Joohee Suh

University of Oklahoma, Kookmin University

Papers

Total Citations

H-Index

About

Joohee Suh’s research lies at the intersection of intelligent robotics and adaptive machine learning, with a central focus on enabling autonomous agents to learn and adapt dynamically to new environments. Her major contributions center on developing neuromodulatory learning models—specifically, the Context-Aware Learning Model and the Context-based Adaptive Robot Behavior Learning Model (CARB-LM). These frameworks allow robots to build knowledge through direct environmental interaction, using reward- and experience-based mechanisms that are online, incremental, and interactive. Suh’s work addresses a critical challenge in robotics: creating controllers that can generalize across contexts without requiring exhaustive pre-programming. While her most-cited papers have garnered modest citation counts—3 each for her 2017 and 2014 works—their conceptual novelty is significant, proposing a shift toward bootstrapping, self-improving systems. Her 2010 paper on collaborative service robot frameworks further underscores her interest in multi-agent coordination. Suh’s research is particularly valuable for students and researchers exploring lifelong learning in robotics, offering a foundation for building agents that learn continuously from feedback rather than static datasets.