---

Transportation & Shipping

Applications of AI and Expert Systems to Transportation Problems: Airlines, Airports, Shipping

---

AITopics > Applications / Expert Systems > AI Applications Areas > Transportation & Shipping

Tweet  

"A 2003 concept Ford Taurus blends forward collision radar, low light cameras, blind spot monitoring, lane-departure, and rear-collision warnings with telematics. A phone can block incoming calls if pre-crash sensing and navigational data tells the system the driver is too busy to answer." - Smart Cars

Introductory Readings

Note: see Autonomous Vehciles section for articles about computer-controlled, autonomous land, air and water vehicles]].

Ramp Activity Expert System for Scheduling and Coordination at an Airport. Geun-Sik Jo, Jong-Jin Jung, Ji-Hoon Koo, and Sang-Ho Hyun. AI Magazine 21(4): Winter, 2000, 75-82. "By user-driven modeling for end users and near-optimal knowledge-driven scheduling acquired from human experts, races can produce parking schedules for about 400 daily flights in approximately 20 seconds; human experts normally take 4 to 5 hours to do the same."

Vehicle warning system trialled. By Mark Ward. BBC News (March 17, 2007). "Vehicles may soon be swapping information about road conditions to warn drivers about jams and dangers. A German research project on show at hi-tech trade fair Cebit envisions a peer-to-peer network for vehicles on a road passing data back and forth. Cars or bikes experiencing problems would pass data that would ripple down the chain of vehicles behind them. Information would be conveyed to drivers via a dashboard screen or through a mobile phone headset. Dr Anselm Blocher - a researcher at the German Research Center for Artificial Intelligence who is co-ordinating the project - said the ad hoc communication system could mean that drivers found out about dangers or jams ahead much more quickly than they do now. ... The system was smart enough to recognise how busy a driver was and would adjust warnings to take account of the 'cognitive load' a driver was under, he said. ... The SmartWeb project is being co-ordinated by the German Research Center for Artificial Intelligence but has 16 other partners including BMW, Siemens, Daimler Chrysler, Deutsche Telekom and the European Media Lab."

• Visit the SmartWeb project site.

Honoring Asia's best. By Isabelle Chan. ZDNet Asia (July 6, 2006). "ZDNet Asia also handed out special awards in six categories. We salute the winners of the Project of the Year Awards--their IT departments, initiative and commitment to making their IT project a success. Winning these awards is no mean feat, as the quality of entries was extremely high and the judges had a difficult time picking the winners. The winners are: ... Project of the Year: ... There were several hot favorites, but the winner was MTR's Engineering Works & Traffic Information Management System (ETMS). The Hong Kong rail transportation company developed the system to ensure better utilization of MTR's limited resources--people, tools, workspace and time--during four non-traffic hours of the day. Developed using artificial intelligence technology, the system automates the planning, monitoring, controlling and reviewing of all maintenance and engineering works."

