Jennifer Padgett

Papers

Total Citations

H-Index

About

Jennifer Padgett’s research lies at the intersection of robotics, spatial reasoning, and probabilistic mapping, where she develops frameworks that allow robots to navigate and understand environments using qualitative, rather than purely metric, information. Her most influential work, the 2016 paper “Probabilistic qualitative mapping for robots” (4 citations), introduces the Probabilistic Qualitative Relational Mapping (PQRM) algorithm, a novel approach that enables robots to build robust environmental maps from noisy sensor data by leveraging soft, relative spatial relationships. This method offers resilience to metrical errors, making it ideal for real-world deployment. Building on this, her 2018 paper “Q-Link: A general planning architecture for navigation with qualitative relational information” (5 citations) extends the paradigm to autonomous planning, providing a flexible architecture for robots to navigate using qualitative relational cues. Though early in her career, Padgett’s contributions are foundational for advancing qualitative spatial reasoning in robotics, offering a promising alternative to traditional metric mapping. Her work is particularly valuable for students and researchers interested in robust, uncertainty-tolerant navigation systems.