Lichun Wang
Papers
3
Total Citations
14
H-Index
2
About
Lichun Wang is a researcher at the forefront of robotic manipulation and cognitive robotics, with a primary focus on enabling robots to understand and interact with objects in human-centric environments. Her work bridges computer vision, affordance learning, and common-sense reasoning to create more intuitive and capable robotic systems. Wang’s major contributions lie in three key areas: learning from demonstration, object affordance state recognition, and tool selection for task execution. In her 2023 work on learning interaction regions and motion trajectories from egocentric videos (9 citations), she pioneered methods for robots to simultaneously acquire spatial interaction knowledge and movement patterns from human demonstrations, making robot teaching more efficient and robot-agnostic. Her OASNet framework (2023, 3 citations) advanced affordance learning by introducing the novel concept of “affordance state”—determining not just what an object can do, but whether it is currently being interacted with, a critical capability for dynamic task planning. Additionally, her 2022 research on fine-grained tool recommendation (2 citations) addressed the overlooked nuance of tool selection, incorporating common-sense knowledge to ensure robots choose tools that are not only functional but also appropriate for the specific object being manipulated, directly impacting task quality. With a growing citation footprint and a clear trajectory toward practical, human-aware robotics, Wang’s work is shaping the next generation of intelligent, context-aware robotic assistants.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3