Download Artificial Intelligence Applications to Critical Transportation Issues PDF

TitleArtificial Intelligence Applications to Critical Transportation Issues
LanguageEnglish
File Size1.5 MB
Total Pages156
Table of Contents
                            Transportation Research Circular E-C168: Artificial Intelligence Applications to Critical Transportation Issues
Transportation Research Board 2012 Executive Committee Officers
Transportation Research Board 2012–2013 Technical Activities Council
Title page
Artificial Intelligence and Advanced Computing Applications Committee
Foreword
Publisher's Note
Acknowledgments
Contents
Why Artificial Intelligence?
	Difference Between Artificial Intelligence and Traditional Methods
	Advantages and Limitations of Artificial Intelligence
Artificial intelligence and Key Transportation Applications Areas
	Application Area 1: Traffic Operations
	Traffic Signal Timing and Optimization
		Evolutionary Algorithms
		Fuzzy Logic Control
		Artificial Neural Networks Control
		Reinforcement Learning and Agent-Based Control
		Summary
	Short Term Traffic Prediction
	Short-Term Traffic and Travel Time Prediction Models
		Taxonomy of Short-Term Traffic Prediction Methods
		Naive Methods
		Parametric Models
		Nonparametric Models
		Discussion, Conclusions, and Outlook
	Neural Networks for Travel Time Prediction on Interrupted Flow Facilities
		Background
		The Problem of Travel Time Prediction
		Travel Time Modeling: Relevant Factors and Problem Formulation
		Experimental Set Up and Data
		Results and Discussion
		Conclusions and Recommendations
	Artificial Intelligence and Transportation Systems Modeling and Simulation
	Agent-Based Modeling and Simulation
		ABMS to Model Decision-Making Processes
		Distributed MAS and Transportation System Performance Optimization
		Future of ABMS in Transportation
	Artificial Intelligence and Microscopic Traffic Simulation Models: Applications to Parameter Calibration and Origin–Destination Estimation
		Parametric Calibration
		Origin–Destination Estimation
		Conclusions
	Ramp Metering
		Artificial Intelligence and Ramp Metering
		Conclusions
	Application Area 2: Artificial Intelligence and Travel Demand Modeling
	Travel Behavior Research
		What Makes Artificial Intelligence Relevant and Appropriate for the Analysis and Modeling of Travel Behavior?
		AI Paradigms, Cognitive Psychology, and Travel Behavior
		Fuzzy Sets Theory
		Neural Networks
		Genetic Algorithms
		Multiagent Simulations
		Conclusions
	Urban Travel Demand Forecasting
		Historical Overview of Urban Travel Demand Forecasting
		Opportunities for AI in Urban Travel Demand Modeling
		Conclusions
	Application Area 3: Transportation Safety and Security
	Transportation Safety Analysis
		Road Safety
		Safety Analysis and Artificial Intelligence
		Conclusion
	Transportation Security
		Applications of AI in Transportation Security Areas
		Conclusions
	Application Area 4: Public Transportation
	Analysis of Public Transportation Planning and Operations
		Analysis of Transit Planning and Operations
		AI and Transit Analysis: Multiobjective Analysis
		Example
		Summary
	Application Area 5: Infrastructure Design and Construction
	Design and Construction of Transportation Infrastructure
		AI Applications in Infrastructure Design and Construction
		Discussions and Future Outlook
Thoughts on the Future of Artificial Intelligence and Transportation
	Montasir Abbas
	Erel Avineri
	Ryan Fries
	Sherif Ishak
	Manoj Jha
	Shinya Kikuchi
	Hongchao Liu
	Edara Praveen
	Yi Qi
	Kristen L. Sanford-Bernhardt
	Nicolas Saunier
	Gary S. Spring
	Ramkumar Venkatanarayana
	Billy M. Williams
	Yunlong Zhang
The National Academies
The National Academies Identifier
                        
Document Text Contents
Page 1

T R A N S P O R T A T I O N R E S E A R C H

Number E-C168 November 2012

Artificial Intelligence
Applications to Critical

Transportation Issues

Page 2

TRANSPORTATION RESEARCH BOARD
2012 EXECUTIVE COMMITTEE OFFICERS

Chair: Sandra Rosenbloom, Professor of Planning, University of Arizona, Tucson
Vice Chair: Deborah H. Butler, Executive Vice President, Planning, and CIO, Norfolk Southern

Corporation, Norfolk, Virginia

Division Chair for NRC Oversight: C. Michael Walton, Ernest H. Cockrell Centennial Chair in
Engineering, University of Texas, Austin

Executive Director: Robert E. Skinner, Jr., Transportation Research Board


TRANSPORTATION RESEARCH BOARD
2012–2013 TECHNICAL ACTIVITIES COUNCIL

Chair: Katherine F. Turnbull , Executive Associate Director, Texas Transportation Institute, Texas

A&M University, College Station
Technical Activities Director: Mark R. Norman , Transportation Research Board

