The team developed a system to control multiple AGVs based on prior senior design teams work. Work was done to develop a waypoint server to send commands to receiver servers on each AGV. Work was also done in the Robot Operating System (ROS) to improve the AGVs navigation capabilities. The AGV hardware was further developed to be more reliable, and a new AGV design was created to use an omnidirectional drivetrain. Work was done on both the hardware and software side to make it possible for multiple AGVs to run simultaneously without interference or downtime.

Fastbreak Outbreak's goal is to see COVID-19 effects on the NBA. With a combination of multiple dashboards that give an overview of a given game, team, and season, and an interactive component that predicts win probabilities based on active/inactive players, Fastbreak Outbreak leveraged state-of-the-art machine learning to predict NBA games using our proprietary Health Score accurately. This Health Score allows for the maximization of correct win probabilities and generating player impact.

Team Members

Feedback Friend is an online market research platform that collects feedback from customers and users. It caters towards start-ups and small businesses who do not need excessive complexity as found in competitors. Feedback Friend offers a best-in-class user experience for simple surveys.

Team Members

Ennis M. Salam
Cesar Padron
Bennett Burks
Kevin Li
Anika Singh
Tim Reynolds

Federated learning is a privacy-preserving, distributed approach to machine learning. Currently, federated learning research is mostly done in simulated environments. As a result, the effects of real-world network congestion and instabilities are not realized during testing. The first goal of our project is to create a federated learning infrastructure that can be deployed to a real network for experimentation purposes. Next, we would like to help researchers address the following problem: can we improve the convergence rate of a federated learning model through in-network aggregation?

The current UT microgrid system will become outdated as UT adopts renewable energy sources, especially as climate change prompts more severe weather changes. The variability of renewable energy sources presents an opportunity to develop an intelligent system that can preemptively detect potential blackouts. Our project aims to distribute power equitably and prevent long-term power failure in microgrids reliant on renewable energy.