Jianjia Xin
Papers
2
Total Citations
11
H-Index
2
About
Jianjia Xin is a robotics researcher whose work focuses on enabling robots to learn complex manipulation skills from human demonstration and common-sense reasoning. Her key research areas include robot learning from egocentric video, human-robot interaction, and knowledge-driven task planning. In her most cited work, "Learning Interaction Regions and Motion Trajectories Simultaneously From Egocentric Demonstration Videos" (2023, 9 citations), Xin addresses a fundamental challenge in robotics: teaching robots to interact with objects without robot-specific programming. By extracting both interaction regions and motion trajectories from first-person video, her approach allows robots to learn manipulation skills that are transferable across different robotic platforms. Her earlier work, "Recommending Fine-Grained Tool Consistent With Common Sense Knowledge for Robot" (2022, 2 citations), tackles the nuanced problem of tool selection—moving beyond simple task completion to consider the object being manipulated and the quality of the outcome. This research integrates common-sense knowledge to recommend tools that are appropriate for specific, fine-grained task requirements. Xin’s contributions are particularly valuable for advancing robotic assistants that can learn naturally from human demonstration and make intelligent, context-aware decisions in real-world environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2