Junseok Kim
Papers
2
Total Citations
7
H-Index
2
About
Junseok Kim is a robotics researcher specializing in manipulation planning for confined and cluttered environments. His work focuses on enabling robots to retrieve target objects from spaces with severely restricted access and limited observation—such as shelves, cabinets, or industrial bins—where lateral views and approach angles are constrained. Kim’s major contributions lie in integrating Monte Carlo Tree Search (MCTS) with grasp and rearrangement planning, allowing robots to reason about occluded objects and safely relocate obstacles using prehensile actions. His 2022 paper, “Grasp Planning for Occluded Objects in a Confined Space with Lateral View Using Monte Carlo Tree Search” (5 citations), introduces a planning framework that accounts for surrounding obstacles to generate collision-free retrieval strategies. Building on this, his 2023 work, “Object Rearrangement Planning for Target Retrieval in a Confined Space with Lateral View” (2 citations), extends the approach to full rearrangement tasks, demonstrating how an agent can systematically clear a path to a hidden target. Though early in his career, Kim’s research addresses a critical gap in robotic manipulation for real-world constrained environments, with potential applications in warehouse automation, assistive robotics, and disaster response.
Research Focus
Key Achievements
Top Papers
- 1
- 2