Shangjie Xue
Papers
1
Total Citations
5
H-Index
1
About
Shangjie Xue is a rising researcher in robot learning and manipulation, with a focus on enabling robots to perform long-horizon, complex tasks through intelligent planning. His most cited work, "Generative Skill Chaining: Long-Horizon Skill Planning with Diffusion Models" (2023, 5 citations), tackles a core challenge in robotics: how to sequence learned skills to solve unseen tasks with intricate subtask dependencies. Xue’s key contribution lies in using diffusion models to generate coherent skill chains, overcoming the myopic limitations of greedy sequencing and improving scalability in manipulation planning. This approach allows robots to plan over extended horizons without succumbing to compounding errors, a critical step toward autonomous systems that can adapt to novel environments. While still early in his career, Xue’s work has already garnered attention for its innovative blend of generative modeling and hierarchical planning. By addressing the scalability of skill chaining, he is paving the way for more robust, real-world robotic applications—from assembly to household tasks—where long-term reasoning is essential.
Research Focus
Key Achievements
Top Papers
- 1