• Project of the Year. By Isabelle Chan. ZDNet Asia (July 6, 2006). "The business challenge was, therefore, to optimize the utilization of MTR's limited resources--people, tools, workspace and time (four non-traffic hours every day)--and yet be able to comply with the statutory and safety regulations. In 2005, MTR embarked on a project called the Engineering Works & Traffic Information Management System (ETMS) which uses artificial intelligence (AI) for planning, scheduling and managing engineering works. ... The project team comprised MTR ITSD in-house staff and a City University of Hong Kong associate professor who specializes in artificial intelligence. MTR ITSD was the project manager of the project, and a pool of users with domain experts provided input to the functions of the system. ... This same AI rule engine is now used by the Immigration Department of Hong Kong for application assessment."
  • Also see this article from the Hong Kong Trade Development Council: MTR Corporation: Safety and efficiency brought about by Artificial Intelligence (June 1, 2006).
• In 2005, this application received the AAAI Award for Innovative Applications of AI: "MTR Corporation for the Hong Kong subway system - Automatic planning and scheduling of maintenance and repair work The Hong Kong MTR metro system carries 2.4 million passengers each weekday, compared with New York’s subway system which carries roughly one-tenth that number daily. Despite the volume of traffic, the Hong Kong subway was punctual more than 99% of the time in 2004. Each night the system is shut down at midnight for only 4 to 5 hours, during which time all necessary maintenance and repair work is performed. The AI based system streamlines scheduling this work -- maximizing the number of jobs done while ensuring operational safety and resource availability."
  • And here's the paper that was presented at the conference: Scheduling Engineering Works for the MTR Corporation in Hong Kong. By Andy Hon Wai Chun, Dennis Wai Ming Yeung, Garbbie Pui Shan Lam, Daniel Lai, Richard Keefe, Jerome Lam, and Helena Chan. 2005. In Proceedings of the Seventeenth Innovative Applications of Artificial Intelligence Conference, 1467 - 1474. Menlo Park, Calif.: AAAI Press. Abstract: "This paper describes a Hong Kong MTR Corporation subway project to enhance and extend the current Web-based Engineering Works and Traffic Information Management System (ETMS) with an intelligent 'AI Engine.' The challenge is to be able to fully and accurately encapsulate all the necessary domain and operation knowledge on subway engineering works and to be able to apply this knowledge in an efficient manner for both validation as well as scheduling. Since engineering works can only be performed a few hours each night, it is crucially important that the 'AI Engine' maximizes the number of jobs done while ensuring operational safety and resource availability. Previously, all constraint/resource checking and scheduling decisions were made manually. The new AI approach streamlines the entire planning, scheduling and rescheduling process and extends the ETMS with intelligent abilities to (1) automatically detect potential conflicts as work requests are entered, (2) check all approved work schedules for any conflicts before execution, (3) generate weekly operational schedules, (4) repair schedules after changes and (5) generate quarterly schedules for planning. The AI Engine uses a rule representation combined with heuristic search and a genetic algorithm for scheduling. An iterative repair algorithm was used for dynamic rescheduling."

Cars that drive themselves en route. By R. Colin Johnson. EE Times Online (March 27, 2006). "Stanford's [Sebastian] Thrun predicts that full autonomy--not just convoy lanes on the freeway--is at least 30 years away. But between then and now will come many milestones, such as autonomous military convoys and a whole raft of convenience and safety features that will slowly bestow various degrees of autonomy onto commercial and consumer vehicles. ... Freescale's [Peter] Schulmeyer sees collision avoidance as a passing goal on the way to full autonomy, with all new innovations in automobiles pointing to increased automation."

Cars soon may 'talk' to roads, each other. By Chris Woodyard. USAToday.com. November 10, 2005. "The demonstration at Honda's test center outside Tokyo previews what is shaping up as the next phase of automotive safety: vehicles that talk to each other and the highway system itself. They silently send or receive warnings from other cars in close proximity. Or they pass information back and forth to sensors along the roadway that become part of a real-time database. They tell of their approach to an intersection, warn about hazards ahead or keep an inattentive driver from running a red light, all with the goal of preventing accidents. Around the world, major automakers from General Motors to BMW see the idea of a transportation system that can communicate as a major safety breakthrough. 'It does seem like it's straight out of a science-fiction movie,' says Robert Strassburger, vice president of vehicle safety for the Alliance of Automobile Manufacturers. 'But it's happening already.' ... Intelligent transportation also offers a lucrative side benefit: the sharing of information that could ease traffic congestion, which wasted an estimated 2.3 billion gallons of gasoline in 2003, according to a Texas Transportation Institute estimate."

