INTELLIGENT TRANSPORTATION SYSTEMS

http://www.ieee.org/its

IEEE ITS SOCIETY NEWSLETTER

Editor: Prof. Bart van Arem, b.vanarem@utwente.nl Vol. 8, No. 2, June 2006

In This Issue
Society News Message from the Editor: Bart van Arem . . . . . . . . Message from the IEEE ITS Society President: Fei-Yue Wang: . . . . . . . . . . . . . . . . . . . . . . . . . Message VP Conferences: Umit Ozguner . . . . . . . . . Message VP Member Activities: Christoph Stiller . . . . Message VP Publications: Jason Geng . . . . . . . . . . IEEE Trans. on ITS Report: Alberto Broggi . . . . . . IEEE Transactions on ITS - Index: Simona Bert . . . . e . 3 3 ITSS Newsletter Editorial Board
Editor-chief: Bart van Arem, . . . . . . . . b.vanarem@utwente.nl Editorial assistant: Dorette Alink-Olthof, . . d.alink-olthof@utwente.nl Associate editors: IEEE Transactions on ITS report and abstracts: Alberto Broggi and Simona Bert, e . . . . . . . . transits@ce.unipr.it Technical contributions: Brian Park, . . . . . . . bpark@virginia.edu Book reviews: Algirdas Pakstas, . . a.pakstas@londonmet.ac.uk Conferences, workshops and journals: Alessandra Fascioli and Massimo Bertozzi, . . . . . . . . itsconfs@ce.unipr.it Research programs: Angelos Amditis, . . . a.amditis@iccs.gr

. 3 . 5 . 6 . 7 . 8 . 10

Conference Reports 14 IEEE ISI 2006 Conference Report, by Daniel Zeng, Hsinchun Chen and Fei-Yue Wang . . . . . . . . . . 14 Technical Contributions 16 Distributing the Cost of Securing a Transportation Infrastructure, by Sudarshan S. Chawathe . . . . . . . 16 Driving into the Future with ITS, by Fei-Yue Wang . . . 22 Research Programs 25 Research Review, by Angelos Amditis . . . . . . . . . . . 25 Announcements 30

Conferences, Workshops, Symposia 37 By Massimo Bertozzi and Alessandra Fascioli . . . . . . . 37 Web Archive
All past issues of this Newsletter can be reached through the Societys Ocial Web Site at: http://www.ieee.org/its

Information for contributors

Announcements, feature articles, books and meetings reviews, opinions, letters to the editor, professional activities, abstracts of reports, and other material of interest to the ITS community is solicited. Please submit electronic material for consideration in any of the following formats: A L TEX, plain ASCII, PDF, or Word, and pictures seperately in jpeg format to the Editor at b.vanarem@utwente.nl as well as to the assistant d.alink-olthof@utwente.nl at least 1 month prior to the newsletters distribution: Issue Due date March February 1st June May 1st September August 1st December November 1st

Electronic Newsletter Subscription

To obtain a free short announcement in your e-mail as soon as the next Newsletter issue is available, please sign in through the Society Web Site at: http://www.ieee.org/its The IEEE ITS Society Newsletter is published 4 times per year and is sent to over 10,000 subscribed ITS professionals from industry, academia and government.

THE IEEE INTELLIGENT TRANSPORTATION SYSTEMS SOCIETY

President: . . . . . . . . . . . . . . . . . . . . . . Fei-Yue Wang, CAS, China and U. of Arizona, Tucson, AZ 85721, USA Immediate Past President: . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Charles J. Herget, Alameda, CA 94502, USA Vice President Conferences: . . . . . . Umit Ozguner, Ohio State University, Columbus, OH 43210, USA Vice President Publications: . . . . . . . . . . . . . . . . . . . . . . . . . . Jason Geng, Rockville, MD 20895-2504, USA Vice President Finance: . . . . . William Scherer, University of Virginia, Charlottesville, VA 22904. USA Vice President Technical Activities: . . . . . . . . . . . . . . . . . . Daniel Zeng, University of Arizona, Tucson, AZ 85721, USA Vice President Administrative Activities: . . . . . . Daniel J. Daily, University of Washington, Seattle, WA 98195, USA Transactions Editor: . . . . . . . . . . . . . . . . . . . . . Alberto Broggi, Universit` di Parma, Parma, I-43100, Italy a Newsletter Editor: . . . Bart van Arem, University of Twente, Enschede, NL-7500AE, The Netherlands

COMMITTEES Awards Committee: Chip White (Chair): . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . cwhite@isye.gatech.edu Conferences and Meetings Committee: Umit Ozguner (Chair): . . . . . . . . . . . . . . u.ozguner@ieee.org Constitution and Bylaws Committee: Daniel J. Dailey (Chair): . . . . . . . . . . . . . . . d.dailey@ieee.org Fellow Evaluation Committee: Robert Fenton (Chair): . . . . . . . . . . . . . . . . . . . . . . . . . fenton.2@osu.edu Finance Committee: Bill Scherer (Chair): . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . w.scherer@ieee.org History Committee: E. Ryerson Case (Chair): . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . r.case@ieee.org Long Range Planning Committee: Pitu B. Mirchandani (Chair): . . . . . . . . . . . pitu@sie.arizona.edu Member Activities Committee: Christoph Stiller (Chair): . . . . . . . . . . . . . . . . . . . . . . stiller@mrt.uka.de Nominations and Appointments Committee: Charles Herget (Chair): . . . . . . . . . . c.herget@ieee.org Publications Committee: Jason Geng (Chair): . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . jason.geng@gmail.com Standards Committee: Jason Geng (Chair): . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . jason.geng@gmail.com Student Activities Committee: Sudarshan S. Chawathe (Chair): . . . . . . . . . . . . . . . . . . chaw@cs.umd.edu Technical Activities Committee: Daniel Zeng (Chair): . . . . . . . . . . . . . . . . . . . zeng@eller.arizona.edu

Society News

From the Editor

by Bart van Arem Dear readers of the newsletter, We have a lot of interesting new material to share with you. In the presidents message Fei-Yue Wang will inform you about many ongoing and new activities of the ITS Society. Many thanks to Brian Park and Angelos Amditis for joining the editorial board of this newsletter, their rst contributions are in this newsletter. We have new interesting technical papers and a research overview focusing on intelligent vehicle activities in Europe. As always, we are keen to receive your contributions, the newsletter is read by over 1,000 readers from all over the world and from all sectors. I hope you enjoy reading this newsletter. Bart van Arem Editor in Chief

Message from the IEEE ITS Society President

by Fei-Yue Wang Dear ITSS Newsletter Readers, Welcome to this new issue of the IEEE ITSS Newsletter. I would like to take this opportunity to summarize the major items discussed in our February ExCom and June BoG meetings. The rst ExCom meeting this year was held on February 11 in Phoenix, Arizona, USA, co-located with the IEEE TAB Meeting. The rst BoG meeting this year was held at IV06 on June 12 at the University of Tokyo, Japan. In addition, an ExCom teleconference was held in May. The major items reported and discussed at those meetings are as follows: Some changes have been made to the ITSS bylaws. The nominations and appointments committee is now the nominations committee. Although the society is solid nancially with a healthy reserve and steady revenue streams, due to the recent changes from the IEEE (dierent formula for publication revenue distribution, increased IEEE 3

administrative fee, among others), we are expecting to have a decit of 51.7K USD in year 2007. To increase our society membership base, we are planning to recruit aggressively from the participants of ITSS conferences through oering discounted society membership dues. Our transactions and newsletters continue to do very well. The number of the submissions at the transactions has experienced signicant growth in the rst several months of 2006, indicating increased acceptance and growing impact on the ITS research eld. The average number of days from submission to the rst decision at our transactions is below 100 days. To manage the increasing number of submissions to our transactions, based on the BoG recommendation, the ITSS VP for Publications is charged with the task of forming a committee to study the feasibility and pros and cons of several possible approaches ranging from increasing the page budget, creating sub-series or parts, to creating multiple transactions. The ITS book series ocially kicks o with the IEEE Press. Interested authors are encouraged to send book proposals to me at feiyue@sie.arizona.edu. The award program has been initiated within the ITSS. We are expecting to convey awards on best doctoral dissertations and ITS research contributions in 2006. Two industry sponsors have agreed to support these awards with multi-year commitments. The society approved a Technical Activity Board (TAB) structuring plan in 2005. The purpose is to establish a comprehensive set of technical committees (TCs) organized by ITS subject topics. These TCs are expected to promote ITS research through special sessions in conferences, special issues in journals, and collaborative eorts with communities outside of the ITSS. Through these TCs, ITSS also plans to form an international conference program committee to provide reviewers for ITSS conferences. Steady progress has been made in this TAB eort. Currently ITSS has nine TCs with several more pending. A Web-based system called ITSS Expertise Portal is also under active development to provide a platform to support TAB functions and allow easy search of ITS experts based on a number of search criteria. It is the consensus among BoG members that developing standards would be a critical direction to take for the ITSS to generate revenue and broaden its impact in both research and industry. A draft of the operating procedures for the ITSS Standard Committee as an IEEE Standards Development Sponsor has been completed and is being forwarded to the IEEE for the approval. The ITSS has been sponsoring a number of premier academic conferences. Consider the set of the ITSS conferences from last year until now, they have all been successful both academically as well as nancially. A number of conferences have been approved at the BoG meeting: VES06, ISI07, SOLI07, VES07, and ISI08. A complete listing of ITSS-sponsored conference series is given below. IEEE Intelligent Transportation Systems Conference (ITSC) IEEE Intelligent Vehicle Symposium (IV) IEEE Vehicular Electronics and Safety Conference (VES) IEEE Intelligence and Security Informatics Conference (ISI) IEEE Service Operations and Logistics, and Informatics Conference (SOLI) IEEE/ASME Mechatronic and Embedded Systems and Applications Conference (MESA) (main sponsorship by IEEE and ASME in alternating years)

