<< Return to Webinar Files

Webinar Presentation

HTML version of the presentation
Image descriptions are contained in brackets. [ ]

Raising Awareness of Artificial Intelligence for Transportation System Management and Operations
(February 13, 2020)

Presenter: Douglas Gettman
Presenter’s Org: Kimley-Horn and Associates, Inc.

T3 webinars are brought to you by the Intelligent Transportation Systems (ITS) Professional Capacity Building (PCB) Program of the USDOT’s ITS Joint Program Office (JPO). References in this webinar to any specific commercial products, processes, or services, or the use of any trade, firm, or corporation name is for the information and convenience of the public, and does not constitute endorsement, recommendation, or favoring by the USDOT.

The slides in this presentation contain the USDOT Federal Highway Administration (FHWA) logo.

Slide 1: Overview

  • Introduction and background.
  • Categories of Artificial Intelligence (AI) technologies and a brief history of AI.
  • Commercialization of AI and state of the practice platforms.
  • Example applications of AI in transportation systems management and operations (TSMO).
  • Considerations for use of AI technologies for TSMO.

This webinar will raise your awareness of the potential for AI in TSMO.

Slide 2: Disclaimer

The U.S. Government does not endorse products or manufacturers. Trademarks or manufacturers’ names appear in this presentation only because they are considered essential to the objective of the presentation. They are included for informational purposes only and are not intended to reflect a preference, approval, or endorsement of any one product or entity.

Slide 3: AI and Transportation Operations

AI has potential for the next generation of transportation system management and operations.

  • AI technologies are maturing as commercially- available software services.
  • AI can provide enhancements to many different TSMO applications and functions.
  • Potential for automated vehicles and unmanned aerial systems in TSMO functions.
  • Two important considerations for AI for agencies:
    • Can AI enhance current capabilities?
    • Can AI enable new capabilities?

Slide 4: Improving Existing Capabilities with AI

  • Incident detection and management.
  • Traffic image analysis.
  • Traffic signal timing optimization.
  • Freeway ramp metering.
  • Natural language decision support.
  • Analysis of data from different sources.

Slide 5: Potential New Capabilities Enabled by AI

  • Automated unmanned aerial vehicle inspections and surveillance.
  • Automation of fleet operations.
  • Chatbot 511 and customer service applications.

[This slide contains a computer-generated image of two vehicles at an intersection. Each vehicle has a beam drawn from it to a traffic light. The traffic light has a beam drawn from it to something out of the image viewport. The image is a representation of vehicle-to-infrastructure (V2I) communication.]

Slide 6: What is Artificial Intelligence (AI)?

The term “artificial intelligence” is often used to describe machines (or computers) that mimic “cognitive” functions that humans associate with the human mind. The traditional problems (or goals) of AI research include reasoningknowledge representation, planning, learning, natural language processing, perception and the ability to move and manipulate objects.

Slide 7: What is Artificial Intelligence (AI)? (continued)

  • As machines become increasingly capable, tasks considered to require “intelligence” are often removed from the definition of AI.
  • Tesler’s Theorem: “Intelligence is whatever machines haven’t done yet.”
    • Larry Tesler is the godfather of the modern graphical user interface (GUI) at Xerox in the 1970s and AI researcher in the late 1960s.
  • Optical Character Recognition (OCR) was once “AI.” Now it can be purchased as part of a multi-function printer/copier/scanner for $40.

Slide 8: AI: Strong and Weak

  • “Strong” AI: mimicking human cognitive functions to a degree generally considered indistinguishable from a human, i.e. “self aware.”
    • Terminator, Blade Runner, Her, Age of Ultron, The Matrix, etc.
    • No system or technology is close to this yet, but many groups are chipping away at the building blocks.
  • Turing Test: If an AI cannot be distinguished from a human person in general conversation then the artificial entity is considered “intelligent.”
    • Chatbot agents creep closer by the year (Alexa, DrQA, Google Assistant, etc.).

