Papers
6
Total Citations
60
H-Index
4
About
Jooseop Yun’s research lies at the intersection of computer vision, mobile robotics, and human-robot interaction, with a focus on enabling robots to navigate and communicate effectively in real-world environments. His most influential work, “Robust visual speakingness detection using bi-level HMM” (29 citations), advances human-robot interaction by developing a hierarchical hidden Markov model to reliably detect when a person is speaking—a critical skill for natural, attentive communication. Yun is perhaps best known for his pioneering contributions to outdoor robot localization using rough, inaccurate maps. In his highly cited papers “Multi-Hypothesis Outdoor Localization using Multiple Visual Features with a Rough Map” and its companion (12 and 8 citations, respectively), he introduced a stereo-vision-based method that fuses multiple visual features to segment buildings and generate robust location hypotheses despite large map uncertainties. This work directly addresses a fundamental challenge: enabling robots to navigate with only sketchy, hand-drawn maps. He further formalized this problem in “A quantitative measure for the navigability of a mobile robot using rough maps” (5 citations), providing a metric to evaluate how well a robot can traverse an environment given an imprecise map. Later, in “Vision-Based Attentiveness Determination Using Scalable HMM Based on Relevance Theory” (3 citations), he extended his HMM expertise to model human attention, aiming to make robots more socially aware. With a total of over 60 citations across these key works, Yun’s research has helped bridge the gap between imperfect human input and reliable robot autonomy, laying groundwork for more intuitive, sketch-based robot guidance systems.
Research Focus
Key Achievements
Top Papers
- 1Robust visual speakingness detection using bi-level HMM29 citations · 2011
- 2
- 3
- 4
- 5A Quantitative Navigability Measure of Rough Maps3 citations · 2009
- 6