As part of the overall revenue-generation eort, we are actively pursuing setting up industry exhibitions at ITSS conferences. The outreaching activities of the ITSS have been quite successful. Three local chapters of the ITSS have been established in China (two of them just completed all the IEEE paperwork). The ITSS also organized the IEEE Presidents visit to China and the IEEE Computational Intelligence Societys Tour de China in Spring 2006. Joint task forces are being formed between ITSS and other IEEE societies such as Systems, Man, and Cybernetics; and Computational Intelligence. Joint events with professional societies outside of the IEEE including the American Society of Mechanical Engineers (ASME) are being planned and organized (e.g., joint sponsorship of the IEEE/ASME MESA conference series). 4

 The current ITSS membership base is concentrated in developed countries such as the U.S. and European countries. Tremendous opportunities to grow the society are expected from emerging markets. As a strategic movement, BoG overwhelmingly supports expanding activities and presence in countries such as China, India, Russia, and Brazil. As an example, industry sponsorship is being currently seeked to support an ITSS Tour de China in 2007 to explore collaboration opportunities and to recruit members. As part of strategic planning to grow our society, the long-term planning committee will create a document describing the vision for the ITSS in ve and 10 years by the end of 2006. A strong membership base and its acitive participation in our programs are the very reason for the existance of the IEEE ITSS. As the rst elected President of the IEEE ITSS, my main responsibility is to promote our members professional interest by creating more and better services and activities in ITS related areas. There is a long way to go, but we are on the right track, lets drive into the future with Intelligent Transportation Systems. Fei-Yue Wang President of IEEE ITSS

Message from the VP for Conferences

by Umit Ozguner I would rst like to thank the publishers of the ITS Society e-Newsletter for giving me the opportunity to address the IEEE ITS Society membership. I hope that all the readers of the Newsletter are indeed members, or will rush to become members so as to participate in, and benet from all our activities. One of our key activities is the organization and coordination of a number of technical meetings. The IEEE ITS Society logo that you see at the top of our conference announcements looks like a seal. I like to think that this is indeed a seal that indicates quality. It guarantees the quality of the presentations, that the papers have been reviewed by a serious group of competent peers, the plenary talks are by experts in the area, the tutorials are informative, demonstrations state-of-the-art and the attendees are the engineers, technical sta and policy-makers you want to meet. That is what our logo means. So how does this all happen? IEEE is an interesting organization with a mixture of professionals and volunteers working to fulll its goals. The setting up of a conference goes through many stages where dierent individuals at IEEE headquarters and Society volunteers all around the world cooperate. Depending on the size of the conference, symposium or workshop, activity begins two to ve years before the event. A team is set up, hotel found, budget established, contracts signed. All the above go through various approval processes. A program committee is formed, announcements distributed, papers reviewed and selected. Proceedings are published, registration is set up, and yes, meals are selected. The conference runs, it is a great success, people cheer. It is over. But actually it is not. Reports are written, bills are paid, and then it is really over. So why go through all of this as a volunteer? It is the same answer as volunteers always give. It is a contribution to your peer group, to ensure quality, to create interest, to provide mentoring, and to be part of a team that guarantees that good things happen in your profession.

After all of that, you shouldnt be surprised as I invite you to participate in organizing our conferences. Volunteer. Get involved. Maybe a small part at rst, and then more responsibility if you are interested. The IEEE ITS Society annually sponsors six conferences at the time I write this. The largest and oldest of them are the IEEE ITS Conference (our agship Conference), this year in Toronto September 17-20, next year in Seattle; and the Intelligent Vehicles Symposium, which we just held June 13-15 in Tokyo. Next year it will be in Istanbul. We are expanding the ITS Society interest area and supporting more focused, somewhat smaller meetings too. So we are sponsoring ISI (Intelligence and Security Informatics), SOLI (Service Operations Logistics and Informatics), VES (Vehicular Electronics and Safety) and MESA (Mechatronic and Embedded Systems and Applications). I will provide a 3 year calendar of these conferences in the next issue of the Newsletter. You can get involved. Write to me (ozguner.1@osu.edu) if you are interested in being part of the teams that are organizing these meetings. It is fun, it is informative and it a worthy endeavor. I would also like to invite you to come up with ideas for new conferences. u Umit Ozgner

Message from the VP Member Activities

by Christoph Stiller

I am frequently asked by PhD students and young professionals whether engagement in our professional society really adds value to their career. I am sure it does in many - often subtle - ways. Clearly, as a prominent issue, the IEEE Intelligent Transportation System Society provides important information via its publication organs, including our ITS newsletter, transactions, ITS conference proceedings and its magazine. Getting rst-hand information about what is going on in our fast moving technical eld is crucial for professional engineers. Often employers appreciate engagement in the IEEE ITSS. This is not just for the reduced rates our members enjoy at important conferences, but because this signals that an engineer is interested and active in his scientic eld and its community. Many engineers consider voluntary work for our activities and conferences not just as a service to our community but also as a networking opportunity for themselves. Sometimes the right information or just the right contact can make a big dierence. So there are many reasons to be IEEE ITSS member! I am therefore glad to see that our society and its activities are still growing at a fast pace driven by its members and enthusiastic volunteers. Many new activities have been and even more are being launched. This includes recognition of outstanding PhD dissertations, new conferences, journals and chapter activities. In less than 1.5 years our society has already come a long way and we have good reasons to stay excited about and actively contribute to the future of ITS!

IEEE ITSS Membership: Opening the world of ITS Technology

IEEE Intelligent Transportation Systems Society: http://www.ewh.ieee.org/tc/its. 6

Message from the VP for Publications

by Jason Geng We are in the process of preparing for the launch of our societys formal magazine - Intelligent Transportation Systems Magazine (ITSM). ITS elds have grown rapidly and those who are interested in academic research already have their dissemination vehicle of IEEE Transactions on Intelligent Transportation Systems. For those practitioners who have focused on ITS applications and implementations, there is no publication vehicle currently for them. ITSM therefore plans to ll this gap and to publish peer-reviewed articles that provide innovative research ideas application results report signicant application case studies raise awareness of pressing research and application challenges in all areas of intelligent transportation systems. In contrast to the highly academic publication of the IEEE Transactions on Intelligent Transportation Systems, the ITSM focus on providing needed information to all members of ITS society, serving as a dissemination vehicle for ITS Society members and the others to learn the state of the art development and progress on ITS research and applications. high quality tutorials, surveys, successful implementations, technology reviews, lessons learned, policy and societal impacts, and ITS educational issues will also be published as well. There will be no overlapping between ITSM with other existing IEEE periodicals ITSM focuses on applications and implementation of ITS research results. None of the existing IEEE periodicals provide coverage in this eld. Paper Sources includes: The contributing authors are expected from the general ITS research and applications community including researchers and practitioners in the elds of intelligent transportation systems, information technologies, law enforcement, terrorism studies, public policy, and social and behavioral studies who are working on national/international ITS-related topics. We also expect high percentage of contributions from ITS experts in various ITS related industries, industry consultants and practitioners focusing on successful implementations, practical challenges, lesson learned, and policy considerations. Invited papers will be utilized to ensure that the initial issues will have the best papers possible. The authors and participants of the annual IEEE ITS conferences, and other meetings sponsored by the ITS Society will also be tapped for contributions. The ITSM is in its infancy, we are inviting everyone who is interested in ITS eld to make his/her unique contribution to its paper source as well as to its board of editors. Please contact me for details: Jason.geng@ieee.org.

Report on IEEE Trans. on Intelligent Transportation Systems

by Alberto Broggi

Transactions EiC report, updated May 23, 2006

A few more numbers on year 2005: the number of papers submitted in 2005 and which reached a decision in 2005 is 128. 1. the average number of days from submission to rst decision for papers that reached a decision in 2005 is 99.5 2. Out of 128 papers that reached a decision, 63% reached a decision within 100 days 3. Out of 128 papers that reached a decision, 79% reached a decision within 120 days 4. Out of 128 papers that reached a decision, 89% reached a decision within 140 days These numbers are shown in the attached chart: the x axis shows all the papers that were submitted in 2005 and reached a decision in the same year; the height of each bar represents the number of days to reach the rst decision.

The following special issues are under way: - special issue on Cooperative Intelligent Vehicles (guest editors: Ljubo Vlacic, Toshio Fukuda) - special issue connected to IV05 (guest editor: Fei-Yue Wang) - special issue connected to ICVES05 (guest editors: Nenning Zheng, Hironao Kawashima) - special issue connected to ITSC05 (guest editors: Bart De Shutter, Andreas Hegyi)

- special issue on On-the-road Mobile Networks (guest editor: C.K.Toh) The migration to ManuscriptCentral version 3.4 is still on hold. It was stopped by IEEE sta since it was demonstrated that the migration process introduces inconsistencies and corrupts the Journal database. Therefore, we are waiting for a bug-x from manuscript Central, before even considering the migration. The attached gure shows: in blue the number of papers submitted in each month from April 2003 (when we switched to electronic submission), and in red the number of papers sill without a decision; this means that either the rst submission did not come to an end, or that a new revision is currently under evaluation. The gure shows that the trend is positive and, a part from isolated cases, all submitted papers receive a notication in a reasonably short time.

