Jungkyoo Shin
Papers
1
Total Citations
6
H-Index
1
About
Jungkyoo Shin is a researcher advancing the frontier of robot manipulation through the integration of large language models (LLMs) and task planning. His primary research areas include long-horizon robotic task planning, manipulation in unstructured environments, and the application of LLMs to bridge symbolic reasoning with real-world physical constraints. Shin’s most cited work, "Task Planning for Long-Horizon Cooking Tasks Based on Large Language Models" (2024, 6 citations), tackles a critical bottleneck in robotics: enabling robots to generalize beyond pre-programmed symbolic representations when faced with unseen, complex tasks like cooking. By leveraging LLMs, his approach enhances the adaptability and robustness of task planners, moving toward more autonomous and flexible robotic systems. This contribution is particularly impactful for service robotics and domestic automation, where long-horizon tasks require both high-level reasoning and low-level execution. With his work gaining early traction, Shin is positioned to influence how robots learn to handle dynamic, real-world scenarios, bridging the gap between language understanding and physical action.
Research Focus
Key Achievements
Top Papers
- 1