Daewon Kwak
Papers
1
Total Citations
2
H-Index
1
About
Daewon Kwak is a robotics researcher whose work centers on socially aware navigation for mobile robots operating in crowded, real-world environments. His key contributions lie at the intersection of Bayesian reinforcement learning and human–robot interaction, addressing critical gaps in how robots perceive and respond to people in complex settings. Kwak’s most notable paper, "Belief-Aided Navigation using Bayesian Reinforcement Learning for Avoiding Humans in Blind Spots" (2024), introduces a novel framework that enables robots to navigate safely even when humans are partially occluded or in sensor blind spots—a common challenge in practical deployment. By integrating belief states into the learning process, his approach allows robots to anticipate human movement without relying on perfect omnidirectional sensor data. Although this work is recent, it has already garnered attention for its practical relevance, receiving 2 citations in a short period. Kwak’s research is particularly impactful for advancing autonomous systems in hospitals, warehouses, and public spaces, where safe, unobtrusive navigation is essential. His work represents a meaningful step toward robots that can truly coexist with humans in dynamic, unpredictable environments.
Research Focus
Key Achievements
Top Papers
- 1