IEEE Trans. on Intelligent Transportation Systems - Index

by Simona Bert e To go directly to the online Transactions Table of Contents, click on Index above. IEEE ITSS members have full access to the papers. Non-members can browse the abstracts, which are provided below. Vol.7, No.2, June 2006 POP-TRAFFIC: A Novel Fuzzy Neural Approach to Road Trac Analysis and Prediction, by Chai Quek, Michel Pasquier and Bernard Lim Abstract: Although much research has been done over the decades on the formulation of statistical regression models for road trac relationships, they have been largely unsuitable due to the complexity of trac characteristics. Trac engineers have resorted to alternative methods such as neural networks but, despite some promising results, the diculties in their design and implementation remain unresolved. In addition, the opaqueness of trained networks prevents understanding the underlying models. Fuzzy neural networks, which combine the complementary capabilities of both neural networks and fuzzy logic, thus constitute a more promising technique for modelling trac ow. This paper describes the application of a specic class of fuzzy neural network known as the Pseudo Outer-Product Fuzzy Neural Network using Truth-Value-Restriction method (POPFNN-TVR) for short-term trac ow prediction. The results obtained highlight the capability of POPFNN-TVR in fuzzy knowledge extraction and generalization from input data as well its high degree of prediction capability as compared to traditional feed-forward neural networks using back-propagation learning. An Enhanced Soft Hando Scheme for real-time streaming services in Intelligent Transportation Systems based on CDMA, by Young-uk Chung and Dong-Ho Cho Abstract: CDMA based radio-on-ber (ROF) road-vehicle communication systems was proposed to support real-time streaming services in intelligent transportation systems (ITS). Soft hando should be provided for real-time streaming services because these services are required to guarantee real-time property and quality of service (QoS). However, soft hando of real-time streaming services causes the shortage of resource in view of the system. In this paper, we propose the double adjustment soft hando (DASH) scheme to support seamless service regardless of the shortage of resource and maximize the resource eciency when real-time streaming services are served in CDMA based ITS. The DASH scheme adjusts data rate of a call when it starts and nishes soft hando. We evaluate the performance of the DASH scheme by analytical and simulation method. Performances are evaluated with respect to the blocking probability, the hando failure probability and the carried trac. Numerical results show that the proposed scheme can give relative good maintenance of calls and good throughput. Power Matching Approach for GPS Coverage Extension, by Samer S. Saab and Zaher M. Kassas Abstract: The inherent problem of the Global Positioning System (GPS), which is signal obstruction, remains the major obstacle that inhibits it from functioning as a reliable standalone positioning system. Therefore, it is becoming a common practice to couple the GPS system with an external positioning system whenever the GPS receiver is expected to operate in regions of dense canopy, such as urban areas. Commercial automobile navigation systems currently employ a GPS receiver coupled with a dead reckoning system and a map-matching algorithm. Most dead reckoning systems, which compensate for GPS inaccuracies and frequent GPS signal obstructions, employ an odometer and a directional sensor. In this paper a power matching approach is proposed for GPS coverage extension in urban area. The algorithm, based on a statistical measure, correlates the received power from dierent GPS satellite vehicles (SVs); leading to a specic 10

signature, to a topographical database with periodic time-varying estimates of SVs received powers. An experimental approach is presented to examine the feasibility of applying the proposed positioning system. Calibrating a Real-Time Trac Accident Prediction Model Using Archived Weather and ITS Trac Data, by Mohamed Abdel-Aty and Rajashekar Pemmanaboina Abstract: Growing concern over trac safety has led to research eorts directed towards predicting freeway crashes in ATMIS (Advanced Trac Management and Information Systems) environment. This study aims at developing crash likelihood prediction model using real-time trac ow variables (measured through series of underground sensors) and rain data (collected at weather stations) potentially associated with crash occurrence. Archived loop detector and rain data and historical crash data have been used to calibrate the model. This model can be implemented using on-line loop and rain data to identify high crash potential in real-time. Principal Component Analysis (PCA) and Logistic Regression (LR) have been used to estimate a weather model that determines a rain index based on the rain readings at the weather station in the proximity of the freeway. A matched case-control logit model has also been used to model the crash potential based on trac loop data and the rain index. The 5-minute average occupancy and standard deviation of volume observed at the downstream station, and the 5-minute coecient of variation in speed at the station closest to the crash, all during 5-10 minutes prior to the crash occurrence along with the rain index have been found to aect the crash occurrence most signicantly. An Automatic Trac Surveillance System for Vehicle Tracking and Classication, by JunWei Hsieh, Shih-Hao Yu, Wen-Fong Hu and Yung-Sheng Chen Abstract: This paper presents an automatic trac surveillance system to estimate important trac parameters from video sequences using only one camera. Dierent from traditional methods which can classify vehicles to only cars and non-cars, the proposed method has a good ability to categorize vehicles into more specic classes by introducing a new linearity feature in vehicle representation. In addition, the proposed system can well tackle the problem of vehicle occlusions caused by shadows, which often lead to the failure of further vehicle counting and classication. This problem is solved by a novel line-based shadow algorithm which uses a set of lines to eliminate all unwanted shadows. The used lines are devised from the information of lane dividing lines. Therefore, an automatic scheme to detect lane dividing lines is also proposed. The found lane dividing lines can also provide important information for feature normalization, which can make the vehicle size more invariant and thus much enhance the accuracy of vehicle classication. Once all features are extracted, an optimal classier is then designed to robustly categorize vehicles into dierent classes. When recognizing a vehicle, the designed classier can collect dierent evidences from its trajectories and the database to make an optimal decision for vehicle classication. Since more evidences are used, more robustness of classication can be achieved. Experimental results show that the proposed method is more robust, accurate, and powerful than other traditional methods, which utilize only vehicle size and single frame for vehicle classication. Detection and Classication of Highway Lanes Using Vehicle Motion Trajectories, by Andrew Naftel, Jos P. Melo, Alexandre Jos Malheiro Bernardino and Jos Santos-Victor Abstract: Intelligent vision-based trac surveillance systems are assuming an increasingly important role in highway monitoring and road management schemes. This paper describes a lowlevel object tracking system that produces accurate vehicle motion trajectories which can be further analysed to detect lane centres and classify lane types. Accompanying techniques for indexing and retrieval of anomalous trajectories are also derived. An algorithm known as Predictive Trajectory Merge-and-Split (PTMS) is used to detect partial or complete occlusions during object motion, and incorporates a Kalman Filter that is used to perform vehicle tracking. The resulting motion trajectories are modelled using variable low degree polynomials. A K-means clustering technique on the coecient space can be used to obtain approximate lane centres. Estimation bias due to vehicle lane changes can be removed using robust estimation techniques based on 11

RANSAC. Through the use of non-metric distance functions and a simple directional indicator, highway lanes can be classied into one of the following: entry, exit, primary or secondary. Experimental results are presented to show the real-time application of this approach to multiple views obtained by an uncalibrated pan-tilt-zoom trac camera monitoring the junction of two busy intersecting highways. Real-Time Disparity Contrast Combination for Onboard Estimation of the Visibility Distance, by Nicolas Hauti`re, Raphal Labayrade and Didier Aubert e e Abstract: An atmospheric visibility measurement system capable of quantifying the most common operating range of onboard exteroceptive sensors is a key parameter in the creation of driving assistance systems. This information is then utilized to adapt sensor operations and processings or to alert the driver that his onboard assistance system is momentarily inoperative. Moreover, a system capable of either detecting the presence of fog or estimating visibility distances constitutes in itself a driving assistance. In this paper, we present a technique to estimate the mobilized visibility distance through use of onboard CCD cameras. The latter represents the distance to the most distant object on the road surface having a contrast above 5%. This denition is very close to the denition of the meteorological visibility distance proposed by the International Commission on Illumination (CIE). Our method combines the computations of local contrasts above 5% and of a depth map of the vehicle environment using stereovision within 60 ms on a current-day computer. In this paper, both methods are described separately. Then, their combination is detailed. Our method is operative night and day in every kind of meteorological conditions and is evaluated thanks to video sequences under sunny weather and foggy weather. ACC+Stop&Go Maneuvers with Throttle and Brake Fuzzy Control, by Jos E. Naranjo, e Carlos Gonzlez, Ricardo Garci and Teresa de Pedro a a Abstract: The research on adaptive cruise control (ACC) extended to Stop&Go maneuvers is presently one of the most important topics in the eld of intelligent transportation systems. The main feature of such controllers is that there is adaptation to a user-preset speed and, if necessary, speed reduction to keep a safe distance from the vehicle ahead in the same lane of the road, whatever the speed. The extreme case is the stop and go operation in which the lead car stops and the vehicle at the rear must do so too. In this paper, we present the development of an ACC system and related experiments. The system input information is acquired by a real-time kinematic phase dierential GPS (i.e. centimetric GPS) and WLAN links. The outputs are the variables that control the pressure on the throttle and brake pedals, calculated by an onboard computer. And the car control is based on fuzzy logic. The system has been installed in two mass-produced Citron Berlingo electric vans, in which all the actuators have been automated to e achieve human-like driving. The results from real experiments show that the unmanned vehicles behave very similarly to human-driven cars and are very adaptive to any kind of situation at a broad range of speeds, thus raising the safety of the driving and allowing cooperation with manually driven cars. Time to Line Crossing for Lane Departure Avoidance: a Theoretical Study and an Experimental Setting, by Said Mammar, Sbastien Glaser and Mariana Netto e Abstract: The main goal of this paper is to develop a distance to line crossing (DLC) based computation of time to line crossing (TLC). Dierent computation methods with increasing complexity are provided. A discussion develops the inuence of assumptions generally assumed for approximation. A sensitivity analysis with respect to the vehicle parameters and positioning is performed. For TLC computation, both straight and curved vehicle paths are considered. The road curvature being another important variable considered in the proposed computations, an observer for its estimation is then proposed. An evaluation over a digitalized test track is rst performed. Real data is then collected through an experiment carried out in test tracks with our equipped prototype vehicle. Based on these real data, the TLC is then computed with the 12

theoretical proposed methods. Obtained results outlined the necessity to take into consideration vehicle dynamics in order to use the TLC as a lane departure indicator. Automatic Commercial Aircraft Collision Avoidance in Free Flight: The Three Dimensional Problem, by Manolis A. Christodoulou and Sis G. Kodaxakis Abstract: In this paper, we consider optimal resolution of air trac (AT) conicts. Aircraft are assumed to cruise within a free altitude layer and are modeled in three dimensions with variable velocity and proximity bounds. Aircraft cannot get closer to each other than a predened safety distance. We consider the problem of solving conicts arising among several aircraft that are assumed to move in a shared airspace. For such systems of multiple aircraft, we minimize the total ight time by avoiding all possible conicts. This paper proposes a formulation of the conict avoidance problem as a mixed integer non linear programming problem. In our case, only velocity changes are admissible as maneuvers. Nevertheless in subsequent work we will be checking for simultaneous velocity and heading angle changes too. Simulation results for realistic aircraft conict scenarios are provided. A Reliability Framework for Trac Signal Control, by Hong K. LO Abstract: An important consideration for trac signal control is that trac arrivals are not deterministic. The eect of stochastic arrivals is mainly handled by introducing stochastic terms in delay formulae. While convenient, this approach is somewhat indirect. Moreover, when the degree of saturation is high, the system becomes transient; it is questionable whether a static or time-invariant result in the form of a delay formula is applicable. In this study, instead of relying on steady state or equilibrium probability measures, we capture the transient eect by analyzing the state of the system from cycle to cycle based on a probabilistic treatment of overow in an event tree. This approach can be used to analyze an existing timing plan or to design a timing plan that satises a certain clearance reliability requirement. Some numerical results are included to demonstrate this approach.