Brainpower under the bonnet. The Economist Technology Quarterly (June 8, 2006; subscription req'd). "The V12 engine found in the Aston Martin DB9 is notable not just for its brawn -- it produces 450 horsepower -- but also for its brain. It detects cylinder misfires using an artificial neural network, a system modelled on the interconnected neurons of a simple brain. ... Neural networks, like brains, are particularly good at analysing data and recognising patterns that are difficult to define precisely. They are trained using thousands of examples, and a 'learning' algorithm that alters the strength of the connections in the network so that it gives the appropriate output value (whether or not a misfire has occurred) depending on the input values (engine speed, acceleration, cylinder position, and so forth)."

• Also see: CarSim turns witnesses' words into movies - Software that can interpret everyday written language is being used to turn descriptions of an event into a 3D animation of what happened. By Duncan Graham-Rowe. New Scientist (September 24, 2005; subscription req'd: Issue2518).

Transims. Los Alamos National Laboratory. " TRANSIMS is an agent-based simulation system capable of simulating the second-by-second movements of every person and every vehicle through the transportation network of a large metropolitan area.It consists of mutually supporting simulations, models, and databases. By employing advanced computational and analytical techniques, it creates an integrated environment for regional transportation system analysis.

Smart cars - Knowledge is power...and safety. By Paul Sharke. Mechanical Engineering (March 2003). "The U.S. Department of Transportation, through the 1998 Intelligent Vehicle Initiative, identified eight areas where intelligent systems could 'improve' or 'impact' safety. The list includes four kinds of collision avoidances: rear end, lane change and merge, road departure, and intersection; two kinds of enhancements: vision and vehicle stability; and two kinds of monitoring: driver condition and driver distraction. Besides reducing collisions, driver assistance systems may unblock clogged highways one day, according to Martin Treiber and Dirk Helbing of the Technical University of Dresden in Germany. Using a highway simulation model, they found motorists tending to overcompensate for slowing traffic ahead. The model indicated that 10 percent of the cars fitted with driver assistance would reduce the problem by eliminating excessive braking. Twenty percent of vehicles using such systems would eliminate traffic jams altogether, they found. The first inklings of intelligent systems to emerge commercially were in high-end cars. Mercedes-Benz, BMW, and Jaguar introduced active cruise control in the United States early in the '00s and in Europe a year or so earlier. Similarly, adjuncts to anti-lock braking systems, such as brake assist and traction control, debuted in expensive cars, but are now finding their way onto cheaper vehicles, minivans, and sport utility vehicles. ... DaimlerChrysler's Vöhringer described research under way that could one day protect pedestrians from automobiles. Such an 'urban assistant system' could identify children running out into the street and halt or slow the car in time to prevent a collision."

Finally, a Car That Talks Back. By John Gartner. Wired News (September 2, 2004). "Honda will soon become the first auto manufacturer to include, as standard equipment in some models, technology that enables drivers to converse with their cars about where to go and how to get there. Using voice-recognition and text-to-speech technology from IBM, the 2005 Acura RL, available in October, and Honda Odyssey, available in September, will produce maps and 'speak' turn-by-turn directions from the navigation system. Drivers will also be able to make phone calls or crank up the air conditioning, all while keeping their eyes on the road and their hands on the wheel. ... By eliminating the need for accessing a touch screen or keypad to look for a destination, Honda is allowing people to focus on driving. 'At the end of the day it's a safer and more elegant solution,' [Frank Viquez] said."

Vision in Transport: "Machine vision has application in many aspects of transport. For example, it can be used to collect and understand data useful in transport planning and safety. It can also play an active role in navigation and vehicle guidance." From the British Machine Vision Association and Society for Pattern Recognition.

NOAA Using Artificial Intelligence to Improve Navigational Safety Data. NOAA News (June 23, 2003). "The NOAA Center for Operational Oceanographic Products and Services (CO-OPS) is now using artificial intelligence to extend and improve its existing real-time quality control monitoring system. This system, called CORMS (Continuous Operational Real-time Monitoring System) operates 24 hours a day, seven days a week ensuring the availability and accuracy of the real-time water levels, currents and meteorological data provided by CO-OPS for navigational safety.

