Backing-out and heading-out maneuvers in perpendicular or angle parking lots are one of the most dangerous maneuvers, specially in cases where side parked cars block the driver view of the potential traffic flow. In this paper a new vision-based Advanced Driver Assistance System (ADAS) is proposed to automatically warn the driver in such scenarios. A monocular grayscale camera was installed at the back-right side of a vehicle. A Finite State Machine (FSM) defined according to three CANBus variables and a manual signal provided by the user is used to handle the activation/deactivation of the detection module. The proposed oncoming traffic detection module computes spatiotemporal images from a set of pre-defined scan-lines which are related to the position of the road. A novel spatio-temporal motion descriptor is proposed (STHOL) accounting for the number of lines, their orientation and length of the spatio-temporal images. Some parameters of the proposed descriptor are adapted for nighttime conditions. A Bayesian framework is then used to trigger the warning signal using multivariate normal density functions. Experiments are conducted on image data captured from a vehicle parked at different locations of an urban environment, including both daytime and nighttime lighting conditions. We demonstrate that the proposed approach provides robust results maintaining processing rates close to real time.

Fault Detection for Vehicular Ad Hoc Wireless Networks

Abstract: -An increasing number of intelligent transportation applications require robust and reliable wireless ad hoc communication. The process of communicating using radio requires a series of software and hardware modules to be functioning correctly. For many vehicle safety and automation applications communication is relied upon to the point where undetected faults can result in potentially dangerous situations, for example if a warning cannot be given in time to prevent a collision. The consequence of problems with any of the network components can be a partial or complete loss of radio communication. Generally, most systems will consider network failure when there is no communication, but this overlooks problems where a partial fault causes degradation in the communication performance. There is a fundamental requirement to detect and respond to the partial failure of a network to ensure that communication is not intermittent, or performs poorly after a certain range. The partial loss of communication is difficult to detect, and is often overlooked in mobile ad hoc network applications. This paper introduces a novel method for modeling the antenna performance using collected data, and using the model to determine the probability that an antenna has some level of performance degradation.

ITS for One of the Most Congested Cities in the Developing World?Dhaka Bangladesh: Challenges and Potentials [ITS in Developing Countries]

Abstract: Transportation planners from Dhaka city always confront the paradox of adjusting an ever increasing travel demand with the limited available resources. Thus, Dhaka city motorists suffocate while they idle in the intolerable gridlock for hours. ITS applications can play an active role in mitigating this gridlock by dramatically changing the existing problems of limited roadway capacity, vulnerable safety and neglected public transportation system. However, after carefully scrutinizing the prevailing traffic conditions and their interlinked problems, the authors have identified various potential ITS applications despite limited active ITS applications in Dhaka city. Observations indicate that rather than perpetuating the concept of ITS in Dhaka city as mythological, it is indeed a cost-effective method for both the users and the government for traffic management.

A Review of Network Mobility Protocols for Fully Electrical Vehicles Services

Abstract: This article reviews IETF network mobility techniques and ISO data protocols involved in electrical charging which represent key enablers for an IP-based platform composed of backend servers, networks of fixed charging stations and of mobile Fully-Electrical Vehicles (FEVs). This platform further allows services for ensuring driver's confidence in reaching arbitrary destinations, despite well-known limitations such as battery technologies, and mitigating the risks involved by the use of inherently insecure basic IP datagram exchanges.

Using Inquiry to Expose Undergraduates to ITS

Abstract: In our rapidly evolving world, asking the right questions and properly defining problem boundaries is paramount to successful engineering design. These practices are especially vital for Intelligent Transportation Systems (ITS), which can address a wide range of transportation problems, but which also can exacerbate these same problems. For example, ITS solutions that address the narrowly defined problem of improving traffic flow in an urban area can lead to more regional sprawl, and therefore more traffic and so on-reinforcing a negative feedback loop with ugly results. If the problem is instead framed as trying to reduce commuting times, entirely different and more sustainable ITS solutions may be found. The best planners proceed with caution to avoid prescribing solutions to perceived problems; instead, they take care to understand challenges to urban mobility and the propagating impacts that different development strategies may have. Genuine inquiry, the act of asking questions, ought to be a foundation of engineering education. Indeed, an accumulating amount of engineering education research makes the benefits of such active learning techniques impossible to ignore. Inquiry-based learning begins by posing questions, problems or scenarios in lieu of simply presenting established facts or portraying an existing path to knowledge. It places students' questions, ideas and observations at the center of the learning experience. As students engage with challenges and questions, they achieve higher levels of learning-past the stage of memorizing and reciting data-to more sophisticated methods of analysis, synthesis, and application. The instructor's role is to creatively combine best practices, including explicit instruction, and small-group and guided learning in an attempt to build on students' interests and ideas, ultimately moving students forward in their paths of intellectual curiosity and understanding. This inquiry-based approach is used to introduce a team of Clemson students to the principles and applications of ITS in developing nations.