13

Conference Reports

by Daniel Zeng IEEE 2006 Conference Report by Daniel Zeng, Hsinchun Chen and Fei-Yue Wang The IEEE International Conference on Intelligence and Security Informatics (IEEE ISI 2006) was held May 23-24, 2006, in San Diego, California. IEEE ISI 2006 was sponsored by the ITS Society and was jointly hosted by the University of CaliforniaIrvine, the University of Texas at Dallas, and The University of Arizona. The two-day program included a plenary keynote address, a plenary panel discussion session focusing on the perspectives and future research directions of government funding agencies, several invited panel sessions, as well as 69 regular papers and 57 posters. More than 150 researchers, government ocials, and practitioners participated in the conference. Intelligence and security informatics (ISI) can be broadly dened as the study of the development and use of advanced information technologies and systems for national and international security-related applications, through an integrated technological, organizational, and policy-based approach. The rst two symposia on ISI (ISI 2003, ISI 2004) were held in Tucson, Arizona; the third (IEEE ISI 2005) in Atlanta, Georgia. IEEE ISI 2006 continued this conference series, providing a stimulating intellectual forum for discussion among previously disparate communities: academic researchers (in information technologies, computer science, critical infrastructures including transportation systems, public policy, and social and behavioral studies), local, state, and federal law enforcement and intelligence experts, and information technology industry consultants and practitioners. The following conference awards were conveyed at the IEEE ISI 2006: IEEE ISI 2006 RESEARCH LEADERSHIP AWARD IN INTELLIGENCE AND SECURITY INFORMATICS by The IEEE Intelligent Transportation Systems Society Technical Committee on Intelligence and Security Informatics in Transportation Systems and The IEEE Systems, Man, and Cybernetics Society Technical Committee on Homeland Security Recipient: Dr. John R. Phillips, Chief Scientist, Central Intelligence Agency (CIA)

IEEE ISI 2006 BEST PAPER AWARD Paper Title: A First Look at Domestic and International Global Terrorism Events, 1970-1997 Authors: Laura Dugan, Gary LaFree, Heather Fogg UNIVERSITY OF MARYLAND

14

 IEEE ISI 2006 BEST PAPER HONORABLE MENTIONS

1. Paper Title: Finding Hidden Group Structure in a Stream of Communications Authors: Je Baumes, Mark Goldberg, Mykola Hayvanovych, Malik Magdon-Ismail, William Wallace, Mohammed Zaki RENSSELAER POLYTECHNIC INSTITUTE

2. Paper Title: Cost-Sensitive Access Control for Illegitimate Condential Access by Insiders Authors: Young-Woo Seo, Katia Sycara CARNEGIE MELLON UNIVERSITY

15

Technical Contributions

by Brian Park Byungkyu Brian Park, University of Virginia, USA. This technical contributions section introduces state-of-the-art research and/or state-of-the-practice applications in the area of intelligent transportation systems (ITS). We are especially interested in receiving contributions from non-ITSS members and promoting interactions among sister societies within IEEE and other organizations advocating the ITS. Original contributions, excerpts from IEEE Journals (with permission) and reprints from recent IEEE conferences (except those hosted by ITSS) can be submitted for consideration for publication in this section. Please send your contributions to me at bpark@virginia.edu.

16

Distributing the Cost of Securing a Transportation Infrastructure 1

Sudarshan S. Chawathe, Computer Science Department University of Maine Orono, Maine 04469, USA E-mail: chaw@cs.umaine.edu http://www.cs.umaine.edu/ chaw/ 1 Introduction ecuring the transportation infrastructure to protect it from hostile agents is an increasingly important task that is the subject of much recent work. No matter what strategy one uses for improving the security of the infrastructure, there are substantial and varied costs related to personnel, equipment, impediments to trac, loss of revenue due to slow or rerouted trac, etc. Once such costs have been determined, an important question is how they are borne by the typically numerous parties involved in the infrastructure. Indeed, lack of agreement on such division of costs has been the topic of much political controversy and threatens to derail initiatives for securing the transportation infrastructure. For example, consider a proposal to implement additional checkpoints on some highways of a regional network and to disallow hazardous-material carriers on certain routes. Such actions incur the obvious direct costs associated with setting up checkpoints and enforcing new regulations. However, there are also indirect costs such as noise, pollution, and danger of rerouted hazardous-material carriers. Further, additional checkpoints may lead to congestion which may result in loss of business in the aected areas. It is not surprising, then, that even modest proposals that aect the functioning of the transportation infrastructure often elicit strong protests. Given the increased awareness of security, it is likely that major disagreement is not about whether additional security is necessary, but rather about who should shoulder what portion of its cost. In this paper, we present a model of the costs and benets of improvements to transportation-infrastructure security. Using this model, we can determine a cost distribution that has a sound basis and is thus likely to be considered fair by the concerned parties.

2 Model We model a network of transportation links using a graph whose vertices represent locations of interest, or simply intersections, and whose edges represent links. A link (i, j) between locations i and j permits, in general, travel both from i to j as well as from j to i. However, travel in these two directions is modeled using separate parameters, as described below. Figure 1 suggests a small transportation network modeled in this manner. One-way links do not pose a problem to this model. The disallowed direction may simply be assigned a very low probability of traversal. A nonzero probability of traversal in the disallowed direction of a one-way link, such as a one-way street, may often model the link more accurately than a zero probability because, for example, it is quite likely that agents perpetrating an attack do not hold trac regulations in high regard. Threats may originate at any vertex of the graph representing the transportation network. Threats that originate at locations on a link between two vertices, such as a rail link between two stations, are modeled by inserting an additional vertex between those vertices. In other words, locations at which threats originate are, by denition, locations of interest and are therefore modeled using vertices in the graph. We use two parameters to describe threats originating at a vertex i: a magnitude mi and a frequency fi . Intuitively, the magnitude represents the seriousness of a threat, modeling quantities such as the amount of damage and the aected area. The frequency indicates how often a threat is likely to materialize at i. Our
1 This work was supported in part by the U.S. National Science Foundation with grants IIS-9984296, IIS-0081860, and CNS-0426683.

17

Figure 1: A network of transportation links used by the running example methods do not depend on any particular interpretation of these parameters. Further, our work uses these parameters only in conjunction, as the product mi fi , which represents the expected magnitude, per unit time, of a threat originating at vertex i. Determining appropriate values for mi , fi , and the other parameters of our model is an important problem, but not one that is the focus of this paper. Our focus is on how such data, once obtained, may be used to allocate system-wide costs of securing the transportation network. When a threat appears at a location in the network, it may either be executed at that location or be transported to another location using one of the links. A threat may appear at a location either because it originates at that location, as described earlier, or because it traversed a link from another location to that location. We use ei to denote the probability that a threat appearing at a location is executed at that location. More precisely, the probability of execution ei is the conditional probability of a threat executing at i given that it has appeared at i. Similarly, we use tij to denote the conditional probability of traversal from i to j, given a threat appearing at i. In general, tij and tji are not the same. Let us use nbd(i) to denote the neighborhood of i, i.e., the set of vertices that are the targets of links from i. Since ei and tij represent probabilities we must have the following for every vertex i in the graph: ei + jnbd(i) tij 1. However, the terms on the left-hand side of this inequality need not sum to one because the threat may disappear (e.g., a planned attack may be abandoned). We denote the cost of improving the security on link (i, j) by cij . The resulting (lower) link traversal probability is denoted by tij . Finally, we dene sij = 1 tij and sij = 1 tij for notational convenience.

3 Vulnerabilities The model of Section 2 allows us to quantify the vulnerability of each location of interest. Intuitively, the vulnerability of a location of interest is the expected magnitude of a threat executed at that location. In order to keep the calculations simple, we henceforth assume that a threat is executed at its intended target (location of interest) as soon as it arrives at that target. That is, we may restrict our attention to traversals that do not visit any vertex more than once (acyclic paths). It is conceptually easy to do away with this assumption by using the steady-state distribution obtained by interpreting the graph of Section 2 as a Markov process [1]. Figure 1 suggests a small transportation network that we shall use as a running example. The four locations of interest are identied by the numbers within the circles: V = {1, 2, 3, 4}. The ve links are identied by the letters above each link: L = {A, B, C, D, E}. The magnitude and frequency of a threat originating at vertex 1 are 1024 and 4, respectively, so that f1 m1 = 4096. (The numbers are chosen to minimize fractions in the calculations that follow but nothing in our model depends on such carefully chosen values.) For all other vertices in this example, fi mi = 0. That is, a nontrivial threat originates only at vertex 1. We use an execution probability of 1/4 at each vertex. That is, ei = 1/4 for all i [1, 4]. Traversal probabilities for all links (in either direction) are uniformly 1/4. That is, for all i, j [1, 4], i = j, we have tij = tji = 1/4 (and thus sij = sji = 3/4). We may verify that these values satisfy ei + jnbd(i) tij 1 for all vertices i in our example. By a slight abuse of notation, we shall use the link identiers, such as A and B, to denote both the links themselves and traversals of those links. More precisely, given a link X = (i, j) with i < j, a traversal from i to j is denoted by X while a traversal from j to i is denoted by X . Paths are denoted by concatenating these labels for the traversals, in sequence. Thus, given Figure 1, AD denotes a path from vertex 1 to vertex 18

Improved set S , {E} {A}, {A, E} {B}, {B, E} {C}, {C, E} {D}, {D, E} {A, B}, {A, B, E} {A, C}, {A, C, E} {A, D}, {A, D, E} {B, C}, {B, C, E} {B, D}, {B, D, E} {C, D}, {C, D, E} {A, B, C}, {A, B, C, E} {A, B, D}, {A, B, D, E} {A, C, D}, {A, C, D, E} {B, C, D}, {B, C, D, E} {A, B, C, D}, {A, B, C, D, E}

Vulnerability v3 (S) 1360 1288 1288 904 1192 1204 820 1156 820 1156 708 722 1114 666 666 617

Table 1: Vulnerability of vertex 3 of Figure 1 for dierent sets of improved links, based on the discussion in Section 3.