Artificial intelligence seen as security boon. By Jill Vardy. National Post Online (October 5, 2001). "Ottawa-based Precarn Inc. is asking Canadian researchers to come up with artificial intelligence systems for transportation safety and security following the Sept. 11 terrorist attacks in the United States. Precarn, a consortium that funds research and development of intelligent systems technologies, says now is the time for projects that use artificial intelligence technology to improve Canada's transportation systems. ... 'The bottom line in all of this artificial intelligence stuff is making massive volumes of information accessible to you when you need it,' Mr. [Randy] Goebel said. For example, intelligent software agents could be used to improve the accuracy and speed of cross-border traffic, monitor traffic and weather patterns, speed up response times and improve management of emergencies and crisis situations."

General Readings

Computers try to outthink terrorists. By Bruce V. Bigelow. The San Diego Union-Tribune (January 13, 2002). Also available from UC San Diego. "In the same way, a neural network could analyze shipping manifests and identify the characteristic features of legitimate cargo entering the United States."

Intelligence: Behold the All-Seeing, Self-Parking, Safety-Enforcing, Networked Automobile - Radar, lasers, wireless radio networks and other embedded tech will enable our cars to sense faraway traffic and stop accidents before they happen. But who will be in the driver’s seat? By Paul Horrell. Popular Science: Special Section - The Future of the Car (August 30, 2005). "Ford and other automakers are moving ahead with experimental systems that could help cars anticipate accidents. That Lexus pre-crash safety system is no more than a toe-in-the-water stage in a worldwide rush of R&D effort to support -- or usurp -- the driver in moments of danger. Video-processing algorithms will soon be powerful enough to recognize another vehicle on a collision course. And if the driver is oblivious to the peril posed, the vehicle can apply its own brakes in time to stop."

"The Journal of Scheduling (JOS) provides a recognised global forum for the publication of all forms of scheduling-oriented research. First published in June 1998, JOS covers advances in scheduling research, such as the latest techniques, applications, theoretical issues and novel approaches to problems. The journal is of direct relevance to the areas of Computer Science, Discrete Mathematics, Operational Research, Engineering, Management, Artificial Intelligence, Construction, Distribution, Manufacturing, Transport, Aerospace and Retail and Service Industries. These disciplines face complex scheduling needs and all stand to gain from advances in scheduling technology and understanding."

Crew_NS: Scheduling Train Crews in the Netherlands. By Ernesto M. Morgado and Joao P. Martins (1998). AI Magazine 19 (1): 25-38. Abstract: " We present a system, CREWS_NS, that is used in the long-term scheduling of drivers and guards for the Dutch Railways. CREWS_NS schedules the work of about 5000 people. CREWS_NS is built on top of CREWS, a scheduling tool for speeding the development of scheduling applications. CREWS heavily relies on the use of AI techniques and has been built as a white-box system, in the sense that the planner can perceive what is going on, can interact with the system by proposing alternatives or querying decisions, and can adapt the behavior of the system to changing circumstances. Scheduling can be done in automatic, semiautomatic, or manual mode. CREWS has mechanisms for dealing with the constant changes that occur in input data, can identify the consequences of the change, and guides the planner in accommodating the changes in the already built schedules (rescheduling)."

Drivers wanted. Motoring - It is already possible to build driverless cars, trucks and buses. But practical problems and safety concerns mean they may never be allowed on the roads. The Economist Technology Quarterly (March 11, 2004). "The teams competing in DARPA's Grand Challenge (see Robots, start your engines) have it easy. The driverless vehicles racing off-road in the Mojave desert merely have to avoid boulders, dunes and the occasional cactus. That is nothing compared with the hazards of the open road. Put those same autonomous vehicles on Interstate 15 -- the busy road that links Los Angeles and Las Vegas -- and they would also have to contend with bleary-eyed weekenders, huge trucks and octogenarians puttering along in mobile homes. Even so, engineers and scientists at a handful of academic and industrial research centres are valiantly grappling with the problem of designing autonomous passenger vehicles, buses and trucks. They imagine a future in which convoys of cars would communicate with each other and with roadside sensors to navigate congested freeways, ensure smooth traffic flow and virtually eliminate accidents."

