On-Policy Reinforcement Learning for Quadruped Robot Navigation in Extreme Icy Terrains.

Explores the Proximal Policy Optimization Reinforcement Learning algorithm and it's use as a local path planner when encountering extreme terrains.

Learn More

Synthetic Data Pipeline for Active Acoustic Machine Learning

Developed a Python application to interface with a HiL simulation for unmanned undersea vehicles, and trained a regression model to predict range and acoustic angle of arrival from synthetic data.

Learn More

Air Hockey Robot

Designed a 3 Degree-of-Freedom robot to play air hockey via an overhead camera.

Learn More