3 via vertex 2, while A CE denotes a path from vertex 2 to vertex 4 via vertices 1 and 3. Further, we use X to denote a non-traversal from i to j, and similarly X to denote a non-traversal from j to i. Let us now calculate the vulnerability of vertex 3. Since there is only one origin of threats (vertex 1) in our example, the vulnerability of any other vertex in our example depends only on the paths leading to that vertex from vertex 1. A threat from vertex 1 may arrive at vertex 3 either directly, using link C, or via vertex 2, by using either of links A and B followed by link D. Therefore, we may calculate the probability of a threat from vertex 1 arriving at vertex 3 as follows. P (((A or B) and D) or C) = 1 P ((((A B) D) C) = 1 P (C)(1 (1 P (A)P (B))P (D))

Using our notation for the traversal probabilities from Section 2, we have the following expression for the vulnerability of vertex 3: v3 = m1 f1 (1 sC (1 (1 sA sB )tD )) (1) Substituting the parameter values from our running example yields v3 = 1024 4 (1 (1/4)(1 (1 (3/4)(3/4))(1/4)) = 1360 The interpretation of this number depends on the interpretation used in assigning values to the parameters m1 and f1 . For instance, if m1 represents the number of persons aected by a bomb and if f1 represents the number of times a year such a bomb is expected to originate at site 1, then 1360 is the expected number of people aected yearly by the bomb, given our model. However, our work is equally applicable to any other interpretation that ts our model described in Section 2. The above calculations are based on the state of the transportation network before any security improvements are made, i.e., the base state. In general, the vulnerability vi of vertex i depends on the set of links on which security improvements have been made. Therefore, we use vi (S) to denote the vulnerability of i given a set S of improved links. The left-hand side of Equation 1 is expressed as v3 () in this notation, which we shall henceforth use. Continuing our running example (Figure 1), suppose that improving the security of a link halves the probability of traversal. Recall that we have traversal probabilities tij = 1/4 for all i, j [1, 4], i = j. Using the notation of Section 2, we have, for all i, j [1, 4], i = j, tij = 1/8 and sij = 7/8. We may calculate v3 (S) for all S L using Equation 1 by substituting sA , sB , sC , and tD with, respectively, sA , sB , sC , and tD depending on whether A, B, C, and D (respectively) belong to S. For 19

S = {A, C}, substituting sA for sA and sC for sC yields the following: v3 ({A, C}) = m1 f1 (1 sC (1 (1 sA sB )tD )) = 1024 4 (1 (7/8)(1 (7/8)(3/4))(1/4)) = 820

The result of such calculations for all subsets S in our running example summarized in Table 1. There is no origin of a threat at vertex 4 in our example. Therefore, as indicated by Equation 1, link E is immaterial for calculating the vulnerability of vertex 3. This fact explains the two sets in the rst column of each row of Table 1. The benet of improving the security of a link is, in general, dierent for each the vertex. A fair scheme for distributing the cost of improving links over the vertices in the network reects these diering benets using the above framework. We defer the details of the distribution scheme to a forthcoming paper.

4 Related Work While our work abstracts away some of the details of how various model parameters are determined, such determination is nevertheless very important and forms the basis of our model by providing the important parameters. For example, Shao presents a method for allocating redundant resources for disaster-recovery planning [2]. Similarly, recent work by Park et al. may be used to determine the vulnerabilities of nodes in a computer-network infrastructure [3]. Sinai discusses how work in the social and behavioral sciences may be applied to model and assess threats of terrorism [4]. Such work is key to determining the parameters, such as threat magnitude and frequency, used by our model in this paper. Information resources such as the MIPT system described by Ellis provide a means for eciently accessing a variety of information necessary for threat assessment [5]. A similar eort in the context of the spread of infectious diseases is described by Zeng et al. [6]. Park and Ho describe a method for addressing insider threats [7], which are an important category of threats in any environment, including the one in this paper. Lin et al.s user-acceptance study based on the COPLINK system [8] highlights the importance of solutions that make a compelling case for acceptance, which is also one of the motivations of our work in this paper. Xu et al. present a method to analyze and visualize criminal networks, focusing on dynamics [9]. Introducing the dynamic element into our model in this paper is an interesting avenue for further work.

References
[1] Breiman, L.: Probability. Society for Industrial and Applied Mathematics (1992) [2] Shao, B.B.M.: Optimal redundancy allocation for disaster recovery planning in the network economy. In: Proceedings of the Symposium on Intelligence and Security Informatics (ISI). Volume 3073 of Lecture Notes in Computer Science (LNCS)., Tucson, Arizona (2004) 484491 [3] Park, E., Seo, J.T., Im, E.G., Lee, C.W.: Vulnerability analysis and evaluation within an intranet. In: Proceedings of the Symposium on Intelligence and Security Informatics (ISI). Volume 3073 of Lecture Notes in Computer Science (LNCS)., Tucson, Arizona (2004) 514515 [4] Sinai, J.: Utilizing the social and behavioral sciences to assess, model, forecast and preemptively respond to terrorism. In: Proceedings of the Symposium on Intelligence and Security Informatics (ISI). Volume 3073 of Lecture Notes in Computer Science (LNCS)., Tucson, Arizona (2004) 531533 [5] Ellis III, J.O.: MIPT: Sharing terrorism information resources. In: Proceedings of the Symposium on Intelligence and Security Informatics (ISI). Volume 3073 of Lecture Notes in Computer Science (LNCS)., Tucson, Arizona (2004) 520525 [6] Zeng, D., Chen, H., Tseng, C., Larson, C., Eidson, M., Gotham, I., Lynch, C., Ascher, M.: West nile virus and botulism portal: A case study in infectious disease informatics. In: Proceedings of the Symposium on Intelligence and Security Informatics (ISI). Volume 3073 of Lecture Notes in Computer Science (LNCS)., Tucson, Arizona (2004) 2841 20

[7] Park, J.S., Ho, S.M.: Composite role-based monitoring (CRBM) for countering insider threats. In: Proceedings of the Symposium on Intelligence and Security Informatics (ISI). Volume 3073 of Lecture Notes in Computer Science (LNCS)., Tucson, Arizona (2004) 201213 [8] Lin, C., Hu, P.J., Chen, H., Schroeder, J.: Technology implementation management in law enforcement: COPLINK system usability and user acceptance evaluations. In: Proceedings of the National Conference on Digital Government Research, Boston, Massachusetts (2003) [9] Xu, J., Marshall, B., Kaza, S., Chen, H.: Analyzing and visualizing criminal network dynamics: A case study. In: Proceedings of the Symposium on Intelligence and Security Informatics (ISI). Volume 3073 of Lecture Notes in Computer Science (LNCS)., Tucson, Arizona (2004) 359377

21

Driving into the Future with ITS

by Fei-Yue Wang

Driving into the future with ITS 2

Fei-Yue Wang, University of Arizona and Chinese Academy of Sciences E-mail:feiyue@sie.arizona.edu

Over the past two decades, intelligent transportation systems have integrated a broad range of

AI-based technologies into both the transportation infrastructure and vehicles themselves. Although the future of ITS is promising, the eld is anything but futuristic. Various ITS products and services are already at work throughout the world, signicantly improving transportation safety, mobility, and productivity [1]. Still, the wide and deep application of intelligent systems in transportation represents a true revolution in the way we think about mobility. As new concepts, methods, tools, and devices continue to emerge in communication, information, automation, and elec- Traveling in intelligent spaces tronics, ITS will provide an increasingly important and exciting platform for AI research and developIntelligent spaces are environments that ment, especially in applied intelligent systems. can monitor whats happening in them, communicate with their inhabitants and neighborhoods, and act on the basis of deciSmart cars on smart roads sions they make. The MIT Oxygen Project http://www.oxygen.lcs.mit.edu and Philips HomeCars will be more than computers with wheels. Lab http://www.research.philips.com/technologies/ They already include many dierent kinds of sensors, misc/homelab/ are just two cases of research to imCPUs, software systems, and communication capac- plement ambient intelligence with human- centered ities[2]. In the next few years, active in- and out- ubiquitous or pervasive computing. vehicle environment sensing will become standard Embedding such intelligence in an automobile features, enabling intelligent driver and passenger as- would be a natural next step for intelligent vehicles. sistance at various levels for driving safety, eciency, Current in- vehicle applications of GPS, ad hoc netand comfort. works, and sensor networks have already led the way. Although it will be dicult to make signicant Future cars will behave more like intelligent agents changes in road infrastructures in the near future, traveling in intelligent spaces; trac control at interseveral technologies are available to give vehicles ad- sections could employ cooperative- driving technoloditional information for safer operations and bet- gies implemented over ad hoc networks, instead of ter performance. Examples include remotely con- relying on trac lights. Such technologies aim for trollable, locally activated variable- message systems; roads with zero fatalities.
2 This

RFID-type roadside sensors; and embedded barcodelike road marks. The quest for smart cars on smart roads provides a challenging but ideal platform for R&D in various AI-based methods and techniques. Some of these areas are well established, such as computer vision, pattern recognition, computational intelligence, machine learning, data mining, and intelligent control. Others are newer, such as applied cognition, advanced message display and user interface design, monitoring driving behaviors, and predicting drivers physical and mental states.

article was written for AI 50th Anniversary

22

Incorporating intelligent-space technology into transportation can help lay the foundation for a connected lifestyle where vehicles, roads, homes, oces, and services can all exchange information. Clearly, such large-scale mobility will pose signicant R&D challenges with respect to personalization, adaptation, networking, and security.

