Jin‐Soo Park

The University of Texas at Austin, Soonchunhyang University

Papers

Total Citations

H-Index

About

Jin-Soo Park is a leading researcher in multi-robot systems and autonomous navigation, with a focus on enabling safe, efficient coordination in confined, dynamic environments. His key contributions center on developing learning-based methods to address the "hallway problem"—a classic challenge where multiple robots must navigate narrow corridors without deadlock or collision. Park’s most cited work, "Learning Perceptual Hallucination for Multi-Robot Navigation in Narrow Hallways" (2023, 9 citations), introduces a novel approach that allows robots to anticipate and adapt to others’ movements by generating perceptual "hallucinations" of future states, significantly improving traffic flow in tight spaces. This builds on his earlier "Learning to Improve Multi-Robot Hallway Navigation" (2020, 3 citations), which laid the groundwork for adaptive coordination. Additionally, Park has advanced pedestrian detection for autonomous vehicles through a distributed deep learning platform (2020, 5 citations), bridging IT convergence and real-world safety. With over 17 citations across his top papers, Park’s work is shaping the next generation of autonomous systems, offering practical solutions for warehouse logistics, service robots, and self-driving cars. His research stands out for its blend of theoretical insight and applied robotics, making him a rising figure in the field.