NCHRP

Web-Only Document 403 Artificial Intelligence Opportunities for State and Local DOTs
A RESEARCH ROADMAP

Conduct of Research Report for NCHRP Project 23-12
Submitted March 2024

The National Academy of Sciences was established in 1863 by an Act of Congress, signed by President Lincoln, as a private, nongovernmental institution to advise the nation on issues related to science and technology. Members are elected by their peers for outstanding contributions to research. Dr. Marcia McNutt is president.

The National Academy of Engineering was established in 1964 under the charter of the National Academy of Sciences to bring the practices of engineering to advising the nation. Members are elected by their peers for extraordinary contributions to engineering. Dr. John L. Anderson is president.

The National Academy of Medicine (formerly the Institute of Medicine) was established in 1970 under the charter of the National Academy of Sciences to advise the nation on medical and health issues. Members are elected by their peers for distinguished contributions to medicine and health. Dr. Victor J. Dzau is president.

The three Academies work together as the National Academies of Sciences, Engineering, and Medicine to provide independent, objective analysis and advice to the nation and conduct other activities to solve complex problems and inform public policy decisions. The National Academies also encourage education and research, recognize outstanding contributions to knowledge, and increase public understanding in matters of science, engineering, and medicine.

Learn more about the National Academies of Sciences, Engineering, and Medicine at www.nationalacademies.org.

The Transportation Research Board is one of seven major program divisions of the National Academies of Sciences, Engineering, and Medicine. The mission of the Transportation Research Board is to mobilize expertise, experience, and knowledge to anticipate and solve complex transportation-related challenges. The Board’s varied activities annually engage about 8,500 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.

Learn more about the Transportation Research Board at www.TRB.org.

COOPERATIVE RESEARCH PROGRAMS

CRP STAFF FOR NCHRP WEB-ONLY DOCUMENT 403

Waseem Dekelbab, Deputy Director, Cooperative Research Programs, and Manager, National Cooperative Highway Research Program

Sid Mohan, Associate Program Manager for Implementation and Technology Transfer

Mireya Kuskie, Senior Program Assistant

Natalie Barnes, Director of Publications

Heather DiAngelis, Associate Director of Publications

Jennifer J. Weeks, Publishing Projects Manager

NCHRP PROJECT 23-12 PANEL
Field of Administration—Area of Agency Administration

J. Neil Mastin, Mott MacDonald, LLC, Raleigh, NC (Chair)

Pouria Asadi, University of Rhode Island, Manchester, CT

Edgardo D. Block, Connecticut Department of Transportation, Newington, CT

Robert C. Cooney, eVision Partners, Inc., Raleigh, NC

Sayuri Koyamatsu, Washington State Department of Transportation, Shoreline, WA

Leni Oman, Spy Pond Partners, LLC, Olympia, WA

Thomas Pannett, Kegler Brown Hill & Ritter, Columbus, OH

Lubna Shoaib, East-West Gateway Council of Governments, St. Louis, MO

Maryam Tagh Bostani, HDR, Vancouver, BC

Alejandro Toriello, Georgia Institute of Technology, Atlanta, GA

Faisal Saleem, FHWA Liaison

AUTHOR ACKNOWLEDGMENTS

We would like to thank Prof. Gerardo Flintsch and Dr. Rich Hanowski for their continuous guidance and advice to help with this project. Dr. Hanowski especially helped us in reaching out to a larger audience during the outreach activities. Prof. Flintsch helped us with his technical insight and insight on the effectivity of the project outcomes to TRB. We would also like to thank some of our colleagues at VTTI who occasionally contributed to this project through their technical know-how and expertise in AI. This includes Calvin Winkowski, Steven Gregory, Neal Feieraband from the information technology team at VTTI, Dr. Balachandar Gudury, Dr. Omkar Kaskar from the division of data and analytics, and Dr. Debanjan Datta who was a graduate student and an expert in natural language process. Without the support of them this project would have been incomplete. Finally, I want to thank Rebecca Hammond and our editing team at VTTI including Dr. Michael Buckley, Laura Krisch, and Lydia Lunning for their continuous support.

Table Of Contents

SUMMARY

CHAPTER 1

PROJECT BACKGROUND

Intersection of Transportation Research and AI at DOTs

Expected Benefits of AI Application in State and Local DOTs

Scope and Challenges Towards AI Application in State and Local DOTs

PROJECT OBJECTIVE

RESEARCH APPROACH

SUMMARY OF TASKS AND DELIVERABLES

SUMMARY OF PROJECT OUTCOMES

ARRANGEMENT OF THE DOCUMENT

CHAPTER 2

INTRODUCTION

PART 1. RESEARCH TREND IDENTIFICATION USING TOPIC MODELING AND CO-OCCURRENCE MATRIX

RESULTS

PART 2. TREND ANALYSIS OF AI IN TRANSPORTATION RESEARCH AT DOT LEVEL

RESULTS

PART 3. A COMPREHENSIVE SUMMARY OF AI TOOLS AND INFRASTRUCTURE

DATA-DRIVEN AI ECOSYSTEM

KEY COMPONENTS OF AI TOOLS

CONCLUSION

CHAPTER 3

INTRODUCTION

PART 1: INTERVIEWS

Interview Results

PART 2: WORKSHOPS

Workshop 1

Workshop 2

CONCLUSION

CHAPTER 4

RESEARCH PROBLEM STATEMENTS

IMPLEMENTATION SCHEDULE

RESEARCH ROADMAP PROPOSED TIMELINE

CHALLENGES AFFECTING POTENTIAL IMPLEMENTATION

Workforce Development

CHAPTER 5

APPENDIX A: LITERATURE REVIEW

INTRODUCTION

What Is AI?