Agent-based control Trac control and vehicle monitoring were among the rst applications of agent technology[3]. As connectivity becomes ubiquitous, agent-based control offers an ideal approach to transportation management, addressing its geographically distributed and alternately busy-idle operating characteristics. Intelligent, autonomous agents will traverse trac control centers, road intersections, highways, streets, vehicles, houses, oces, and so on. They will use the Internet as well as wireless and ad hoc networks to collect the right information at the right times and to make smart decisions. Agent-based control essentially transforms centralized operational algorithms to distributed operational agents, letting networked transportation systems operate on a management-on-demand or service-on-demand basis. This approach can provide a cheap, reliable, and exible way to control trafc and transportation systems in connected environments. It can also improve ITS performance at low cost while reducing the modications required for system upgrades. To implement agent-based ITS control, we must develop a comprehensive operational framework based on the emerging Internet gateway infrastructure. Such a framework would connect networked trac devices, letting them seamlessly communicate with each other and receive a variety of trac-related services from providers. To this end, we must address various issues related to the theoretical foundation and software and hardware requirements for applying agent- based technologies to transportation devices and systems. Clearly, distributed AI methods will be essential in those eorts.

computer simulations to computational experiments. The ATS concept is derived from articial societies, proposed by Rand researchers to study the social effects of information infrastructures[4]. Its an idea perfectly suited to complex transportation problems when testing and validating with real systems is either economically or legally prohibitive. An agent-based ATS is a large, integrated transportation model including analytical descriptions of trac ow models as well as rule-based human and vehicle behaviors and social and natural events. An ATS allows transportation activities to grow in a bottom-up fashion, providing an alternative to real systems for experimental investigations and thus elevating simulations to experiments[5]. New computing techniques, such as peer-to-peer and grid computing, could support an open ATS on the Internet for modeling transportation operations in articial cities. Researchers could test and evaluate dierent trac management systems in a way similar to playing games on the Internet. A transportation operation center could also run both real and articial transportation systems in parallel. In addition to testing and experimenting, parallel execution implementations could support system training and learning; real-time hardware- inthe-loop, rolling-horizon optimizations; and adaptive control for transportation problems. They could even act as a backup mechanism. We can expect the sciences of the articial, introduced by Nobel laureate and AI founder Herbert A. Simon,[6] to play a signicant role in future ITS research, especially in developing sustainable transportation systems. ood transportation systems are fundamental to eective societies. Many existing transportation problems still call for AI techniques to achieve costeective solutions, and emerging issues will depend even more on AI solutions. From highways to railroads, port automation to free space ight, and national security to new weaponry, AI will play a critical role in our drive to future intelligent transportation systems.

References Articial transportation systems Computer simulations have always played a signicant role in transportation research. Analytical models alone cant handle the complexities in transportation operations, especially of human activities. Articial transportation systems go a step beyond 23 1. S. Tang, F.-Y. Wang, and Q. Miao, ITSC 05: Current Issues and Research Trends, IEEE Intelligent Systems, vol. 21, no. 2, 2006, pp. 96102. 2. L. Li et al., IVS 05: New Developments and

Research Trends for Intelligent Vehicles, IEEE Intelligent Systems, vol. 20, no. 4, 2005, pp. 1014. 3. F.-Y. Wang, Agent-Based Control for Networked Trac Management Systems, IEEE Intelligent Systems, vol. 20, no. 5, 2005, pp. 9296. 4. C.H. Builder and S.C. Bankes, Articial Societies: A Concept for Basic Research on the

Societal Impacts of Information Technology, Rand report P-7740, 1991.

5. F.-Y. Wang and S. Tang, Articial Societies for Integrated and Sustainable Development of Metropolitan Systems, IEEE Intelligent Systems, vol. 19, no. 4, 2004, pp. 8287.

6. H.A. Simon, The Sciences of the Articial, 3rd ed., MIT Press, 1996.

24

Research Programs
Research Review
by Angelos Amditis Angelos Amditis, Institute Of Communication and Computer Systems, Greece IEEE ITSS Newsletter is happy to introduce starting from this issue a special section focusing on research activities worldwide. In this volume of the IEEE ITSS Newsletter the focus is on the European activities on Active and Preventive Safety and Human Machine Interaction, namely the co-funded by the 6th European Research Framework Programme Integrated Projects PReVENT and AIDE.. Activities on Trac Management, Rescue and Services and Cooperative Systems will follow in successive Volumes of the Newsletter where anyone interested is welcome to contribute. If you are interested in publishing material to the research section please send a short one page text with focus on the overview of research results and activities world wide. Please, send you contributions for future newsletters to a.amditis@iccs.gr.

25

Review of the EU projects PReVENT and AIDE

Introduction Road safety is a major concern for all of us. Although things have improved in recent years, the number of road fatalities is still unacceptably high in the European Union and all over the world. In 2000, road accidents killed over 40000 people in the European Union and injured more than 1.7 million. Trying to address this huge problem, European Commission, between other things, launched eSafety, which is a joint initiative of the Research Community with the industry and other stakeholders aiming to accelerate the development, deployment and use of Intelligent Integrated Safety Systems, that use information and communication technologies in intelligent solutions, in order to increase road safety and reduce the number of accidents on Europes roads. For more information you can visit: http://www.escope.info/ Building the Active Safety Systems of the future PReVENT (EC, 6th FW Integrated Project, IST) envisions the early availability of advanced, next generation preventive and active safety applications and enabling technologies and an accelerated deployment on European roads. PReVENT consists of a number of subprojects in complementary function elds: Safe Speed and Safe Following These functions help drivers keep or choose a speed or inter-vehicle distance, allowing them to safely cope with the road situation they will meet in the following seconds. The approach is mostly autonomous. Lateral Support This eld deals with autonomous applications focusing on the lateral areas of a vehicle to help drivers keep their vehicle at the safest position in the lane, as well as warn them if the vehicle is about to run o the road. Intersection Safety This function eld covers the investigation of autonomous and cooperative approaches to safety applications dedicated at approaching or passing intersections. Vulnerable Road Users and collision Mitigation Collision mitigation and pre-crash protection systems focus on reduction of injuries and fatalities in case of unavoidable crashes (in particular during the last 2-3 seconds before the impact). Collision mitigation by braking signicantly reduces kinetic energy of impact, thereby greatly reducing crash severity. Cross-functional Activities An additional cross-functional eld covering methodologies, common architectures, liability issues, and technology or standardization oriented activities safeguards a common approach. More information on PReVENT can be found at http://www.prevent-ip.org. The INSAFES Subproject Most of the functions described above are being developed and tested within this year- nishing date January 2007 - , therefore I would like to point out a cross-functional activity which integrates dierent function elds and will continue until the beginning of 2008. This cross-functional activity is one of the PReVENTs subprojects called INSAFES and its general goal is to improve the functionality and reliability of applications developed within PREVENT and to advance from stand-alone safety applications, targeting one specic function each, to an integrated system, covering a vast range of applications. INSAFES focuses on the full coverage of the surrounding of a vehicle, in order to warn the driver, intervene, or mitigate the eects of an accident. INSAFES addresses the proper use and interpretation of all the information available from sensors or functions that are being developed in PReVENT, and the subsequent situation and risk assessment. INSAFES functions include:

26

 All around collision warning Integrated longitudinal support - including collision mitigation, safe speed, and hazard detection increasing the Safety margin Optimal Maneuver suggestion Lane Keeping support with lane oset adapted to vehicles in adjacent lanes Lane change aid with haptic feedback and correction Low speed obstacle warning and start-inhibit Enhanced curve speed warning A sub-set of the functions co-exist in the vehicle, thus, coordination is needed in order to support the driver in the optimal sense. This coordination of functions is performed in INSAFES in accordance to the work of the AIDE Integrated Project which focuses in turn on the design and development of adaptive and integrated HMI solution for the future vehicles.

Figure 1: PreVENT applications

27

The AIDE Integrated Project: Building the future automotive HMI solutions The general objective of the AIDE IP (EC, 6th FW Integrated Project, IST) is to generate the knowledge and develop the methodologies and human machine interface technologies required for safe and ecient integration of multiple driver assistance and information functions into the driving environment. Specically, the goal of the IP is to design, develop and validate a generic Adaptive Integrated Driver-vehicle InterfacE (AIDE) that... maximizes the eciency of individual and combined advanced driver assistance systems by means of innovative, integrated and adaptive, human-machine interface concepts that prevent negative behavioral eects (e.g. under-load, over-reliance and safety margin compensation) and maximizes positive eects (e.g. enhanced situational awareness), thereby enhancing the safety benets of these systems. AIDE should demonstrate signicantly enhanced safety benets compared to existing solutions. reduces the level of workload and distraction related to the interaction with individual and combined invehicle information and nomad devices, thereby reducing the number of road accidents. AIDE should demonstrate a signicant reduction in the imposed workload and distraction compared to existing solutions. enables the potential benets of new in-vehicle technologies and nomad devices in terms of mobility and comfort, without compromising safety. AIDE should demonstrate that the benets of new in-vehicle technologies could be enjoyed without increased accidents risk

