• INSPIRE Lab
  • Research
  • Team
  • Publication
  • Teaching
  • News
  • Skip to primary navigation
  • Skip to main content
  • Skip to primary sidebar
  • Skip to footer
UT Shield
The University of Texas at Austin
  • INSPIRE Lab
  • Research
    • Research Areas
    • Facilities
    • Awards & Grants
    • Opportunities
  • Team
    • Principal Investigator
    • Current Students
    • Alumni
  • Publication
    • Publications by topic
    • Publications by year
  • Teaching
  • News
    • Lab Updates
    • Conferences

May 17, 2026, Filed Under: Uncategorized

CTR-2026

News / Lab Updates / CTR Symposium 2026
April 8, 2026

INSPIRE Lab Presents Two Posters at CTR Symposium 2026

— EV evacuation and autonomous vehicle behavior discovery

On April 8, 2026, INSPIRE Lab presented two research posters at the Center for Transportation Research (CTR) Annual Symposium at UT Austin, showcasing recent work on electric vehicle evacuation and autonomous vehicle identification.

Presentation 1 EV Evacuation

Express Charging Lanes for Electric Vehicle Evacuation

Presenter: Mohammad Reza Ghorbanali Zadegan · Advisor: Dr. Zhaomiao Guo

The poster proposed express charging lanes to separate EVs by charging demand at charging stations during evacuations. Two operational frameworks were analyzed — System Optimal (centralized) and User Equilibrium (decentralized) — demonstrating that express lanes can reduce total evacuation delay and improve system performance without adding new infrastructure.

Reza presenting Express Charging Lanes poster at CTR 2026
Reza presenting alongside Dr. Guo at the CTR Symposium
Presentation 2 Autonomous Vehicles

SVBRD-LLM: Self-Verifying Behavioral Rule Discovery for Autonomous Vehicle Identification

Presenter: Xiangyu Li · Advisor: Dr. Zhaomiao Guo

The poster introduced a zero-shot LLM framework that discovers and verifies interpretable behavioral rules for autonomous vehicle (AV) analysis from roadside traffic videos. Using YOLOv26 + ByteTrack trajectories and kinematic/context features, the framework builds a verified library of 20 rules and achieves strong AV identification performance — offering a transparent alternative to opaque classifiers.

Xiangyu presenting SVBRD-LLM poster at CTR 2026
Xiangyu presenting the SVBRD-LLM framework with Reza
Related
EVs & Power Systems → Autonomous Mobility → Infrastructure Resilience → All Publications →
← Back to Lab Updates

Primary Sidebar

Recent Posts

  • CTR-2026
  • Xiangyu welcome
  • CTR 2025

Footer

FOOTER SECTION ONE

FOOTER SECTION TWO

FOOTER SECTION THREE

  • Email
  • Facebook
  • Instagram
  • Twitter

UT Home | Emergency Information | Site Policies | Web Accessibility | Web Privacy | Adobe Reader

© The University of Texas at Austin 2026