Papers
7
Total Citations
114
H-Index
4
About
Jae Sung Park is a robotics researcher whose work sits at the intersection of motion planning, human-robot interaction, and probabilistic collision detection. His research addresses one of the central challenges in modern robotics: enabling high-degree-of-freedom robots to operate safely and intelligently alongside humans in shared, dynamic environments. Park's most influential contribution, "I-Planner: Intention-aware Motion Planning Using Learning-Based Human Motion Prediction" (2018, 67 citations), introduced a framework that predicts human actions using offline learning and temporal coherence, allowing robots to anticipate and respond to human behavior in real time rather than merely reacting to it. This work represents a meaningful step forward in proactive, socially aware robot navigation. Complementing this, Park has made significant advances in probabilistic collision detection, developing fast and bounded algorithms applicable to both convex and non-convex shapes under uncertainty — critical capabilities for robots operating in unpredictable environments. More recently, he has expanded into natural language interfaces for robotics, designing systems that translate complex verbal instructions into actionable motion plans through dynamic constraint mapping. Collectively, his research bridges perception, prediction, and planning, offering practical tools that bring robots closer to safe, intuitive collaboration with humans.
Research Focus
Key Achievements
Top Papers
- 1
- 2Efficient probabilistic collision detection for non-convex shapes25 citations · 2017
- 3
- 4
- 5
- 6
- 7