Improving Congestion Impact Estimation

The purpose of this project is to develop an accurate estimation of different congestion reduction schemes by creating more accurate digital twins. Current schemes are often benchmarked in micro-simulators but inaccurate micromodels of driver and pedestrian behavior can lead to the impacts being drastically over or under-estimated. Our goal is to improve these micro-models using new techniques in imitation learning. These new micro-models will be ported into SUMO, a standard micro-simulator, and used to recompute the expected benefits of popular schemes for tackling congestion. They will also be tested on the Waymo Sim Agents Challenge to see if they are competitive with existing state-of-the-art ML-based models. The proposed work does not directly tackle congestion but focuses on enabling researchers and policy-makers to more effectively tackle congestion. Micro-simulator are used to investigate the impact of an intervention and consequently overestimates in their impact can lead to improper estimation of the impact of an intervention per dollar.

• Record URL:
  https://c2smarter.engineering.nyu.edu/improving-congestion-impact-estimation/

Language

• English

Project

• Status: Active
• Funding: $137285
• Contract Numbers:

  69A3551747124

• 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:

  Connected Communities for Smart Mobility Towards Accessible and Resilient Transportation for Equitably Reducing Congestion (C2SMARTER)

  New York University
  Brooklyn, New York  United States  11201
• Project Managers:

  Pohl, Lizzie

  Chase, Holly

• Performing Organizations:

  Connected Communities for Smart Mobility Towards Accessible and Resilient Transportation for Equitably Reducing Congestion (C2SMARTER)

  New York University
  Brooklyn, New York  United States  11201

  New York University Tandon School of Engineering

  6 Metrotech Center
  Brooklyn, NY  United States  11201
• Principal Investigators:

  Vinitsky, Eugene

• Start Date: 20240901
• Expected Completion Date: 20251130
• Actual Completion Date: 0
• USDOT Program: University Transportation Centers

Subject/Index Terms

• TRT Terms: Digital twins; Traffic congestion; Traffic simulation
• Identifier Terms: SUMO (Traffic simulation model)
• Subject Areas: Data and Information Technology; Operations and Traffic Management; Planning and Forecasting;

Filing Info

• Accession Number: 01937748
• Record Type: Research project
• Source Agency: Connected Communities for Smart Mobility Towards Accessible and Resilient Transportation for Equitably Reducing Congestion (C2SMARTER)
• Contract Numbers: 69A3551747124
• Files: UTC, RIP
• Created Date: Nov 21 2024 4:47PM