Collaborators

Active Collaborations

  • Accessible Path Mapping for All: Leveraging ScooterLab for Multimodal Wheeled Mobility Analytics
    Team: Vaskar Raychoudhury, Md Osman Gani, Nadim Mahmud
    Affiliation: Miami University (Department of Computer Science and Software Engineering); University of Maryland, Baltimore County (Department of Information Systems)
    Description: This project leverages ScooterLab's micromobility-sensing infrastructure to support accessible path routing and navigation for wheelchair users and others with limited mobility. The team investigates environmental and surface-level features (e.g., roughness, slope, path barriers, and facilities), integrates ScooterLab data with the MyPath AI-based routing platform, and develops cross-modal data fusion methods between e-scooter and wheelchair sensor trajectories to improve real-world accessible routing and labeling.
  • Scooting in the Heat: E-Scooters as Sensors and Mobility Enablers During Periods of Extreme Heat
    Team: Rounaq Basu
    Affiliation: Georgia Institute of Technology (School of City & Regional Planning)
    Description: This project examines how e-scooter users adapt during periods of extreme heat and how thermal comfort and environmental exposure can be measured and validated using high-resolution, ground-level data. Using ScooterLab environmental sensor data (temperature, humidity, air quality), audio data, GPS data, and participant surveys/interviews, the study analyzes changes in trip patterns, route choice, and exposure to hazardous environmental conditions to inform climate-resilient transportation planning.
  • Integrating Heat and Air Quality Data into ScooterLab
    Team: Esteban Lopez Ochoa
    Affiliation: UT San Antonio (Urban and Regional Planning and Architecture)
    Description: The project combines stationary environmental sensor data with scooter-based sensing, explores adding environmental sensors to measure exterior ridership conditions on the fleet, and compares/validates ridership heat data against stationary sensors. A core goal is to use the scooter fleet to sense vulnerable neighborhoods without stationary coverage so communities and policymakers have better data for understanding extreme heat and air pollution in the built environment.
  • Calibrating Affordable Environmental and Air Quality Sensors on Scooters for Urban Climate Monitoring
    Team: Farzad Hashemi, Parisa Najafian
    Affiliation: UT San Antonio (School of Architecture and Planning)
    Description: This work introduces SCOOT-sense, a framework that turns an electric scooter into an affordable and accurate mobile sensing platform for urban microclimate monitoring. Using low-cost onboard sensors for temperature, humidity, and particulate matter with GPS, and calibrating against reference instruments using machine learning models, the project demonstrates high-fidelity pedestrian-level mapping of heat and air quality across diverse urban settings in San Antonio.
  • Toward Smarter Mobility: AI-Powered Safety Insights for AVs and Vulnerable Road Users
    Team: Shunhua Bai, Mason Cantu, Mahin Ramezani
    Affiliation: Texas A&M Transportation Institute (Center for Efficient Mobility University Transportation Center project)
    Description: This project investigates safety interactions between autonomous vehicles (AVs) and vulnerable road users (VRUs), including pedestrians, cyclists, and e-scooter riders, using advanced AI and data-fusion methods on high-resolution real-world data. A central component is ScooterLab e-scooter sensor data to detect abrupt maneuvers (e.g., sudden braking, rapid acceleration, sharp turns), which are analyzed alongside AV trajectory data to identify risk hotspots, built-environment factors, and behavior patterns that can inform safer urban mobility systems. The work is currently in its initial phase, focused on comprehensive literature review to guide subsequent data analysis.
  • LiDAR-Based Mapping and Object Tracking: Leveling the Plain-Field for Ethical and Open Urban Sensing
    Team: Esteban Lopez Ochoa
    Affiliation: UT San Antonio (Urban and Regional Planning and Architecture)
    Description: This project develops an open, low-cost, LiDAR-only workflow for urban mapping and urban sensing (object tracking and motion analysis). The approach emphasizes privacy-preserving data collection, transparent and ethical data practices, and scalable open-source pipelines that can support distributed city-level sensing and analysis.