Berth Allocation and Planning. By Hon Wai Leong. Innovation 6(1). "A berth-allocation planning system makes use of a software architecture that enables it to integrate different solution engines, developed to solve different sub-problems. Technologies used range from specialised algorithms to artificial intelligence."

New software makes debut in tanker sector - Tankers International uses system to manage scheduling across its VLCC fleet. By Hugh O’Mahony. Lloyd's List (subscription req'd.). "Cutting-edge software deployed to accelerate complex decision-making in the logistics sector is being applied for the first time in oil tanker operations to optimise scheduling. ... After two years of trials Tankers International plans to take live a 'multi-agent' software package next month from London developer Magenta to manage scheduling across its very large crude carrier fleet. Multi-agent software uses the artificial intelligence principle of ontology to assess the factors subject to change - 'agents' - that act on a set of assets, devising optimal deployment in relation to prevailing requirements. ... When a new cargo is offered, 'agents', amounting to individual software programmes, 'negotiate' the optimum vessel for the cargo by comparing alternative routes, vessels, ports, costs, freight rates, fuel against propulsion, speed and distance."

• Also see: Magenta Deploys its Multi-Agent Technology to Optimize One of the World's Largest Oil Tanker Fleets. PRNewswire / available from WQAD (August 13, 2004). "[W]hen a new cargo is offered, agents are created within the database that contains all the data about the cargo - for example freight rates, size and type of cargo, as well as load and discharge ports. The agents then negotiate within the virtual market to decide the optimum vessel for the cargo, based on TI's fleet strategy. The agents do this by competing to find the best solution between supply and demand by comparing alternative routes, vessels, ports, costs, freight rates, fuel for propulsion, speed, distance and even positions of the vessels. This data and the defining concepts upon which the agents base their decisions are stored within the knowledge database, known as the Ontology. Unlike other systems, the agents are also able to resolve conflicts as they are not bound by rigid rules and are able to work around problems."

Intelligent Retail Logistics Scheduling. By John Rowe, Keith Jewers, Joe Sivayogan, Andrew Codd, and Andrew Alcock. (1996). AI Magzine 17 (4): 31-39. "The supply-chain integrated ordering network (SCION) depot-bookings system automates the planning and scheduling of perishable and nonperishable commodities and the vehicles that carry them into J. Sainsbury depots. This initiative is strategic, enabling the business to make the key move from weekly to daily ordering. The system is mission critical, managing the inward flow of commodities from suppliers into J. Sainsbury’s depots. The system leverages AI techniques to provide a business solution that meets challenging functional and performance needs. The SCION depot-bookings system is operational, providing schedules for 22 depots across the United Kingdom."

Security Blanket. By Chana R. Schoenberger. Forbes Global (April 14, 2003). "The threat of smuggled bombs has the government ordering up detailed contents lists for containers. What's to stop a terrorist from lying about what's inside. Not much. ... The U.S. has also ordered shippers to submit far more detailed manifests a week earlier than before. Lists of shipped items are fed into a computer in the government's newly upgraded Automated Targeting System, which uses artificial intelligence software to flag suspicious containers based on combinations of country of origin, weight discrepancies and names linked to terrorist groups."

Is There a Future for Speech in Vehicles? By Kenneth White, Harvey Ruback and Roberto Sicconi. Speech Technology Magazine (November / December 2004). "Today, speech recognition technology is becoming an important component in how people are using and interacting with their cars. ... Many people associate speech in cars with science fiction movies and television shows where the cars act like R2D2 robots on wheels. In today’s world the main reason for using speech is less Hollywood and more pragmatic. In fact, it usually boils down to safety."

