Jeongwoo Oh
Papers
2
Total Citations
11
H-Index
1
About
Jeongwoo Oh is a rising researcher at the forefront of socially-aware robotics, focusing on how autonomous systems can safely and comfortably navigate crowded human environments. His work bridges reinforcement learning, multi-agent coordination, and human-robot interaction to create robots that are not just functional, but socially intelligent. Oh’s most cited paper, “SCAN: Socially-Aware Navigation Using Monte Carlo Tree Search” (2023, 10 citations), introduces a novel global planning framework that uses Monte Carlo Tree Search to anticipate and respect pedestrian comfort, moving beyond simple collision avoidance to genuine social consideration. Building on this, his recent work “MAC-ID: Multi-Agent Reinforcement Learning with Local Coordination for Individual Diversity” (2024) tackles the challenge of modeling diverse pedestrian behaviors in multi-robot settings, a critical step for real-world deployment in spaces like malls or hospitals. Though early in his career, Oh’s contributions are already shaping how the field thinks about robot navigation—not as a purely technical problem, but as a deeply social one. His research is essential reading for anyone interested in the future of autonomous systems that must coexist with people.
Research Focus
Key Achievements
Top Papers
- 1SCAN: Socially-Aware Navigation Using Monte Carlo Tree Search10 citations · 2023
- 2