Papers
1
Total Citations
5
H-Index
1
About
Xuguang Feng is a leading researcher in agricultural robotics, with a primary focus on computer vision and robotic manipulation for precision harvesting. His most notable contribution is the development of TomatoPoseNet, an efficient keypoint-based 6D pose estimation model specifically designed for non-destructive tomato harvesting. This work addresses a critical challenge in agricultural robotics: enabling robotic arms to approach and grasp fruit with the correct posture without causing damage, even in cluttered environments with small, hard-to-detect pedicels. Despite being published in 2024, this paper has already garnered 5 citations, signaling its rapid impact on the field. Feng's research bridges the gap between advanced computer vision techniques and practical agricultural applications, offering scalable solutions for automated harvesting systems. His work is particularly valuable for students and researchers interested in the intersection of deep learning, robotics, and sustainable agriculture, as it demonstrates how efficient models can overcome real-world constraints like limited computational resources and environmental variability.
Research Focus
Key Achievements
Top Papers
- 1