Slide 9: AI: Strong and Weak (continued)

  • “Weak” or narrow AI: performing a specific function to a meeting or exceeding (and often vastly exceeding) human competency.
    • Playing Jeopardy.
    • Playing Atari games, Chess, Go, DoTA2 (Dawn of the Ancients).
    • Translating human speech to text.
    • Recognizing objects in images.
    • Driving on freeways and city streets.
    • Translating from one language to another.
    • Classifying and clustering data.

Slide 10: AI History

  • 1960s to 1970s
    • Playing checkers
    • Solving algebra problems
    • Speaking English
    • Optical Character recognition
  • 1980 to 1990s
    • Expert systems
    • Medical diagnosis
    • Neural networks
    • Fuzzy logic
    • Search algorithms
  • 2000 to 2010s
    • Chatbots
    • Image analysis
    • Game playing
    • Natural language
    • Commercialization
  • 2020 and beyond
    • Maturity
    • “Plug and Play”

Slide 11: Key AI Technologies for TSMO

  • Neural networks.
  • Imagery analysis systems.
  • Chatbots.
  • Natural language processing.
  • Structured Query Language (SQL) query generation.
  • Question-answering systems.
  • Self-driving and self-flying systems.

Slide 12: Neural Networks: a Foundational Element

[This slide contains a graphic flowchart of three inputs that pass through hidden layers, activation functions, and weighted sums to become two outputs.]

Slide 13: Supervised Learning

[This slide contains a Supervised Learning flowchart: (1) Labeled Observations feeds into (2) Training Set and (2) Test Set. (2) Training Set feeds into (3) Machine learning model. (2) Test Set and (3) Machine learning model feed into (4) Trained model, which feeds into (5) Performance results. (5) Performance results feeds back into (3) Machine learning model.]

Slide 14: Real-World Complexity

27 million connections, 250,000 trained parameters.

  1. Raw 4D driving scene
  2. Convolutional feature map
  3. Convolutional feature map
  4. Convolutional feature map
  5. Convolutional feature map
  6. 1154 neurons
  7. 100 neurons
  8. 50 neurons
  9. 10 neurons
  10. 10 neurons
  11. Steering and acceleration controls

[This slide contains a Real-World Complexity flowchart, whose order is listed above.]

Slide 15: Fuzzy Logic

  • Input variables.
    • Volume, Occupancy on mainline.
    • Volume on ramp.
  • Output variable.
    • Metering rate.
  • Codify inputs and outputs as natural language.
    • “Very high,” “high,” “medium,” “low.”
  • IF…THEN rules are fuzzy.
    • If mainline occupancy is HIGH and ramp volume is LOW then metering rate is LOW.

Not really “AI” but better at translating messy natural language IF…THEN problems to numerical answers.

Slide 16: Solution Search

  • Genetic algorithms.
  • Evolutionary algorithms.
  • Ant colony optimization.

Not really “AI” but better at finding better solutions.

[This slide contains a line chart of global maximum/minimum and local maximum/minimums.]

Slide 17: Solution Search (continued)

  • Solution search is sometimes referred to as machine learning or training.
  • IBM DeepBlue chess-playing computer is an example of a purpose-built weak-AI computer for doing one thing very well.
  • Neural network parameters are trained by use of solution search methods generally called “back propagation.”

Slide 18: Unsupervised Learning

[This slide contains a screenshot of a Bill Gates tweet that reads “#AI bots just beat humans at the video game Dota 2. That’s a big deal, because their victory required teamwork and collaboration - a huge milestone in advancing artificial intelligence.”]

Slide 19: Robotics and Driverless Systems

  • What data will automated vehicles provide?
  • 3D LiDAR (light detection and ranging)/video scans of assets.
  • BVLOS (Beyond visual line of sight) surveillance.
  • Equipment delivery.
  • Crash abatement and safety protection.
  • Rural applications.

[This slide contains two images: (1) a 3D LiDAR image of an intersection and (2) a photo of a drone delivering equipment.]