Transferring ITS Research to the Real World [President's Message]

Abstract: The IEEE ITS Society has been on the forefront of disseminating Intelligent Transportation System research results with our conferences, most notably the Intelligent Vehicle Symposium (this year held in Dearborn, Michigan, see http://www. ieeeiv.net/) and the ITS Conference (this year held in Qingdao, China, see http://www. itsc2014.org/). In addition, our IEEE Transactions on Intelligent Transportation Systems has consistently had the highest impact factors of any journal in disseminating ITS research results. But we need to remember that advancing research in ITS is only part of the story— there is often a large gap between conducting innovative research and then having it deployed in the real world. The researchers and the practitioners need to interact closely, otherwise the best ITS research may never come to fruition. To help bridge this gap, this IEEE ITS Magazine serves as an interdisciplinary forum for researchers, practitioners, application engineers, transportation agencies, government sponsors, and academia to share information on all aspects of intelligent transportation systems. Sponsors of ITS research have a vested interest in making sure that their investment eventually leads to deployment. Government agencies don’t fund ITS research just so that it ends up as a paper in our society’s conferences or journal publications. It is critical that the best ITS research has a pathway to eventually becoming a reality. A common pathway is exemplified with the recent connected vehicle research programs being carried out in the U.S., in Europe, and in Asia. Vehicles that can communicate with each other or with the infrastructure are “connected”, allowing for a wide variety of innovative applications. These applications can focus on improving safety, mobility, environmental factors, or some combination of all three. Applications usually start as a general “concept” whose operation can then be carefully defined. These concepts (and their many variations) can then be modeled and evaluated using advanced analytical or computer simulation tools. These tools can be used to quantify particular benefits in safety, mobility or the environment. These research results often find their way into our transactions and conference papers—but the research shouldn’t simply end there. If an application has the potential to be highly beneficial, costs and other deployment issues need to be considered. A small demonstration of the ITS technology or a prototype may be in order to see if the concept is viable in the real world. Next, pilot programs may be implemented at a larger scale and over a longer period of time to collect supporting data. The best pilot programs may even transition to a long term deployment, where different business models can support these new ITS applications. Our IEEE ITS Society does a great job in dealing with the technical issues of ITS; however we need to consider many of the other non-technical issues if we are ever going

New Conductor, Same Orchestra [Editor's Column]

Abstract: It is with great pleasure that I take on the responsibility as the new Editor-in-Chief of the ITS Magazine after my appointment by the ITSS President in January 2014. My first words in my message have to necessarily be words of gratitude toward my predecessor in the post, Dr. Jeffrey Miller, not only for the brilliant work that he has done as EiC in the last years in order to push the quality of the journal, but also for the generous and seamless support that he has provided to me in the preparation of the 2014 Summer issue. Definitely, Jeffrey has made the transition painless for me, and I hope, also for our readers, authors, and contributors. Thanks indeed for that, Jeff! As already announced in our previous issue, this year should mark the first impact factor of the Magazine. As a matter of fact, all manuscripts published in the Magazine since its inception in 2009 are already indexed in the Inspec® database that can be consulted from the Web of Knowledge. That’s great news that I want to share with you but, of course, it goes without saying that I cannot take any credit for that. It has been the timely efforts of our previous EiCs, Dr. Jeffrey Miller and Dr. Christoph Stiller, that has made this possible. I will build on the momentum created by them. Kudos to Jeff and Christoph for this great achievement! As a premier publication of the ITS Society, we are committed to make the Magazine a reference journal for ITS papers targeting a wide audience. For such purpose, we welcome contributions from top researchers all across the globe. Of particular interest to the Magazine are articles providing descriptions of advanced experiments and applications, overviews of research projects, prospective studies and future trends, comparisons among ITS technologies, etc. As usual, your suggestions and comments for improving the Magazine are most appreciated. Do not hesitate to contact me in order to share your views regarding the suitability of a paper or any other question on guidelines. You can e-mail me or simply grab me at a conference. I am always open for fruitful discussions. Please, accept my gratitude in advance to all authors, associate editors and other contributors, for your valuable support. I hope many of you are planning to submit your next article to the ITS Magazine. It is time to make the Magazine flourish and grow into a high impact factor publication. You can count on my full commitment for that. Let’s make it together!

Image Processing and Pattern Recognition Research Center of the Technical University of Cluj-Napoca, Romania [ITS Research Lab]

Abstract: The Technical University of Cluj-Napoca is a 100-year old institution of higher technical education based in the city of Cluj-Napoca, in the heart of Transylvania, Romania. The University offers all levels of degree education in multiple technical fields, including Computer Science and Engineering. Currently, there are more than 20000 students enrolled with TUCN. The Image Processing and Pattern Recognition Research Center (IPPRRC) was set up in 1998 as an independent research team within the Computer Science Department of TUCN leveraging expertise in hardware design and software integration, signal and image processing and pattern recognition. Three years later, Prof. Nedevschi and a young research team started a fruitful cooperation with the research division of Volkswagen AG, Germany, in the field of stereovision applied to driving assistance. The initial research agreement SCABOR- Stereo CAmera Based Object Recognition, a one year contract, was followed by more than 12 research contracts, for more than 10 years, with multiple scientific and technologic achievements. Today, IPPRRC is a powerful research team consisting of four senior and 8 junior faculty members with eleven graduate students.