Jiyoun Moon
Papers
10
Total Citations
109
H-Index
6
About
Jiyoun Moon is a pioneering researcher at the intersection of robotics, artificial intelligence, and natural language processing, whose work focuses on enabling robots to understand and interact with complex, dynamic environments. Their key research areas include 3D scene understanding, semantic SLAM (Simultaneous Localization and Mapping), and neuro-symbolic task planning for multi-agent systems. Moon’s major contributions include developing view-point invariant 3D classification methods using convolutional neural networks (29 citations) and a variational observation model for probabilistic semantic SLAM (25 citations), which allow robots to perceive and map objects with unprecedented accuracy. They have also advanced human-robot collaboration by creating frameworks for natural language-based scene understanding, such as generating questions from semantic graphs and planning tasks using PDDL (Planning Domain Definition Language) for UAV-UGV cooperation. Notably, Moon’s work on flexible semantic ontological models (10 citations) and meta reinforcement learning for underwater manipulator control (6 citations) demonstrates their ability to tackle real-world challenges in autonomous navigation and hazardous environments. With over 100 total citations, Moon’s research is shaping the future of intelligent robotics, bridging the gap between low-level perception and high-level symbolic reasoning.
Research Focus
Key Achievements
Top Papers
- 1
- 2A Variational Observation Model of 3D Object for Probabilistic Semantic SLAM25 citations · 2019
- 3
- 4
- 5
- 6Meta Reinforcement Learning Based Underwater Manipulator Control6 citations · 2021
- 7Object-oriented Semantic Graph Based Natural Question Generation4 citations · 2020
- 8
- 9
- 10