Traditional sidewalk performance evaluation has primarily relied on flow metrics, such as level of service, that treat pedestrians as uniform units, similar to vehicles on a highway. These methods typically rely on basic pedestrian intersection or screenline counts, which capture pedestrians at a single point location. More recently, advanced sensors such as video- and LIDAR
This project investigates how roadside LiDAR sensing and generative scene prediction models can support more informative and uncertainty-aware traffic safety assessment at urban intersections. Conventional surrogate safety measures, such as time-to-collision and post-encroachment time, are widely used to identify potential traffic conflicts. However, these measures are primarily based on observed kinematic relationships and may not
This project builds on results from prior TBD Center projects to advance the development of a multi-scale, synthetic data-based simulation framework for evaluating urban freight policy and infrastructure interventions. In Phase 1, we conducted a comprehensive review of existing freight data sources and machine learning- and generative-AI based approaches to address persistent data gaps for
Integrating Microsimulation in a Multi-scale Local Freight Activity Model Read More »
Over the last decade, many shoppers in the U.S. and around the world have quickly become reliant on home-based deliveries of household and retail goods. While growth in e-commerce is easily demonstrated from retail sales records, relevant activity trade-offs and resulting impacts on passenger and freight travel activity remain less well-understood. Some home deliveries are
Measuring the Motivators of Home Delivery Decisions Read More »
Employing the state-of-the-art research on attention and feedback mechanisms, especially with vision language models (VLMs), has not been fully explored previously for transportation behavior analysis, especially for the analysis of a variety of pedestrian behaviors related to sidewalks and streets. This project will expand our previous project exploring top-down visual attention for transportation behavior analysis
The proliferation of 3D and video data from urban intersections offers a unique opportunity to analyze and protect vulnerable road users (VRUs). However, the effectiveness of modern detection models like PointPillar or CenterPoint is limited by the availability of high-quality labeled data. In Year 2, we demonstrated the feasibility of multimodal sensing using LiDAR and
In most urban areas, there is currently a misalignment between difficult-to-measure freight vehicle demands and infrastructure capacities (e.g., parking and loading zones) to accommodate these demands. This misalignment typically results in high costs for industry (e.g., wasted time, wasted fuel, parking fines) as well as in congestion, traffic conflicts, and other externalities for the surrounding
Taking a two-phase approach, this study aims to investigate the nature and scale of household-based service demands, and to establish a baseline for better data collection and modeling of this under-studied component of travel demand in future research efforts. Part 1 of this project will utilize data from the recently completed Transportation Heartbeat of America
The Home as a Trip Attractor: An Exploratory Study of Residential Service Demand Read More »
Every day, New York City hosts countless events ranging from street festivals and protest marches to unexpected incidents and major sporting events. Each of these events may create ripples through the city’s complex transportation network, affecting how millions of New Yorkers move around their city. But what if we could predict these ripples? This proposal
From Reactive to Predictive: Modeling Urban Event Impacts on Transportation Systems Read More »
This project stands at the intersection of cognitive psychology, AI and computer vision, and transportation safety and efficiency. By focusing on the nuanced ways in which humans allocate their visual attention, and how this can inform the development of artificial intelligence (AI) and machine learning (ML) to aid in self-driving cars, transportation safety automation, and
Exploring Top-Down Visual Attention for Transportation Behavior Analysis Read More »