Slide 20: Computer Vision Processing

  • Computer vision process is becoming a semi-mature market with many companies entering the space to provide services for TSMO.
  • Some providers require their own cameras.
  • Some providers can use “any camera.”
  • Likely that “any camera” solutions will continue to mature since replacement of cameras is not trivial and expensive for IOOs (Infrastructure Owner-Operators).

Slide 21: Commercialization

  • More than 1,000 companies are involved in various aspects of AI.
  • Providing AI capabilities now is like providing Big Data capabilities five years ago.
  • Widespread use of AI chatbots (Alexa, Google Assistant, DrQA).
  • All major cloud service providers have AI suites.

Slide 22: Commercialization (continued)

  • On-Premise
    • DOT Manages
      • Applications
      • Data
      • Runtime
      • Middleware
      • O/S
      • Virtualization
      • Servers
      • Storage
      • Networking
  • Infrastructure (as a Service)
    • DOT Manages
      • Applications
      • Data
      • Runtime
      • Middleware
      • O/S
    • Vendor Manages
      • Virtualization
      • Servers
      • Storage
      • Networking
  • Platform (as a Service)
    • DOT Manages
      • Applications
      • Data
    • Vendor Manages
      • Runtime
      • Middleware
      • O/S
      • Virtualization
      • Servers
      • Storage
      • Networking
  • Software (as a Service)
    • Vendor Manages
      • Applications
      • Data
      • Runtime
      • Middleware
      • O/S
      • Virtualization
      • Servers
      • Storage
      • Networking

Most commercial AI today is SaaS.

Slide 23: Google Cloud AI

  • TensorFlow - neural network development and training.
  • Cloud AutoML - neural network architecture.
  • DialogFlow - chatbots.
  • Actions - chatbots.
  • Firebase - databases.
  • Duplex - context-sensitive conversations.
  • Temporal Action Localization - assigning meaning/intent to video.

Slide 24: Microsoft Azure AI

  • “Cognitive Services.”
  • Neural networks training/development.
  • AI chatbots (Cortana).
  • Pre-built neural networks for common apps.
    • Object recognition in images.

Slide 25: Microsoft Azure AI (continued)

  • Labs” - alpha tools currently pre-release.
  • Project knowledge exploration.
    • Turning natural language questions into SQL queries.
  • Project anomaly finder.
    • Analyzing and reporting problems/anomalies in data streams without extensive coding.

Slide 26: Amazon AI

  • Lex - Alexa.
  • Polly - Alexa.
  • Rekognition - imagery analysis.
  • SageMaker - neural network construction, training, etc.
  • Preview services.
    • Forecast: “deploy neural networks and machine learning with no expertise.”

Slide 27: Procuring AI

  • Not easy to determine what something will cost to build or use long-term.
  • More likely that AI applications and services will be purchased from a vendor/developer/university.
    • They build the apps you want on top of services and tech from Google, Amazon, Microsoft, others.
  • Purchased “as a service.”

Slide 28: AI Hype Cycle

[This slide contains a line graph of the AI “hype cycle.”]

Slide 29: Future of Commercial AI

  • Hype in AI is at a peak.
  • General future trends:
    • AI-specific hardware/chips (ex: Tesla).
    • Migration of centralized machine learning to edge IoT (internet of things) devices.
    • Interoperability of NN models - Open Neural Network Exchange (ONNX).
    • Automation of the process of NN training.
    • Increasing capabilities of chatbots.
    • Consumer-ready driverless services/vehicles.
    • Democratization of AI services to non-professionals (software, database, and statistics experts).
    • Automated unmanned aerial vehicles.

Slide 30: Example AI applications in TSMO

  • AI for incident detection.
  • AI (fuzzy logic) for ramp metering.
  • Chatbots for question and answering.
  • Traffic prediction & integrated corridor management (ICM).
  • Signal timing plan optimization.

