Guangyi Tang
Papers
5
Total Citations
84
H-Index
5
About
Guangyi Tang is a rising researcher at the forefront of autonomous robotics, with a focus on scene understanding, multi-robot coordination, and robust navigation in dynamic environments. Tang’s work bridges deep learning and reinforcement learning to solve critical challenges in robot perception and path planning. Their 2023 survey on deep learning-based scene understanding for autonomous robots, with 40 citations, provides a comprehensive roadmap for the field, establishing Tang as a key synthesizer of emerging techniques. In 2024, Tang introduced a novel cooperative coverage path planning method using improved K-means clustering and deep reinforcement learning, garnering 20 citations and advancing multi-robot patrol efficiency. Tang has also made notable contributions to visual SLAM under dynamic conditions, enhancing map point reliability to overcome traditional ORB-SLAM limitations. More recently, Tang developed a lightweight GRU-based gesture recognition model for skeleton dynamic graphs, and an integration model for blind spot estimation and traversable area detection in indoor robots. With a growing citation record and work spanning from fundamental surveys to applied navigation systems, Tang is shaping the next generation of intelligent, autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1Deep learning-based scene understanding for autonomous robots: a survey40 citations · 2023
- 2
- 3
- 4
- 5