View Important Policies and System Requirements for this course

Interested in registering 5 or more engineers for a course? Contact us for information and rates.

INSTRUCTORS: 
Fengze Yang
Zhipeng Bao
Stanley Young

Purpose and Background

These presentations were recorded at the International Conference on Transportation & Development 2025.

Independent Mobility GPT: A Multi-Agent LLMs Framework for Mobility Analysis (19 minutes)

This presentation introduced a novel framework called Independent Mobility GPT, which uses a multi-agent system of large language models (LLMs) to enhance traffic and mobility analysis. By automating the querying, data processing, and code generation phases, this AI-powered system reduces the time and expertise required for traditional traffic data analysis. It uses a structured agent architecture, including input validation, database interaction, and supervision agents, to iteratively refine results. A case study on Seattle’s I-405 and SR-520 demonstrated the model’s ability to predict traffic patterns during closure events. The framework not only automates mobility analytics but also improves prediction accuracy through feedback loops and optimization. Future developments aim to integrate visual data inputs and fine-tuned models for even greater performance.

Your Ride Your Rules: Psychology and Cognition Enabled Automated Driving Systems (14 minutes)

This talk focused on building trust in autonomous vehicles (AVs) through personalized and explainable interactions using psychological and cognitive inputs. The presenter outlined key limitations in current AV systems, such as lack of personalization, transparency, and responsiveness in ambiguous situations. Their proposed system integrates AI agents, the Psychologist, Driver, and Coordinator, that collectively interpret human emotions and instructions, adapt vehicle behavior in real-time, and provide understandable explanations to occupants. Using multimodal data like facial expressions, EEG signals, and voice inputs, the system allows passengers to influence AV behavior, improving comfort, trust, and safety. Case studies demonstrated how vehicles adapt to changing emotions, interact with pedestrians, and navigate out of ambiguous traffic situations like roundabouts or roadblocks.

Vehicle Automation Benefits and Challenges for Passenger Transport System Beyond Automated Driving (17 minutes)

This presentation examined the broader infrastructure, operational, and societal challenges surrounding vehicle automation beyond simply making cars drive themselves. While companies like Waymo and Baidu are advancing AV technologies, scaling these systems into public mobility solutions introduces major hurdles, including fleet management, charging infrastructure, user interfaces, emergency protocols, and multi-party ride-sharing. The speaker emphasized that automation alone isn’t sufficient; instead, a system-of-systems approach is needed to address real-world complexities. Case examples highlighted how issues like fleet electrification, ambiguous customer interactions, and ride-sharing discomfort can impede adoption. Drawing from transit history and real-world AV rollouts, the talk outlined strategies for cities and operators to prepare for widespread AV integration.

Benefits and Learning Outcomes

Upon completion of this course, you will be able to:

• Explain how a multi-agent LLM framework improves traffic data analysis and mobility insights.
• Describe the process of optimizing analysis outputs using iterative supervision and AI feedback loops.
• Identify the limitations in current autonomous driving systems regarding personalization and transparency.
• Discuss how AI agents and psychological signals are used to adapt AV behavior to individual passenger preferences in real time.
• List the five key operational challenges that must be addressed to successfully implement automated vehicle systems in public transportation.
• Explain how system-level coordination and user experience design affect the scalability of autonomous mobility solutions.

Assessment of Learning Outcomes

Students' achievement of the learning outcomes will be assessed via a short post-test assessment (true-false, multiple choice, and/or fill in the blank questions).

Who Should Attend?

• Transportation Engineers
• Transportation Professionals
• Traffic engineers
• Highway engineers
• Materials engineers
• Construction engineers

How to Earn Your CEUs/PDHs and Receive Your Certificate of Completion

To receive your certificate of completion, you will need to complete a short post-test and receive a passing score of 70% or higher within 1 year of purchasing the course.

How do I convert CEUs to PDHs?

1.0 CEU = 10 PDHs [Example: 0.1 CEU = 1 PDH]