Fingerprinting New York City's Scaffolding Problem with Longitudinal Dashcam Data

Scaffolds, also called sidewalk sheds, are intended to be temporary structures to protect pedestrians from construction and repair hazards. However, some sidewalk sheds are left up for years. Long-term scaffolding becomes eyesores, creates accessibility issues on sidewalks, and gives cover to illicit activity. Today, there are over 8,000 active permits for scaffolds in NYC; the more problematic scaffolds are likely expired or unpermitted. This research uses computer vision on street-level imagery to develop a longitudinal map of scaffolding throughout the city. Using a dataset of 29,156,833 dashcam images taken between August 2023 and January 2024, we develop an algorithm to track the presence of scaffolding over time. We also design and implement methods to match detected scaffolds to reported locations of active scaffolding permits, enabling the identification of sidewalk sheds without corresponding permits. We identify 850,766 images of scaffolding, tagging 5,156 active sidewalk sheds and estimating 529 unpermitted sheds. We discuss the implications of an in-the-wild scaffolding classifier for urban tech, innovations to governmental inspection processes, and out-of-distribution evaluations outside of New York City.

Webots.HPC: A Parallel Robotics Simulation Pipeline for Autonomous Vehicles on High Performance Computing

In the rapidly evolving and maturing field of robotics, computer simulation has become an invaluable tool in the design process. Webots, a state-of-the-art robotics simulator, is often the software of choice for robotics research. Even so, Webots simulations are often run on personal and lab computers. For projects that would benefit from an aggregated output dataset from thousands of simulation runs, there is no standard recourse; this project sets out to mitigate this by developing a formalized parallel pipeline for running sequences of Webots simulations on powerful HPC resources. Such a pipeline would allow researchers to generate massive datasets from their simulations, opening the door for potential machine learning applications and decision tool development. We have developed a pipeline capable of running Webots simulations both headlessly and in GUI-enabled mode over an SSH X11 server, with simulation execution occurring remotely on HPC compute nodes. Additionally, simulations can be run in sequence, with a batch job being distributed across an arbitrary number of computing nodes and each node having multiple instances running in parallel. The implemented distribution and parallelization are extremely effective, with a 100\% simulation completion rate after 12 hours of runs. Overall, this pipeline is very capable and can be used to extend existing projects or serve as a platform for new robotics simulation endeavors.