Focus of the Task

PART 1. RESEARCH TREND IDENTIFICATION USING TOPIC MODELING AND CO-OCCURRENCE MATRIX

Results and Analysis

Trend Analysis

Key Findings

PART 2. TREND ANALYSIS OF AI IN TRANSPORTATION RESEARCH

Methodology

Results

Key Findings

REFERENCES

APPENDIX A1

APPENDIX A2

APPENDIX A3

APPENDIX B: LITERATURE SURVEY OF AI TOOLS

INTRODUCTION

Data-driven AI Ecosystem

Workflow of AI Development

Key Components of AI Tools

AI SOFTWARE PLATFORMS

Traditional ML-based Solutions

Deep Learning Frameworks

Open-source Toolboxes

Statistical Analysis Platforms

Development and Deployment

Visualization and Analytics Software

Data Annotation Tools

Solution-based Systems

AI DATA MANAGEMENT

Data Provider

Data Modality

Data Sharing

Large-scale Data Collection, Storage, and Management

LARGE-SCALE DATA PROCESSING ON GPU/EDGE/CLOUD

Computing

Edge Computing

Cloud Computing

COST AND BENEFIT

AI Software Tools

Big Data Management

Computing

Outsourcing, Crowdsourcing, Knowledge Building

CONCLUSION

REFERENCES

APPENDIX B1

CNNs

Recurrent Neural Network

Auto-encoder

APPENDIX C: SYNERGY ANALYSIS AND INTERVIEW WITH DOTS

INTRODUCTION

METHODS

Participant Recruitment

Data Collection

Data Analysis

RESULTS AND ANALYSIS

Current AI Practices

Challenges with AI Work

Ways to Overcome Challenges

Workforce and Infrastructure

Future Scope of AI Integration

SUMMARY

CONCLUSIONS

REFERENCES

APPENDIX C1

APPENDIX C2

APPENDIX C3

APPENDIX D: WORKSHOP REPORT

INTRODUCTION

Project Progress and Scope of This Document

METHODS

Step 1: Participant Recruitment and Outreach

Step 2: Finalize Topics

Step 3: Conduct Workshops

Step 4: Analysis of Outcomes

RESULTS

Part I: Workshop 1

Part II: Workshop 2

CONCLUSION

APPENDIX E: RESEARCH PROBLEM STATEMENTS

INTRODUCTION

Research Problem Statement 1: Case Studies of Implementation of Artificial Intelligence Programs in State and Local Departments of Transportation

Research Problem Statement 2: Toolbox to Guide the Selection and Deployment of Artificial Intelligence Technologies in State and Local Transportation Agencies

Research Problem Statement 3: Workforce Needs and Development to Prepare Transportation Agencies for the Application of Existing and Emerging Artificial Intelligence Approaches

Research Problem Statement 4: Implementable Funding Strategies for Artificial Intelligence Opportunity Applications for State and Local DOTs

Research Problem Statement 5: Develop a Guidebook to Understand the Vulnerability and Security Concerns for AI-based Transportation Solutions

Research Problem Statement 6: Exploring the Integration of AI-based Methods in Multimodal Transportation Planning

Research Problem Statement 7: Validation of Artificial Intelligence Applications for Automated Pavement Condition Evaluation

Research Problem Statement 8: Explore Natural Language Processing-based Methods for Document Management and Public Interaction at DOTs

Research Problem Statement 9: Develop a Guidebook for Successful Collaboration with Industry Partners that Provides AI-based Solutions

Research Problem Statement 10: Guidebook to Create Sharable, Reliable Sources of Data Sets

Research Problem Statement 11: Creating a framework to process and manage data collected by DOTs

APPENDIX F: IMPLEMENTATION OF RESEARCH FINDINGS AND DISSEMINATION PLAN

INTRODUCTION

PROBLEM STATEMENTS

Project Workshop

IMPLEMENTATION PLAN

CHALLENGES AFFECTING POTENTIAL IMPLEMENTATION

Workforce Development

Developing Workforce

CONCLUSION

List of Figures

Figure 1. Project task outline

Figure 2. Chord diagram illustrating the interdependencies among transportation topics. The width of the arcs represents the strength of interrelation between transportation topics, providing insights into their relative importance and interdependencies

Figure 3. A detailed view of different AI topics used in Transportation topics “Traffic Management” and “Highway Management/Design”

