Kai Lu
Papers
3
Total Citations
102
H-Index
2
About
Kai Lu is a robotics researcher whose work focuses on the intersection of deep reinforcement learning, robotic manipulation, and autonomous grasping in unstructured environments. His most significant contribution is a novel robotic grasping system for cluttered scenes, detailed in his highly cited 2019 paper (87 citations), which integrates a composite hand combining a suction cup and gripper to achieve stable object retrieval. This work addresses a critical challenge in industrial and service robotics: enabling robots to reliably pick items from messy, unpredictable piles. Lu further advances the field through his research on active affordance exploration for grasping (13 citations), teaching robots to discover how objects can be manipulated by interacting with them. His 2020 work on semi-empirical simulation of force response models (2 citations) introduces data-driven methods for simulating contact with deformable objects, using point-based surface representations and learned nonlinear models. By combining reinforcement learning with practical hardware design and physics simulation, Lu’s research directly impacts the development of more capable, adaptive robots for manufacturing, logistics, and domestic assistance.
Research Focus
Key Achievements
Top Papers
- 1
- 2Active Affordance Exploration for Robot Grasping13 citations · 2019
- 3