Intelligent Traffic Light Control. By Marco Wiering. ERCIM News (No. 53, April 2003). "Intelligent traffic light control does not only mean that traffic lights are set in order to minimize waiting times of road users, but also that road users receive information about how to drive through a city in order to minimize their waiting times. This means that we are coping with a complex multi-agent system, where communication and coordination play essential roles. Our research has led to a novel system in which traffic light controllers and the behaviour of car drivers are optimized using machine-learning methods."

Related Resources

Access ITS. Homepage for the Intelligent Transportation Systems of America Organization.

Advanced Highway Maintenance and Construction Technology Research Center: a partnership between the California Department of Transportation and UC Davis. Projects include Mobile Robots: "A tethered mobile robot is a self-propelled, automated device that can operate intelligently in close proximity to a support vehicle. The use of mobile robots can enhance worker safety, reduce maintenance costs, and improve operational efficiency."

• Also see: Robots That Repair Roads. By Jenn Shreve. Wired News (November 12, 2001). "For a highway maintenance worker, sealing cracks along the freeway is a lot like walking a tightrope without a net. Introduce a drunk driver or a flying chunk of debris, and a workaday job becomes a fatality statistic. A robot, on the other hand, knows no fear and works tirelessly and quickly: A day's worth of sealing cracks in the road can be finished in an hour."

ATON: "The main goal the Autonomous Agents for On-Scene Networked Incident Management (ATON) project [at the Computer Vision and Robotics Research Laboratory - UCSD] is to make tangible and substantive contributions to the realization of a powerful and integrated traffic-incident detection, monitoring and recovery system."

CITR: Ohio State University Center for Intelligent Transportation Research.

City University of Hong Kong (CityU): "This website highlights professional services for Artificial Intelligence (AI) system/expert system development, such as our award-winner AI scheduling software and AI rostering software. It also contains case studies of AI scheduling/AI rostering projects we have performed over the past decade in for various industries in Hong Kong, such as health, transportation, food and education." Be sure to see the Berth Allocation case study.

CVL: Computer Vision Lab at the University of Tokyo ( IKEUCHI Laboratory,Institute of Industrial Science) and other universities. Check out their research regarding recognition and classification of vehicles for ITS applications.

ICODES, Integrated Computerized Deployment System, from theMarine Corps Systems Command Transportation Distribution Information Systems (TDIS) Program Office. "ICODES is a decision-support system that applies the Integrated Cooperative Decision-Making (ICDM) framework to the area of Ship Stowplanning. It is designed to satisfy the focused stowplanning demand of the U.S. Army and the U.S. Marine Corps by assisting personnel at the port to react quickly and efficiently to changing transportation requirements. As a ship load planning software tool, ICODES utilizes artificial intelligence (AI) principles and techniques to assist embarkation specialists in the rapid development of cargo stow plans."

• Also see this article: Ahoy there, solution. By Doug Beizer. Washington Technology (May 29, 2006; Volume 21, Number 10). "It’s not uncommon for a family preparing for a long road trip to use pad and pencil to tick off items on a checklist as they load the minivan. And until recently, the Navy used much the same method when loading a vessel for an ocean voyage. The difference is more than one of size. Intricate planning is needed to store hundreds of pieces of cargo on a ship’s multiple decks. Even more complex planning and precise loading is necessary to safely load and store hazardous materials. But now the armed forces have upgraded their loading arsenal to include specialized software running on rugged handhelds, said Boone Pendergrast, a customer support representative for CDM Technologies Inc., a San Luis Obispo, Calif., company that developed the software. The Integrated Computerized Deployment System (Icodes) is a ship stow-planning application that uses artificial-intelligence principles and techniques that CDM developed in association with California Polytechnic State University, San Luis Obispo. ... 'Under the old scenario, if you don’t notice the mistake until two or three hours later, there could be 30 to 50 pieces that might have to be moved to get that one piece out,' Pendergrast said. The system also has slashed the planning time, he said. Where once it took five people five days to plan a load, now one skilled user can do a stow plan in half a day."

