Gao Wang
Papers
8
Total Citations
138
H-Index
5
About
Gao Wang is a robotics researcher whose work spans robot safety, simultaneous localization and mapping (SLAM), and compliant control of robotic manipulators. His most influential contribution — a model-independent collision detection method using vibration analysis (2019, 62 citations) — broke from conventional torque-based approaches, offering a more flexible and robust solution for protecting robots during physical contact. Building on this foundation, Wang extended his collision research to intelligent classification, enabling smart factory systems to distinguish the materials, components, and human involvement in robot collisions using variational mode decomposition of vibration and motor current signals. In the domain of SLAM, Wang has made notable advances in dynamic and challenging environments. His COEB-SLAM system (2023, 33 citations) integrates object detection, epipolar geometry constraints, and blur filtering to maintain accuracy amid moving objects, while subsequent work addresses low-light image enhancement to further broaden real-world applicability. His research on EKF-based torque fusion (2023, 21 citations) demonstrates additional expertise in force-sensorless compliance control, improving robot sensitivity without dedicated sensors. Spanning structural optimization, trajectory planning, and adaptive control, Wang's body of work reflects a comprehensive and practically oriented approach to making robotic systems safer, smarter, and more perceptually capable.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Active Compliance Control Based on EKF Torque Fusion for Robot Manipulators21 citations · 2023
- 4
- 5
- 6
- 7
- 8