Digital twin for managing the curb and reducing congestion

Curb space in dense urban cores is under intense pressure from e-commerce deliveries, service vehicles, ride-hailing, and passenger pick-up/drop-off. Without a data-driven view of curb regulations and heterogeneous delivery demand, cities face double-parking, spillback congestion, and safety conflicts. This project addresses the gap by creating an open-data-based digital twin that links curb regulations, observed curb activity proxies (differentiating between commercial and residential delivery behaviors), and network performance to support actionable curb management decisions. This project is part of a larger project. The larger project is developing a proof-of-concept strategic curb digital twin to analyze curb demands and test curb management solutions. The digital twin will act as a virtual replica of a portion of downtown Los Angeles (DTLA), built using publicly available data to ensure the model is transparent, replicable, and directly useful to public agencies. This approach is centered on a transparent, agent-based simulation model. The research team will construct a high-fidelity virtual environment by integrating multiple open datasets and agency records, including geographic information system (GIS) road networks from the LA GeoHub, land use and business listings from DataLA, LADOT signal timing charts for realistic traffic control, and network details from OpenStreetMap. This allows the team to simulate crucial behaviors, such as a delivery driver’s search for parking calibrated using parking citation data, or a private car's decision process calibrated using open-source global positioning system (GPS) Exchange Format (GPX) data. This creates a reliable virtual testbed to evaluate various management strategies. The team can introduce and assess policies such as dynamic pricing for loading zones and passenger car parking, or time-of-day restrictions, and observe their combined effect on delivery efficiency and overall traffic congestion. The prototype will serve as proof-of-concept for this multi-agent simulation, establishing a foundational tool for holistic curb management. This Phase 1 project focuses on freight deliveries and expands the larger project by introducing heterogeneity into freight delivery demands. Retail establishments may receive relatively large shipments and restaurants may receive daily shipments from multiple suppliers. Residents receive small package deliveries. Different types of deliveries imply differences in delivery vehicle dwell time, demand for a nearby parking space, and delivery route configurations. The team will use land use, employment, and demographic data to generate freight delivery demands. The team then classify these demands based on stop dwell times and commercial vs residential, because of the temporal differences in these demands. The different demands are operationalized as different agents within the model.

• Record URL:
  • https://www.metrans.org/research/digital-twin-for-managing-the-curb-and-reducing-congestion

Language

• English

Project

• Status: Active
• Funding: $45,000.00
• Contract Numbers:

  69A3551747109

• Sponsor Organizations:

  Office of the Assistant Secretary for Research and Technology

  University Transportation Centers Program
  Department of Transportation
  Washington, DC  United States  20590
• Managing Organizations:

  Pacific Southwest Region University Transportation Center

  University of Southern California
  Los Angeles, CA  United States  90089
• Project Managers:

  Hong, Jennifer

• Performing Organizations:

  University of Southern California, Los Angeles

  University Park Campus
  Los Angeles, CA  United States  90089
• Principal Investigators:

  Giuliano, Genevieve

• Start Date: 20260101
• Expected Completion Date: 20260630
• Actual Completion Date: 0
• USDOT Program: University Transportation Centers Program

Subject/Index Terms

• TRT Terms: Congestion management systems; Curb side parking; Delivery service; Digital twins; Traffic congestion; Traffic simulation
• Geographic Terms: Los Angeles (California)
• Subject Areas: Data and Information Technology; Freight Transportation; Highways; Operations and Traffic Management; Planning and Forecasting;

Filing Info

• Accession Number: 01981629
• Record Type: Research project
• Source Agency: Pacific Southwest Region University Transportation Center
• Contract Numbers: 69A3551747109
• Files: UTC, RIP
• Created Date: Mar 3 2026 4:23PM