IEEE Intelligent Transportation Systems Society. Field of Interest:"The Society is interested in theoretical, experimental and operational aspects of electrical and electronics engineering and information technologies as applied to Intelligent Transportation Systems (ITS), defined as those systems utilizing synergistic technologies and systems engineering concepts to develop and improve transportation systems of all kinds."

• Also see:
  • Conferences: IEEE ITSC and IEEE IV
  • IEEE Transactions on Intelligent Transportation Systems.
  • IET Intelligent Transport Systems: "an interdisciplinary journal devoted to research into the practical applications of intelligent transport systems and infrastructures.

Intelligent Transportation links from iCivilEngineer.com. Projects, articles, and much, much more await you at this site.

Intelligent Transportation Research Center (ITRC) at MIT. "ITRC focuses on the key Intelligent Transportation Systems (ITS) technologies, including an integrated network of transportation information, automatic crash & incident detection, notification and response, advanced crash avoidance technology, advanced transportation monitoring and management, etc., in order to improve the safety, security, efficiency, mobile access, and environment."

ITS Research Lab at The University of Queensland. "The Intelligent Transport Systems (ITS) Research Laboratory was established through an Australian Research Council Infrastructure Grant and contributions from a consortium of Australian universities, road and transport authorities and the private sector. The Laboratory is aimed at developing and evaluating advanced traffic management and advanced vehicle technologies to enhance environmental quality and improve the safety and efficiency of the transport system."

Intelligent Transportation Systems from AIRVL, the AI, Robotics and Vision Laboratory at the University of Minnesota's Department of Computer Science and Engineering.

"PATH is a collaboration between the California Department of Transportation (Caltrans), the University of California, other public and private academic institutions, and private industry. PATH's mission: applying advanced technology to increase highway capacity and safety, and to reduce traffic congestion, air pollution, and energy consumption." Be sure to see their collection of research projects.

The Smart Travel Lab at the Center for Transportation Studies, University of Virginia. As stated in the Directors' message: "The Smart Travel Lab is a state-of-the-art facility that supports research and education in the rapidly emerging area of intelligent transportation systems (ITS). Using the latest information technologies and analysis and modeling techniques, researchers in the lab are developing prototype systems and applications that promise to improve the effectiveness of ITS. This web site provides information on Smart Travel Lab activities and previews a number of prototypes developed in the lab. Please check back with us often to learn of new developments.The Smart Travel Lab is a joint effort between the Department of Civil Engineering at the University of Virginia and the Virginia Transportation Research Council."

SmartWeb: "The goal of the SmartWeb project (duration: 2004 - 2007) is to lay the foundations for multimodal user interfaces to distributed and composable semantic Web services on mobile devices. The SmartWeb consortium brings together experts from various research communities: mobile services, intelligent user interfaces, language and speech technology, information extraction, and semantic web technologies.... The academic partners of SmartWeb are the research institutes DFKI (consortium leader), FhG FIRST, and ICSI together with university groups from Erlangen, Karlsruhe, Munich, Saarbrücken, and Stuttgart. The industrial partners of SmartWeb are BMW, DaimlerChrysler, Deutsche Telekom, and Siemens as large companies, as well as EML, Ontoprise, and Sympalog as small businesses. The German Federal Ministry of Education and Research (BMBF) is funding the SmartWeb consortium with grants totaling 13.7 million euros." (Also see this related article above.)

The Thinking Car. Siemens AG. "The use of cutting-edge technologies will make driving in the future even more safe, comfortable, reliable and environmentally friendly. The intelligent networking of all automobile systems assists the driver both in dangerous situations and in navigation and communications."

Other References Offline

Chew, Tat-Leong, Andrew Gill, and Joo-Hong Lim. 1989. Planning the Discharging and Loading of Container Ships. In Innovative Applications of Artificial Intelligence, ed. Schorr, Herbert and Alain Rappaport, 317-332. Menlo Park, CA: AAAI.

