Catherine Glossop

Papers

Total Citations

113

H-Index

About

Catherine Glossop is an emerging robotics researcher whose work sits at the intersection of robot learning, autonomous navigation, and cross-embodiment generalization. She is best known as a key contributor to **NoMaD (Goal Masked Diffusion Policies for Navigation and Exploration)**, a groundbreaking framework that unifies task-oriented navigation and open-ended exploration within a single diffusion-based policy model — a problem that had previously required separate, specialized systems. This work has attracted 96 citations since its 2024 publication, reflecting its significant influence on the robot learning community. Glossop's research extends beyond single-robot settings into the ambitious challenge of cross-embodiment learning, exploring how large-scale foundation models can be trained across radically diverse robot platforms for both manipulation and navigation tasks. Her 2024 paper on this topic pushes the boundaries of how broadly such policies can generalize, contributing to the growing movement toward universal robot learning frameworks. Her contributions reflect a clear research vision: building scalable, flexible robotic systems that can operate effectively in unfamiliar environments without the brittleness of task-specific models — a direction that positions her as a promising voice in next-generation autonomous robotics.