Papers
7
Total Citations
66
H-Index
6
About
Kaimeng Wang is a robotics researcher whose work bridges the critical gap between human dexterity and robotic precision, focusing on Programming by Demonstration (PbD), robot grasping, and surgical robotics. His most influential contribution, with 19 citations, pioneered the combination of intraoperative 5-aminolevulinic acid-induced fluorescence with 3-D MR imaging to guide robotic laser ablation for precision neurosurgery—a technique that enhances surgical accuracy in delicate brain procedures. Wang has made significant strides in enabling robots to learn complex manipulation tasks from human demonstrations. His 2023 work on learning robotic insertion tasks from human demonstration (12 citations) addresses the longstanding challenge of contact dynamics in industrial assembly, while his 2024 approach to robot grasp planning (10 citations) tackles the fundamental problem of generating stable grasps for advanced manufacturing. Notably, he developed a method for robot programming using only a monocular RGB camera (7 citations), eliminating the need for expensive sensor suites. Wang has also contributed foundational analytical solutions to inverse kinematics, including a Dixon resultant-based approach for 6R manipulators with offset wrists (8 citations) and vector polynomial methods for configuration design (6 citations). His recent work on single-demonstration learning for high-precision industrial insertion (4 citations) introduces an Imitated-to-Finetune framework that allows robots to master precision tasks from observing just one human example.
Research Focus
Key Achievements
Top Papers
- 1
- 2Learning Robotic Insertion Tasks From Human Demonstration12 citations · 2023
- 3Robot Grasp Planning: A Learning from Demonstration-Based Approach10 citations · 2024
- 4
- 5Robot programming by demonstration with a monocular RGB camera7 citations · 2022
- 6
- 7