Papers
5
Total Citations
52
H-Index
5
About
Dequan Guo is a leading researcher in intelligent robotics for critical infrastructure, with a primary focus on substation inspection and autonomous manipulation. His work bridges computer vision, sensor fusion, and motion planning to enhance the safety and efficiency of power transmission systems. Guo’s most influential contribution, “A Small Object Detection Method for Oil Leakage Defects in Substations Based on Improved Faster-RCNN” (25 citations), provides a robust AI solution for detecting subtle equipment failures—a vital task for inspection robots. He further advanced environmental perception with “Environment Understanding Algorithm for Substation Inspection Robot Based on Improved DeepLab V3+” (8 citations), enabling robots to navigate complex substations with greater accuracy. Earlier in his career, Guo tackled foundational robotics challenges, developing efficient algorithms for manipulator kinematics and path planning (2009, 14 combined citations). His latest work (2025) introduces a novel multisensory navigation assistant that fuses 2D laser radar with other data to solve asynchronous information matching, promising more reliable autonomous navigation. Through these innovations, Guo has significantly reduced human risk in hazardous environments while improving real-time, all-weather inspection capabilities.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Research of Manipulator Motion Planning Algorithm Based on Vision8 citations · 2009
- 4Efficient Algorithms for the Kinematics and Path Planning of Manipulator6 citations · 2009
- 5