Raising Awareness of Artificial Intelligence for Transportation Systems Management and Operations

Printable version [PDF 2.1 MB]
You may need the Adobe® Reader® to view the PDFs on this page.
Contact Information: Operations Feedback at OperationsFeedback@dot.gov

U.S. Department of Transportation
Federal Highway Administration
Office of Operations
1200 New Jersey Avenue, SE
Washington, DC 20590
ops.fhwa.dot.gov

FHWA-HOP-19-052

December 2019

---

Table of Contents

[ Foreword ] | [ Notice and Quality Assurance Statement ] | [ Technical Report Documentation Page ] | [ SI (Modern Metric) Conversion Factors ]

Executive Summary

Chapter 1. Introduction and Background

Chapter 2. Categories of Artificial Intelligence Technologies

Introduction

General Categories of Machine Learning

Chapter 3. Commercialization of Artificial Intelligence Technologies

State of the Practice and Commercialization of Artificial Intelligence

Summary of Commercial Artificial Intelligence Development

Chapter 4. Artificial Intelligence for TSMO Applications

Artificial Intelligence for Incident Detection

Artificial Intelligence for Ramp Metering

Chatbots for Natural Language Question and Answering

Traffic Prediction and Traveler Information

Unmanned Aerial Systems Used by State Departments of Transportation

Summary of this Chapter

Chapter 5. Considering Artificial Intelligence Technologies in Transportation Planning, Deployment, and Operations

Systems and Technology

Staffing and Organization

Business Processes

Collaboration with Other Departments and Agencies

Summary

References

List of Figures

Figure 1. Photo. The first chatbot interaction.

Figure 2. Diagram. A semantic network representation for just a few words and concepts.

Figure 3. Flowchart. Example of a neural network.

Figure 4. Flowchart. Supervised machine learning algorithm development.

Figure 5. Graph. Example of fuzzy logic sets.

Figure 6. Photo. The Deep Blue chess-playing supercomputer in 1997.

Figure 7. Graph. The problem of finding a local optimal solution instead of the global minimum or maximum using simplified search methods.

Figure 8. Screenshot. Bill Gates' tweet regarding OpenAI's defeat of expert human players.

Figure 9. Photo. Delivery drone prototype.

Figure 10. Photo. Interior of a driverless car prototype.

Figure 11. Photo. Automated identification of traffic features from airborne unmanned aerial systems.

Figure 12. Chart. Information technology considerations for on-premise, infrastructure-as-a-service, platform-as-a-service, and software-as-a-service implementations.

Figure 13. Photo. Photo. Driverless shuttle.

Figure 14. Photo. UAS for construction inspection.

Figure 15. Screenshot. Google DialogFlow setup for the "performance report."

Figure 16. Chart. The Delaware Department of Transportation concept of how artificial intelligence can apply to the transportation management centers working process.

Figure 17. Photo. Network modeled by artificial intelligence in Delaware.

Figure 18. Diagram. Vehicle re-identification using inductive loop signatures matched by a neural network model.