Featured

Updated from an original post on 14 Apr 2026. I recently integrated a Pull Request from OldCrow on our Web Shepherd web application. They have made substantial improvements to scalability, replacing the original O(n²)-complex interaction loop with spatial indexing and other techniques. This extends the practical range from a few hundred agents to a few thousand agents while maintaining smooth real-time performance in most Web browsers. To learn more: The full interactive demo has been updated A slimmer version for website integration still uses the old technique, but will be updated shortly Code and Documentation has been updated on GitHub References Van Havermaet, S., Simoens, P., Landgraf, T., & Khaluf, Y. (2023). Steering herds away from dangers in dynamic environments. Royal Society Open Science, 10(5), 230015. ...

click for time travel Background The Great Canadian Hairy Star Party was an educational initiative produced by ScienceWeb in 1996. It featured observations, sketches, and other artwork from students across Canada related to Comet Hyakutake, a spectacular comet that passed close to Earth in March of that year. Centre Consolidated Elementary School in Lunenburg, Nova Scotia participated by having students submit their personal observations on a dedicated website. I was one of those students. ...

This project implements a Machine Learning (ML) pipeline for the Adver-City synthetic dataset. The dataset is designed for investigating cooperative perception in autonomous vehicles. Overall, this project enables efficient, reproducible modelling of the Adver-City dataset through ML workflows. We have chosen to train a model to identify weather conditions (clear, fog, rain) from nighttime images. Note: full GitRepo available here. Figure 1: Example Scenario (foggy) from the Adver-City dataset. The dataset contains images of a variety of weather conditions (clear, fog, rain) and times of day (day, night). In this project we focus on classifying weather conditions from nighttime images. Operation The project is organized into four main stages. Depending on what your goal is (data exploration, ingestion, or training), the notebooks indicated below describe how to run each stage of the workflow. ...