Paul Carlson, Research Engineer, Texas Transportation Institute, Texas A&M University, College

Station, Operations and Maintenance Group Chair
Thomas J. Kazmierowski, Manager, Materials Engineering and Research Office, Ontario Ministry of

Transportation, Toronto, Canada, Design and Construction Group Chair
Ronald R. Knipling, Principal, safetyforthelonghaul.com, Arlington, Virginia, System Users Group

Chair
Mark S. Kross, Consultant, Jefferson City, Missouri, Planning and Environment Group Chair
Peter B. Mandle, Director, LeighFisher, Inc., Burlingame, California, Aviation Group Chair
Harold R. (Skip) Paul, Director, Louisiana Transportation Research Center, Louisiana Department of

Transportation and Development, Baton Rouge, State DOT Representative
Anthony D. Perl, Professor of Political Science and Urban Studies and Director, Urban Studies Program,

Simon Fraser University, Vancouver, British Columbia, Canada, Rail Group Chair
Steven Silkunas, Director of Business Development, Southeastern Pennsylvania Transportation

Authority, Philadelphia, Pennsylvania, Public Transportation Group Chair
Peter F. Swan, Associate Professor of Logistics and Operations Management, Pennsylvania State,

Harrisburg, Middletown, Pennsylvania, Freight Systems Group Chair
James S. Thiel, General Counsel, Wisconsin Department of Transportation, Legal Resources Group

Chair
Thomas H. Wakeman, Research Professor, Stevens Institute of Technology, Hoboken, New Jersey,

Marine Group Chair
Johanna P. Zmud, Director, Transportation, Space, and Technology Program, RAND Corporation,

Arlington, Virginia, Policy and Organization Group Chair

Page 78

70

APPLICATION AREA 1: TRAFFIC OPERATIONS


Ramp Metering


GEORGE X. LU
University of Vermont


HONGCHAO LIU

Texas Tech University



amp metering is a control strategy that regulates the frequency of vehicles entering the
freeway at entrance ramps. Operated by either single or systemwide stop-and-go type traffic

signals, the objective of ramp metering is to maintain optimum control of freeway and prevent
operational breakdowns through limiting the rates of entering vehicles at entrance ramps or
freeway-to-freeway connector ramps. For both pretimed and traffic-responsive local and
systemwide control strategies, the underlying idea of a ramp metering algorithm is to balance
demand and capacity of the freeway through well-defined objective functions and constraint sets
(1). In this regard, linear programming has been widely used since the emergence of ramp
metering concept in 1960s. Since then, transportation problems have become increasingly
complex as their scope of analysis expanded rapidly beyond the traditional domain. These
problems are characterized by


• A large number of factors involved;
• Parametric associations among the factors are unfathomable;
• A huge amount of incomplete data is encompassed; and
• Many objectives and constraints are so intertwined that the priorities among the

stakeholders are blurry (2).

Kosko stated: “As the complexity of a system increases, our ability to make precise and

yet significant statements about its behaviors diminishes, and significance and complexity
become almost mutually exclusive characteristics” (3). Given that complex problems are difficult
to solve using conventional methodologies, there has been a growing interest in employing
artificial intelligence (AI) paradigms to address transportation issues to improve operation,
safety, and efficiency of transportation systems.


ARTIFICIAL INTELLIGENCE AND RAMP METERING

Fuzzy Logic Based Algorithms

Fuzzy logic algorithms appear well suited to ramp metering because they can utilize inaccurate
or imprecise information and allow smooth transition between metering rates. Inputs and outputs
are descriptive (e.g., “no congestion,” “light congestion,” and “medium congestion”) to allow for
imprecise data. Fuzzy logic systems use rule-based logic to incorporate human expertise. This
way, it can balance several performance objectives simultaneously and consider many types of

R

Page 79

Lu and Liu 71



information, such as traffic conditions downstream, occupancy, flow rate, speed, and ramp
queue. These capabilities allow fuzzy logic to anticipate the problem and take temperate and
corrective action before the congestion occurs.

Sasaki and Akiyama developed a fuzzy traffic control system on an urban expressway
(4–6). The authors showed that control of an urban expressway depends upon a skilled operator’s
judgment and decisions. The premier goal of the Sasaki and Akiyama’s research was to
investigate the effectiveness of fuzzy logic-based models in describing the operator’s judgment
process. A simple fuzzy reasoning model for on-ramp control and its performance were
presented in their papers. The resulted strategies include restricting the number of booths and
closing the gates, which proved to be successful from the test on the Osaka–Sakai route of the
Hanshin Expressway. A main conclusion of their study is that fuzzy logic-based traffic controller
system can effectively describe the judgment process and consequently take the place of human
operators.