Slide 31: Incident Detection

  • Nevada Department of Transportation (DOT) and Florida DOT.
    • Waycare.
    • Reported improvements using neural networks to analyze and detect incident conditions.
  • Iowa DOT.
    • Iowa State University (TIMELI).
    • Rural detection.
    • Currently in pilot implementation.
    • Positive feedback from Iowa DOT staff.

Slide 32: Ramp Metering

  • Washington State DOT.
    • Has used fuzzy logic for more than 15 years.
    • More than 200 ramp meters use the fuzzy logic system.
    • Reduced software coding of calibration parameters, traffic modeling, error/anomaly handling.
  • Caltrans District 4 (Bay Area).
    • I-80 ATM (Active Traffic Management).
    • Benefits or comparison with traditional ramp metering algorithms has not been evaluated (or released publicly at time of report).

Slide 33: Chatbot question and answering

  • MTC (Metropolitan Transportation Commission) 511 (Bay area).
    • Invoke 511 through Alexa.
    • Standard 511 queries as calling 511 through phone.
  • Virginia DOT “hackathon.”
    • “Talk DOT” app: Alexa Skill to ask questions of the Virginia DOT database as if you were using the Web interface.
  • Surprise, AZ/Kimley-Horn.
    • Google Assistant app to query the Kadence adaptive control system of current or past performance (ATSPMs - automated traffic signal performance measures) of individual signals or arterials.

Slide 34: Google Assistant Training Phrases

[This slide contains a screenshot of a Performance Report from Google’s Dialogflow which is displaying the “Training phrases” section and the “Actions and parameters” section.]

Slide 35: Unmanned Aerial Vehicles (UAV)

  • 35 of 50 State DOTs now have a UAV program as of March 2018.
  • 20 active and 15 in research phase.
  • Piloted UAVs for asset surveillance.
  • North Carolina DOT/North Carolina Highway Patrol.
    • Crash reconstruction data collection.
    • Reduced costs from $13,000 to $4,000.
    • Reduced time from two hours to 30 minutes.
    • Alpha research phase.

Slide 36: Considering AI in TSMO

  • Identify clear objectives for AI applications.
  • Thorough research of systems and technology required.
  • Evaluate staffing and organization needs for project deployment.
  • Evaluate how AI will modify business processes.
  • Identify collaboration with other agencies/divisions/departments that can reduce costs and increase value.

Slide 37: Considering AI in TSMO (continued)

  • Big-brother privacy and security issues and policy.
  • Short supply of highly-skilled personnel to implement AI applications (public-private partnerships).
  • Ownership of data (particularly with public-private partnerships).

Slide 38: Self-Assessment Checklists

Refer to report for full content.

Is there flexibility to acquire agency staff with these skill sets (1.e., redefine roles, expand technical staff groups)? What retention issues might we experience with highly-skilled staff?
Do we have a mechanism to obtain these skills if they cannot be addressed by current staff or roles (i.e., contract/outsource, training)?
Are there any operational or policy limitations on our agency deploying AI applications? How do we remove such barriers if they exist?
Do we have significant understanding or are we hearing about peer agency programs and experiences, national trends, and AI technologies?
What training will staff need to develop, deploy, operate, and maintain AI systems?
Will there be a commitment from agency leadership to continue with AI systems?

Slide 39: Where to Start?

  • Interdepartmental workshop on AI.
  • Determine a short-list of high-priority applications that meet regional goals.
  • Develop a program plan for research, development, and implementation.
  • Consider connections of AI apps with automated and connected vehicle programs.

Slide 40: Raising Awareness Document

Raising Awareness of Artificial Intelligence for Transportation Systems Management and Operations
September 2019

Available in National Transportation Library soon.

↑ Return to top


Get technical support

Technical Assistance is available to Federal, State and local transportation agencies through:

ITS Peer Program - The ITS Peer-to-Peer Program puts you in touch with technical experts or experienced peers.

ITS Help Line - The ITS Help Line provides technical support by email or telephone at 866-367-7487.


go to twittergo to email