In order to successfully help young children, adults must understand their intentions. Similarly, for robots to provide effective support, they must be able to do this. We examined how adults and AI can infer intents from incomplete puzzles. We are interested in the reasoning strategies that emerge in reasoners and whether they predict success.  Furthermore, we seek to understand whether AI has similar success in inferring the puzzles. We hypothesized that the number of correctly connected pieces correlates with the reasoners’ accuracy. Additionally, in the human sample, we speculated that the frequency of some reasoning strategies as well as the reported confidence are associated with their accuracy. Responses from 530 participants were asked to identify the puzzle the child was assembling, explain their reasoning process, and their confidence. We asked four visual language models the same questions and assessed the accuracy of their inferences. This project was supported by funding from F&M's Committee on Grants Program.

Project Mentor:  Professor Willie Wilson, Department of Computer Science

Many waterways in Lancaster County and the greater Mid-Atlantic region are impacted by high flow velocities and flooding given the presence of legacy sediment created by mill dam activity over the last 400 years. After a dam breaches, the waterway incises through accumulated mill pond sediment, resulting in a deep, narrow channel that acts as a chute, rapidly transporting water and promoting flash flooding. The Blue-Green Connector is an ongoing recreation trail and stream restoration project located on the Little Conestoga Creek in Lancaster, PA. This independent research explores the impact that the Blue-Green Connector legacy sediment removal stream restorations have on flood risk and severity, using the USACE’s Hydrologic Engineering Center River Analysis System (HEC-RAS) program to simulate various restoration scenarios (i.e. pre-restoration, post-restoration, combinations of completed sites) and calculate flood parameters, such as discharge, water level, residence time, and peak flooding extent. This project was supported by funding from F&M's Committee on Grants Program.

Project Mentors:  Professors Dorothy Merritts and Julia Carr, Department of Earth and Environment