Fengkai Luan
Papers
1
Total Citations
1
H-Index
1
About
Fengkai Luan is a researcher advancing the frontier of intelligent perception for embodied agents and indoor robotics. His primary research areas center on computer vision, object detection, and multi-domain fusion models, with a particular focus on addressing the unique challenges of cluttered indoor environments. Luan’s most notable contribution is the development of MDF-YOLO, a Hölder-based regularity-guided multi-domain fusion detection model that tackles severe occlusion, scale variations, and densely packed objects—common obstacles that hinder reliable semantic mapping and human-robot interaction. This work, published in 2025, has already garnered early citations, signaling its relevance to the growing field of service robotics. By integrating mathematical regularity principles into detection frameworks, Luan’s approach enhances both accuracy and robustness in real-world indoor settings. His research directly supports critical downstream tasks such as path planning and autonomous navigation, making him a key contributor to the next generation of intelligent, context-aware robotic systems.
Research Focus
Key Achievements
Top Papers
- 1