Chen et al. (7) presented a fuzzy controller for freeway ramp metering that uses rules of
the form: IF “freeway condition” THEN “control action.” The controller has been designed to
consider varied levels of congestion, a downstream control area, changing occupancy levels,
upstream flows, and a distributed detector array in its rule base. Through fuzzy implication, the
inference of each rule is used to the degree to which the condition is true. Using a dynamic
simulation model of conditions at the San Francisco–Oakland Bay Bridge, the action of the fuzzy
controller is compared to the existing “crisp” control scheme, and an idealized controller. Tests
under a variety of scenarios with different incident locations and capacity reductions show that
the fuzzy controller is able to extract 40% to 100% of the possible savings in passenger-hours. In
general, the fuzzy algorithm displays smooth and rapid response to incidents, and significantly
reduces the minute-miles of congestion.

Taylor et al. designed a fuzzy logic ramp-metering algorithm to overcome the limitations
of conventional ramp-metering strategies (8). The fuzzy controller also demonstrated improved
robustness, prevented heavy congestion, intelligently balanced conflicting needs, and is user
friendly. The objective was to maximize total distance traveled and minimize total travel time
and vehicle delay while maintaining an acceptable ramp queue level. A multiple ramp study site
from the Seattle I-5 corridor was modeled and tested using the freeway simulation software,
FRESIM. For five of the six testing sets, encompassing a variety of traffic conditions, the fuzzy
controller outperformed the three other controllers tested.

Vukanovic and Ernhofer presented the ACCEZZ ramp metering algorithm which is an
adaptive control approach based on fuzzy logic (9). Results from its calibration and validation as
well as its evaluation using a microscopic simulation show how different control strategies can
improve traffic conditions especially during peak hours. To evaluate the potential benefits of
ramp metering, the ramp metering software TRANSRAMP has been developed, implemented,
and tested at a demonstration site in Munich, Germany. Since its implementation, TRANSRAMP
controls traffic at two consecutive on ramps successfully with the ACCEZZ algorithm.

Jiang et al. designed a fuzzy self-adaptive proportional–integral–derivative (PID)
controller and applied it to freeway ramp metering (10). A traffic flow model to describe the
freeway flow process is built first. Based on the model and in conjunction with nonlinear
feedback theory, a fuzzy-PID ramp controller is designed. The ramp metering rate is determined
by the PID controller whose parameters are tuned by fuzzy logic according to the density tracking
error and error variation. Gauss and triangle curves are used for the membership functions of the
fuzzy variables. Finally, the control system is simulated in MATLAB software and the result

Page 155

The National Academy of Sciences is a private, nonprofit, self-perpetuating society of distinguished schol-
ars engaged in scientific and engineering research, dedicated to the furtherance of science and technology
and to their use for the general welfare. On the authority of the charter granted to it by the Congress in
1863, the Academy has a mandate that requires it to advise the federal government on scientific and techni-
cal matters. Dr. Ralph J. Cicerone is president of the National Academy of Sciences.

The National Academy of Engineering was established in 1964, under the charter of the National Acad-
emy of Sciences, as a parallel organization of outstanding engineers. It is autonomous in its administration
and in the selection of its members, sharing with the National Academy of Sciences the responsibility for
advising the federal government. The National Academy of Engineering also sponsors engineering programs
aimed at meeting national needs, encourages education and research, and recognizes the superior achieve-
ments of engineers. Dr. Charles M. Vest is president of the National Academy of Engineering.

The Institute of Medicine was established in 1970 by the National Academy of Sciences to secure the
services of eminent members of appropriate professions in the examination of policy matters pertaining
to the health of the public. The Institute acts under the responsibility given to the National Academy of
Sciences by its congressional charter to be an adviser to the federal government and, on its own initiative,
to identify issues of medical care, research, and education. Dr. Harvey V. Fineberg is president of the
Institute of Medicine.

The National Research Council was organized by the National Academy of Sciences in 1916 to associate
the broad community of science and technology with the Academy’s purposes of furthering knowledge and
advising the federal government. Functioning in accordance with general policies determined by the Acad-
emy, the Council has become the principal operating agency of both the National Academy of Sciences
and the National Academy of Engineering in providing services to the government, the public, and the
scientific and engineering communities. The Council is administered jointly by both Academies and the
Institute of Medicine. Dr. Ralph J. Cicerone and Dr. Charles M. Vest are chair and vice chair, respectively,
of the National Research Council.

The Transportation Research Board is one of six major divisions of the National Research Council. The
mission of the Transportation Research Board is to provide leadership in transportation innovation and
progress through research and information exchange, conducted within a setting that is objective, interdisci-
plinary, and multimodal. The Board’s varied activities annually engage about 7,000 engineers, scientists,
and other transportation researchers and practitioners from the public and private sectors and academia, all
of whom contribute their expertise in the public interest. The program is supported by state transportation
departments, federal agencies including the component administrations of the U.S. Department of
Transportation, and other organizations and individuals interested in the development of transportation.
www.TRB.org

www.national-academies.org

www.TRB.org
www.nationalacademies.org

Page 156

TRANSPORTATION RESEARCH BOARD
500 Fifth Street, NW
Washington, DC 20001

Similer Documents