Pengkun Quan
Papers
9
Total Citations
83
H-Index
5
About
Pengkun Quan is a robotics and computer vision researcher whose work sits at the intersection of autonomous systems, electric vehicle (EV) charging automation, and cable-driven manipulator technology. His research has made significant contributions to the challenge of automating EV charging infrastructure, a problem of growing importance as electric vehicles become increasingly prevalent worldwide. Quan's most influential work focuses on the visual identification and precise localization of EV charging ports in complex real-world environments. His 2021 paper on contour feature detection has garnered 37 citations, establishing foundational methods for enabling robotic charging systems to reliably recognize charging ports across diverse conditions. He has extended this work to handle multiple vehicle types simultaneously, employing advanced deep learning architectures including customized YOLO variants and attention mechanisms. Beyond perception, Quan addresses the critical safety dimension of human-robot interaction, developing collision detection and classification frameworks for cable-driven manipulators using DCNN-SVM hybrid approaches, accumulating over 10 citations. His contributions to cable-driven robot kinematics, including self-calibration methods and peg-in-hole assembly controllers, demonstrate a comprehensive systems-level understanding of robotic charging platforms. With a total citation footprint approaching 83 citations, Quan represents an emerging voice in intelligent EV charging robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9