Figure 4. Trends of different AI topics over the years

Figure 5. Transportation areas across the selected projects

Figure 6. Distribution of Projects over the years

Figure 7. A typical AI ecosystem with multiple components, including data processing pipeline, human-in-the-loop interaction, and development for AI-based systems

Figure 8. High level overview of topic modeling. It takes a several keywords and identifiers and automatically cluster them to a number of independent topics

Figure 9. Literature review to assess the scope of AI in transportation research and development

Figure 10. Schematic diagram of the process to find associations and interdependencies between transportation topics and AI

Figure 11. Schematic overview of the process to analyze trends

Figure 12. Schematic of the overall idea of the topic modeling

Figure 13. (a) Word cloud for transportation topic “traffic management” (b) Word cloud for transportation topic “accessibility”

Figure 14. (a) World cloud for AI topic “numerical methods and optimization” (b) Word cloud for AI topic “Advanced Machine Learning”

Figure 15. Overlap within transportation topics

Figure 16. Overlap within AI topics

Figure 17. Interdependencies within transportation topics

Figure 18. Interdependency of traffic management with other transportation topics

Figure 19. Interdependency of winter road management with other transportation topics

Figure 20. Sankey plot of transportation problems solved by AI topics

Figure 21. AI topics used in solving work-zone analysis

Figure 22. Interdependency of commercial vehicle and freight operations with other transportation topics

Figure 23. Trends of different AI topics over the years. We can see some topics like big data analysis, advanced machine learning has positive trend while statistical machine learning has slight negative trend. Topics like Evaluation stays similar across years

Figure 24. Transportation areas across the selected projects

Figure 25. Distribution of Projects over the years

Figure 26. A typical AI ecosystem with multiple components, including data processing pipeline, human-in-the-loop interaction, and development for AI-based systems

Figure 27. Typical workflow of an AI deployment process with six components (Adapted from Volet, 2018)

Figure 28. An example dashboard from Power BI that can summarize data from tabular data and link them to maps and other modalities. Image from Antdata (2021)

Figure 29. Key elements related to data annotation tools (CloudFactory, n.d.)

Figure 30. Various commercial data annotation tools and their supported data types (CloudFactory, n.d.)

Figure 31. Various commercial data annotation tools and their supported data types and capabilities (CloudFactory, n.d.)

Figure 32. A developer needs to guarantee the performance of an algorithm in the targeted image. The same image may produce different results for different algorithms

Figure 33. Number of responses on AI integration by the DOTs

Figure 34. Number of responses on challenges faced by DOTs

Figure 35. Project task outline

Figure 36. Top transportation research areas identified by workshop participants

Figure 37. Challenges faced at DOT level

Figure 38. Type of Organizations needed by DOTs

Figure 39. Difficult in determining if AI program is ready for implementation

List of Tables

Table 1. List of milestones (M) and deliverables (D)

Table 2. Prioritize the ideas from one to six for workforce and infrastructure needs, readiness, and evaluation of AI programs

Table 3. Prioritize ideas from one to eight for current practices of AI in transportation and challenges faced by DOTs

Table 4. Rank the Roadmap ideas based on the likeliness of receiving funding

Table 5. Final research problem statements, objectives and areas

Table 6. Problem statement potential partnerships and expected budget and duration of each research problem statement proposed

Table 7. Research roadmap timeline to show the temporal relations between the projects. For more details on dependencies, please refer to the text

Table 8. Journal articles in the report

Table 9. Definition of transportation AI topics

Table 10. Definition of AI topics used in this project

Table 11. Top five AI topics used for transportation topics

Table 12. Associations Within Transportation Topics. We presented the top five transportation topics that are seen to have strong co-occurrence in research

Table 13. Number of AI topic papers having co-occurrence with transportation topics (Part A)

Table 14. AI Topics having co-occurrence with transportation topics (Part B)

Table 15. Correlation of normalized number of papers and years (Part A)

Table 16. Correlation of normalized number of papers and years (Part B)

Table 17. A cost-benefit analysis of different AI-based tool sets available for use

Table 18. Cost-benefit analysis for big data management

Table 19. Cost-benefit analysis of computing resources for AI applications

Table 20. Grouping the roadmap ideas by research focus areas

Table 21. Prioritize the ideas from one to six for workforce and infrastructure needs, readiness, and evaluation of AI programs

Table 22. Prioritize ideas from one to eight for current practices of AI in transportation and challenges faced by DOTs

Table 23. Rank the Roadmap ideas based on the likeliness of receiving funding

Table 24. Grouping the roadmap ideas by research focus areas

Table 25. Project ideas with corresponding research areas

Table 26. Final Research Problem Statements, Objectives, and Areas. (1) workforce development and infrastructure development, (2) readiness and evaluation of AI, (3) challenges in adopting AI, (4) current practices and prioritization, (5) external collaboration, and (6) equity, policy & planning

Table 27. Problem statement potential partnerships and expected budget and duration of each research problem statement proposed

Table 28. Risk rating and probability definitions

Table 29. Challenge matrix

Table 30. Typical roles for AI personnel (Source: GSA, 2022)