Jun Shao
Papers
4
Total Citations
26
H-Index
3
About
Dr. Jun Shao is a rising roboticist whose research focuses on the intersection of task planning, trajectory optimization, and manipulation, with a particular emphasis on integrating large language models (LLMs) into robotic systems. His most impactful work, "MLDT: Multi-Level Decomposition for Complex Long-Horizon Robotic Task Planning with Open-Source Large Language Model" (2024, 15 citations), introduces a novel framework that decomposes intricate tasks into manageable sub-tasks, enabling open-source LLMs to plan effectively for long-horizon robotic operations—a significant step toward accessible, data-driven AI in robotics. Dr. Shao also advances practical manipulation through "Trajectory Optimization for Manipulation Considering Grasp Selection and Adjustment" (2023, 5 citations), which optimizes both grasp and motion for dexterous handling. His paper "Towards Safe and Aggressive Motion Generation for Dynamic Targets Pick-and-Place" (2023, 4 citations) presents a time-optimal trajectory generation method that balances safety with aggressive motion, using spatial-temporal deformation to track moving objects—a critical achievement for high-speed industrial applications. With a growing citation record and contributions that bridge LLM-based planning and real-time control, Dr. Shao is shaping the future of autonomous, adaptive robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4