The work in the AIDE IP is organized in four sub-projects (SPs), which are major blocks of work in the IP. Each SP is further divided into work packages (WPs) which, in turn, consist of a number of tasks. Each of the sub-projects 1-3 deals with one of the main aspects described in the Objective- section, i.e. behavioral research, methodological- and technological development respectively, where SP3 is the largest in terms of resources allocated. The fourth sub-project gathers a number of horizontal and common activities, including the Consortium Management and dissemination and deployment activities. The AIDE sub-projects are: Sub-project 1: Behavioral Eects and Driver-Vehicle-Environment Modeling Sub-project 2: Evaluation and Assessment Methodology Sub-project 3: Design and Development of an Adaptive Integrated Driver-vehicle Interface Sub-project 4: Horizontal Activities

28

Figure 2: AIDE proposes a unied HMI solution for integrating ADAS and IVIS In order to reach these objectives, three sub-goals have been dened: Development of a model for prediction of behavioral eects of driver assistance and information systems. This model will be the basis for the design of the adaptive integrated driver-vehicle interface. Development of a generic, industrially applicable, methodology for the evaluation of road vehicle human-machine interfaces with respect to safety. This methodology will be used for verifying the quantied goals stated above. Design, development and evaluation of three prototype vehicles, one city car, one luxury car and one heavy truck, with the adaptive integrated driver-vehicle interface implemented. AIDE project started in March 2004 and its duration is four years. More information can be found at http://www.aide-eu.org. Conclusions A lot of eort is spent for the development of new Active Safety systems and interaction strategies that are expected to address part of the problems that lead to the unacceptable high number of trac accidents and casualties. The concept that prevailed in EC research the last years was to involve all relevant stakeholders in large Integrated projects able to gather the needed resources and consensus in order to address important research issues. Examples of this policy are also AIDE and PReVENT that were presented in this bulletin. As these projects have just passed their mid life it is very interesting and important to see their results demonstrated in a wider audience. That is why in September 2007, a common Safety Application Road show will be organized by PReVENT, involving all project participants to exhibit the project results and create awareness as an important milestone for the preparation of the European market. AIDE will be also present at this event. References and links http://www.prevent-ip.org http://www.aide-eu.org http://www.cordis.lu 29

Announcements

Baher Abdulhai, Ph.D., Conference Chair Canada Research Chair in Intelligent Transportation Systems (ITS) Director, Toronto Intelligent Transportation Systems Centre Department of Civil Engineering, University of Toronto

Toronto Ready for IEEE ITSC 2006

Mark your calendar and book your trip to the 2006 IEEE Intelligent Transportation Systems Conference in Toronto starting th September 17 , 2006. Register online and book your hotel at www.itsc2006.org. The organizing committee is working around the clock preparing for the busiest ever IEEE ITS Conference, to take place in the heart of Toronto, arguably one of the early birth places of ITS.

The record high submission of 430 papers sets the stage for quality presentations on the latest in travel and traffic management, ITS modeling and analysis, public transportation management, advanced vehicle safety systems and intelligent vehicles research. In addition, we plan on having 12 special sessions on a variety of topics, such as cybercars and microscopic travel flow models. Complemented by cutting-edge short courses and tutorials, the conference will be as exciting as Toronto itself. ITSC 2006 brings together top scientists, practitioners, and administrators from all over the world to share their knowledge of the latest developments in the field.
Toronto is the largest city in Canada and the fifth largest city in North America. Toronto is vibrant economic and cultural hub that is commonly referred to as the worlds most cosmopolitan city. From Little Italy to Greektown, Chinatown to Little India, the waterfront and the Fashion district, Toronto offers everything you could possibly think of, and more. The ' Megacity' a is flourishing example of multiculturalism. Torontonians take pride in their diverse city, and celebrate their cultural differences under one big red maple leaf. We are honored to have you with us, teach us, learn from us, and have fun with us. Join us for the gala dinner in the world-famous CN Tower, whose award winning fine dining restaurant is located 351 m high and offers guests a rotating 360 degree view of the city. Feel free to have an extended stay in Toronto and visit attractions like the World-famous Niagara Falls and the Toronto International Film Festival. On behalf of the organizing committee and conference sponsors, we look forward to having you in Toronto!

30

ITS CENTRE AND TESTBED

The IEEE Intelligent Transportation Sy stems Society inv ites y to the ou 9th Annual International IEEE ITS Conf erence hosted byThe Univ ersityofToronto Civ Engineering Department il and the IEEE Toronto Section

IEEE ITSC 2006

September 17- 2006 20, Toronto Marriott Downtown Eaton Centre Toronto, Canada www. itsc2006. org

W ELCOME TO ITSC 2006!

Intelligent Transportation Sy stems ( , regardless ofthe manydef ITS) initions, hav obj e ectiv that are univ es ersallythe same. ITS encompass a broad range ofwireless and wireline communicationsbased inf ormation, control and electronics technologies to help monitor and enhance sy stem wide perf ormance, reduce congestion, prov alternate routes to ide trav elers, enhance productiv , and ultimatelysav liv time and money ity e es, . W ell bef the adv ofthe trade name, ITS was born in sev ore ent eral cities around the word since 1960 and Toronto is s, proudlyone ofthem. ITS started to cry stalliz and mature since the early1990 Although ITS started as a technical e s. approach only theyhav ev ed to cov a wide spectrum ofsustainability env , e olv er , ironmental and economic issues.ITSC 2006 will f ocus on " stem Intelligence in ITS" while continuing the tradition ofpreceding ITSC conf Sy , erences, leading adv ances in basic research on technology related to intelligent transport sy stems, ITS applications and interf aces between ITS technologyand the society . ITSC 2006 ofers participants f f rom the public sector ( g.national gov e. ernments, local authorities, international organiz ations, planners, public transport authorities, academic institutions) the priv sector ( g.f , ate e. reight and transport operators, public transport operators, car manuf acturers, serv prov ice iders, telecom operators, sy stem integrators, f owners, road leet operators, motoring organiz ations)and all ITS stak eholders a number ofpresentations and discussions with international ex perts on the latest dev elopments in the f and up- date technologies. The conf ield toerence will bring together top scientists, industrial engineers, administration and the R&D communityf rom all ov the world. er Toronto is the largest cityin Canada and the fth largest cityin North America.Toronto is v if ibrant economic and cultural hub erred to as the world most cosmopolitan city From Little Italyto Greek s . town, Chinatown to Little India, that is commonlyref the waterf ront and the Fashion district, Toronto ofers ev thing y could possiblythinkof and more. f ery ou , The ' Megacity is a ' f lourishing ex ample ofmulticulturalism.Torontonians tak pride in their div e erse city and celebrate their cultural diferences , f under one big red maple leaf Come j us, teach us, learn f . oin rom us, and hav f with us. J us f the gala dinner in the e un oin or world-amous CN Tower, whose award winning f dining restaurant is located 351 m high and ofers guests a rotating 360 f ine f degree v iew ofthe city Feel f to hav an ex . ree e tended stayin Toronto and v other attractions lik Niagara Falls and the isit e Toronto International Film Festiv Enj ! al. oy

31

32

CALL FOR PAPERS

MESA06 ---The 2nd IEEE/ASME International Conference
on Mechatronic and Embedded Systems and Applications Beijing, China on August 13-16, 2006
Advisory Committee Jorge Angeles, McGill University, Canada David M. Auslander, U. of California, Berkeley, USA Tianyou Chai, Northeast University, China Krishna C. Gupta, U. of Illinois at Chicago, USA Ren C. Luo, National Chung Cheng University, China Michael McCarthy, U. of California, Irvine, USA Bahram Ravani, U. of California, Davis, USA T. J. Tarn, Washington University, USA Masayoshi Tomizuka, U. of California, Berkeley, USA Youlun Xiong, Huazhong U. of Sci and Tech, China General Chair Feiyue Wang, U. of Arizona and Chinese Academy of Sciences, USA General Co-Chairs Nanning Zheng, Xian Jiaotong University, China Dongming Guo, Dalian U. of Technology, China Program Chair Harry H. Cheng, U. of California, Davis, USA Program Co-Chairs Ying Chen, Hangzhou Dianzi University, China Hanqi Zhuang, Florida Atlantic University, USA S. Felix Wu, U. of California, Davis, USA Dalei Guo, Chinese Academy of Sciences, China Yanqing Guo, University of Arizona, USA Publicity Chairs Daniel Zeng, University of Arizona, USA Huayong Yang, Zhejiang University, China Q. Jeffrey Ge, State University of New York, USA Industrial Liaison Chairs Frederick M. Proctor, National Institute of Standards and Technology, USA Zhilie Chen, Shenzhen Evoc Intelligent Technology Co.,Ltd, China Special Session Chairs Lefei Li, University of Arizona, USA Xudong Hu, Zhejiang Sci-Tech University, China Workshop and Tutorial Chairs Jian S. Dai, University of London, UK Bo Chen, University of California, Davis, USA Awards Committee Chairs Peihua Gu, Shantou University, China Zuomin Dong, University of Victoria, Canada Du Zhang, California State University, USA Local Organizing Chairs Chunheng Wang, Chinese Academy of Sciences Li Zheng, Tsinghua University, China Huiguang He, Chinese Academy of Sciences Publication Chair Hao Hong, Chinese Academy of Sciences, China Executive Secretariat Contact E-Mail: mesa2006@gmail.com Sponsors IEEE Intelligent Transportation Systems Society ASME Division of Computer and Information in Engineering ASME Division of Design Engineering Chinese Association for Automation Chinese Mechanical Engineering Society Objectives Mechanical and electrical engineering show an increasing integration of mechanics with electronics and information processing. This integration is between the components (hardware) and the information-driven functions (software), resulting in integrated systems called mechatronic systems. The development of mechatronic systems involves finding an optimal balance between the basic mechanical structure, sensor and actuator implementation, automatic digital information processing and overall control for which embedded systems play a key role. The field of embedded system is getting more and more challenging, and issues in development of embedded software are attracting attention of an increasing number of researchers both in industry and academia. The goal of MESA06 is to bring together experts from the fields of mechatronic and embedded systems to disseminate the recent advances made in the area, discuss the future research directions, and exchange application experience with respect to the conference themes. Topics

