Lusong Li
Papers
1
Total Citations
2
H-Index
1
About
Lusong Li is a researcher advancing the frontier of robotic dexterous manipulation, with a primary focus on articulated object interaction and sim-to-real transfer. Their most cited work, “DexSim2Real²: Building Explicit World Model for Precise Articulated Object Dexterous Manipulation” (2025, 2 citations), introduces a novel framework that constructs an explicit world model to enable precise, goal-conditioned manipulation of everyday articulated objects—such as cabinets, drawers, and doors—using dexterous robotic hands. This contribution addresses a critical challenge in robotics: bridging the simulation-to-reality gap for complex, multi-joint objects. By building an explicit model of object kinematics and dynamics, Li’s approach allows robots to generalize manipulation skills across diverse articulated structures without extensive real-world training. The work has quickly gained attention for its potential to make robotic assistants more capable in unstructured human environments. Li’s research sits at the intersection of computer vision, reinforcement learning, and robotic control, offering a pathway toward robots that can interact with the physical world as fluidly as humans. As this work continues to accumulate citations, it promises to influence future developments in household robotics and autonomous manipulation.
Research Focus
Key Achievements
Top Papers
- 1