Dutton., Trish 1992. HUB SIAASHING: A Knowledge-Based System for Severe, Temporary Airline Schedule Reduction. In Innovative Applications of Artificial Intelligence 4, ed. Scott, A. Carlisle and Phillip Klahr, 265-278. Menlo Park, CA: AAAI.

Heng, Goh Kwong, Goh Kah Seng, Lye Chee Whye, et al. 1995. Scheduling of Marine Resources in the Port of Singapore Authority: A Total Approach. In Proceedings of the Seventh Innovative Applications of Artificial Intelligence Conference, 62-69. Menlo Park, CA: AAAI

Lavitt, Michael O. 1997. Crew Tracking Software to Use Artificial Intelligence. Aviation Week and Space Technology 147: 94-95.

Murphy, Kathleen, Elizabeth Ralston, David Friedlander, et al. 1997. The Scheduling of Rail at Union Pacific Railroad. In Proceedings of the Ninth Annual Conference on Innovative Applications of Artificial Intelligence, ed. Senator, Ted and Bruce Buchanan, 903-912. Menlo, CA: AAAI. The Union Pacific Railroad (UPRR) has over 31,000 miles of track covering a 24 state region. Planning and scheduling the production, packaging, delivery, and pickup of rail, involved in the maintenance of this network, is a very complex task. Manually scheduling only a subset of the resources required has historically taken several days to accomplish. Moreover, the inability to fully schedule all resources can lead to inefficient resource utilization. This paper describes the Rail Train Scheduler (RTS), designed and developed to capture the expertise of the UPRR scheduler, generate production schedules of all the resources involved, and provide a decision support tool for determining the best mix of resources required. RTS is an expert system that uses constraint satisfaction and domain specific heuristics to produce good, low cost schedules. It has been deployed since January, 1996. UPRR anticipates a savings of about $500,000 per year from the use of RTS.

Ng, Ian, Andrew Gill, Ian Chia, et al. 1997. SunRay V-An Intelligent Container Trucking Operations Management and Control System. In Proceeding of the Ninth Annual Conference on Innovative Applications of Artificial Intelligence, ed. Senator, Ted and Bruce Buchanan, 913-918. Menlo Park, CA: AAAI.

Rothstein., Janet 1991. National Dispatcher Router: A Multiparadigm-Based Scheduling Advisor. In Innovative Applications of Artificial Intelligence 2, ed. Alain Rappaport and Reid Smith, 291-304. Menlo Park, CA: AAAI.

Wang, Fei-Yue. Driving into the Future with ITS. IEEE Intelligent Systems (May/June 2006) 21(3): 94-95. Abstract: "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. The future will include smart cars on smart roads and agent-based ITS control. Many existing transportation problems still call for AI techniques to achieve cost-effective solutions, and emerging issues will depend even more on AI solutions. AI will play a critical role in our drive to future intelligent transportation systems. This article is part of a special issue on the Future of AI."

Wylie, Rob, Robert Orchard, Michael Halasz, et al. 1997. IDS: Improving Aircraft Fleet Maintenance. In Proceedings of the Ninth Annual Conference on Innovative applications of Artificial Intelligence, ed. Senator, Ted and Bruce Buchanan, 1078. Menlo Park, CA: AAAI. This paper describes the Integrated Diagnostic System (IDS), an applied AI project to develop hybrid information systems to diagnose problems and help manage repair processes of commercial aircraft fleets. A study at one major airline indicated that significant benefits could accrue (approximately 2% of overall maintenance budget) through the use of innovative information technology. The IDS prototype (currently in extended field trial) takes as input a stream of messages representing maintenance and diagnostic events. These are filtered and aggregated in order to yield information in an appropriate form for various decision making tasks (and in particular for the maintenance staff while performing fault isolation and repair procedures). IDS was built using ART*Enterprise and makes extensive use of its rule-based and case-based reasoning facilities in order to apply various sources of knowledge (manuals, heuristics, historical data) to this problem.