Mechatronics and robotics Embedded systems infrastructure and theory Sensor and MEMS Networked mechatronic and embedded systems Development, verification, and debug tools for mechatronic and embedded systems Mechatronic and embedded system applications Education in mechatronics and embedded computing

Paper Submission Complete manuscripts in PDF format must be electronically submitted to the conference website http://www.asmemesa.org. Submitted manuscripts should be six (6) pages or less in IEEE twocolumn format, including figures, tables, and references. Important Dates

May 10, 2006 June 20, 2006 July 1, 2006

Full paper, proposal for special session, workshop and tutorial Notification of acceptance Camera ready paper submission

For detailed information, please visit the conference web site at

http://www.asmemesa.org
or https://150.135.155.193/mesa06/

33

Call for Papers

2006 IEEE International Conference on Vehicular Electronics and Safety
Organized by Tongji University Sponsored by the IEEE Intelligent Transportation Systems Society Supported by the Automotive Intelligent Transportation Society of SAE China Shanghai Society of Automotive Engineers
December 13-15, 2006, Shanghai, China
Advisory Committee Co-Chairs Charles Herget IEEE ITS Society Konghui Guo Jilin Univ. , China Guoqing Sun China National Technical Committee of ITS Standardization Nanning Zheng Xian Jiaotong Univ., China Xiaoyu Zhang SAE of China Zhihua Zhong Hunan Univ., China General Chair Gang Wan Tongji Univ. , China gangwan@mail.tongji.edu.cn Associate General Chair Dongyuan Yang Tongji Univ., China Program Chair Feiyue Wang Univ. of Arizona Feiyue@sie.arizona.edu Program Co-Chairs Alberto Broggi Univ. of Parma, Italy broggi@Foresto.ce.unipr.it Henning Wallentowitz RWTH Aachen Univ., Genermy wallentowitz@ika.rwth-aachen.de Wolfhard Lawrenz Univ. of Applied Science Germany Lawrenz@cs-group.ed Minggao Ouyang Qinghua Univ., China Tutorial Chair Li Li Univ. of Arizona forcelee@gmail.com Finance Co-Chair Zhuoping Yu Tongji Univ., China

The International Conference on Vehicular Electronics and Safety (ICVES06) is an annual forum sponsored by the IEEE Intelligent Transportation Systems (ITS) Society. It gathers researchers from industries and universities to discuss research and applications for vehicle electronics, and vehicle safety systems. Papers dealing with all aspects of vehicle electronics and vehicle safety-related intelligent systems are solicited for ICVES06. PROGRAM TOPICS

Active and Passive Safety Systems Telematics Vehicular Power Networks X-By Wire Technology System-On-a-Chip Vehicular Sensor Vehicle Bus Sensor Network Embedded Operation System Electro Magnetic Compatibility Inter-Vehicular Network Vehicle Testing Vehicle Hardware /Software System

Navigation and Localization Systems Vehicular Measurement Technology Vehicular Signal Processing Micro-electromechanical Systems Image Sensor Vehicle/Engine Control Driver Assistance Driving Systems Adaptive Cruise Control Systems Pattern Recognition for Vehicles Human Machine Interaction Diagnostics on Line Virtual/Digital System Others

SPECIAL SESSION ORGANIZATION is encouraged. Organizers should contact Prof. Xin Guan at guan.hsin@ascl.jlu.edu.cn. PAPER SUBMISSION Complete manuscripts in PDF format must be electronically submitted to conference website: https://150.135.155.193/ves06/index.php. Submitted manuscripts should be within six (6) pages in IEEE two-column format including figures, tables and references. A Latex style file and a Microsoft Word template are available from the IEEE website http://www.ieee.org/pubs/transactions/stylesheets.xml. Submission MUST be PDF FORMAT. Please refer to the following websites for the most up-to-date information: https://150.135.155.193/ves06/index.php http://iv.tongji.edu.cn http://www.ieeeves.org http://www.ewh.ieee.org/tc/its/conf.html. IMPORTANT DATES Paper submission deadline-------------August 10, 2006 Notification of acceptance-------------October 10, 2006 Camera-ready copy due---------------- November 10, 2006 CALL FOR DEMONSTRATIONS You can get the information of the conference agenda from Prof. Zhuoping Yu at yuzhuoping@fcv-sh.com

yuzhuoping@fcv-sh.com
Yuetong Lin Indiana State University liny@indstate.edu Publication Chair Tsuneo Takahashi NF company, Japan Special Session Chair Xin Guan Jilin Univ., China Registration Chair Feng Luo Tongji Univ., China luofeng@fcv-sh.com Local Arrangements Chair Liguang Li Tongji Univ. , China Liguang@mail.tongji.edu.cn Student Activity Chair Grey Lai University of Arizona, USA guanpi@gmail.com

34

IEEE Robotics and Automation Society Technical Committee on Intelligent Transportation System
The IEEE Robotics and Automation society a few years ago launched the Technical Committee on ITS; the founding co-chairs were Stefano Stramigioli and Alberto Broggi. As of today this Technical Committee, under the responsibility of Urbano Nunes, Christian Laugier, and Alberto Broggi, is one of the most active ones and in fact won the 2006 RAS most active technical committee Award. Check their web page at http://thth.berkeley.edu/tab-db/ - click on Intelligent Transportation Systems). You can post information, sign up for the mailing list and join this technical committee by sending an e-mail to Urbano Nunes at urbano@deec.uc.pt. The committee is organising special sessions on Cybercars Technology and Trends at IEEE ITSC 2006, Sept 17-20 Toronto, and on Perception and Navigation for Automated Vehicles at IEEE IROS/RSJ 2006, Oct. 9-14 Beijing. For more information contact Urbano Nunes at urbano@deec.uc.pt. The committee is organising a workshop for IEEE/RSJ IROS 2006 (full day workshop), Title: Safe Navigation in Open and Dynamic Environments - Autonomous Systems versus Driving Assistance Systems ( visit: http://isrc.skku.edu/fact2006/iv iros06 ver1.htm. For further information, please contact the organizers. Christian LAUGIER Christian.Laugier@inrialpes.fr; Roland SIEGWART rsiegwart@ethz.ch.

Third DARPA Grand Challenge In October 2005, DARPA organized its 2nd Grand Challenge Desert Classic, in which teams had to complete 132 miles of autonomous driving within 10 hours. The rst price, 2 Million USD was won by a team from Stanford. DARPA has now announced its Third Grand Challenge Urban Challenge, to be held in November 2007. This time teams need to complete 60 miles of autonomous city driving within 6 hours. The challenge includes obeying trac laws, avoiding accidents, nding detours if necessary, etc. The price money is 2,75 Million USD. For more information check http://www.darpa.mil/grandchallenge/index.asp.

35

Intelligent Transport Systems - European & UK Initiatives London, 20th July

This event organised by the European Framework Programme UK National Contact Points for IST and Land Transport aims to provide you with information on the opportunities likely to arise for research in the area of Intelligent Transport Systems (ITS) within Framework Programme 7. Presentations will be given from two of the Directorates General in the European Commission responsible for ITS research, DG Information Society & Media and DG Transport & Energy. Eric Sampson, Head of the Transport and Technology Division within the Department for Transport will provide information on the policy perspective and research priorities in DfT and Phil Pettitt, CEO of innovITS (Knowledge Transfer Network on ITS), will describe the developing strategy for the new UK Innovation Platform on Intelligent Transport Systems and Services. The programme will also include presentations from the UK IST NCP and a previous project participant. The event will take place on Thursday 20th July at the DTI Conference Centre, 1 Victoria Street, London. Registration will begin at 9.30am with the conference starting at 10.00am and nishing at 4.00pm. There will be ample opportunities to network and speak directly with the Commission, DTI and the UK National Contact Point team. To register for this free conference, please download the registration form and programme at the internetsite: http://fp6uk.ost.gov.uk/page.aspx?SP=1121

36

Conferences, Workshops, Symposia

by Massimo Bertozzi and Alessandra Fascioli This section lists upcoming ITS-related conferences, workshops, or exhibits. Contributions are welcome; please send announcements to itsconfs@ce.unipr.it.

7th Short Course on Dynamic Trac Flow Modelling and Control Chania, Crete, Greece July 1721 Intelligent Transport Systems - European & UK Initiatives Event London, UK July 20 2nd Intl. Wks. on Vehicle-to-Vehicle Communications http://www.v2vcom.org San Jose, California, USA July 21 11th Intl. Conf. on Vision In Vehicles http://www.visioninvehicles.org Dublin, Ireland July 2729 2nd Intl. Symposium on Road Safety http://geog.hku.hk/isrs2006 Hong-Kong, China August 5 Wks. on Networking in Public Transport http://www.wnept.org Waterloo, Ontario, Canada August 10 2nd IEEE/ASME Intl. Conf. on Mechatronic and Embedded Systems and Applications http://www.asmemesa.org Beijing, China August 1316 Performance Metrics for Intelligent Systems Workshop http://www.isd.mel.nist.gov/PerMIS 2006 Gaithersburg, MD, USA

August 2123 6th Wks. on Algorithmic Methods and Models for Optimization of Railways http://algo06.inf.ethz.ch/atmos Zurich, Switzerland September 14 Intl. Congress Motor Vehicle & Transportation http://www.mec.upt.ro/mvt2006 Timisoara, Romania November 1517, submission by September 10 IEEE 64th Semiannual Vehicular Conf. (fall) http://www.ieeevtc.org/vtc2006fall Montral, Canada September 25-28 ITS World Congress 2006 http://www.itsworldcongress.com London, UK October 812 4th Intl. Wks. on Intelligent Transportation http://wit.tu-harburg.de Hamburg, Germany March 2021, 2007, submission by November 17 IEEE 65st Semiannual Conf. (spring) Dublin, Ireland April 2325, 2007, submission by September 16 Vehicular Technology Technology

6th Triennial Symposium on Transportation Analysis http://tristan.ep.ch Bentota, Sri-Lanka June 1015, 2007, submission by August 31

37