Papers
16
Total Citations
173
H-Index
9
About
Yoonchang Sung is a robotics researcher whose work spans autonomous navigation, multi-target tracking, object search, and hazardous environmental monitoring. With a career rooted in making robots smarter and safer in complex, real-world settings, Sung has made significant contributions to probabilistic frameworks for perception and decision-making under uncertainty. His early work on human-following robots using laser range finders — now approaching 30 citations — established robust tracking methods for cluttered environments, while subsequent research extended these ideas to searching and tracking unknown numbers of mobile targets using limited field-of-view sensors. Sung's more recent contributions have pushed the frontier of 3D multi-object search through POMDP-based planning (21 citations) and correlational object search strategies that help robots efficiently locate hard-to-detect items. His involvement in Virginia Tech's Team VALOR and the development of ESCHER, a full-sized humanoid robot for the DARPA Robotics Challenge, demonstrates his breadth across both algorithms and physical systems. A 2023 survey on decision-theoretic approaches to environmental monitoring further cements his role as a synthesizer of ideas across the robotics community. Collectively, his portfolio reflects a consistent commitment to principled, probabilistic solutions for autonomous robots operating in uncertain, dynamic environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2Multi-Resolution POMDP Planning for Multi-Object Search in 3D21 citations · 2021
- 3
- 4
- 5
- 6Towards Optimal Correlational Object Search14 citations · 2022
- 7
- 8
- 9
- 10Multi-Robot Coordination for Hazardous Environmental Monitoring7 citations · 2019