Papers

4

Total Citations

132

H-Index

3

About

Xingxu Li is a researcher specializing in agricultural robotics, computer vision, and deep learning, with a particular focus on automating tomato cultivation and harvesting processes. His work sits at the intersection of precision agriculture and artificial intelligence, tackling real-world challenges such as low harvest success rates and crop damage that plague conventional automated systems. Li's most significant contribution is MTD-YOLO, a multi-task deep convolutional neural network designed for cherry tomato fruit bunch maturity detection, which has garnered an impressive 108 citations since its publication in 2023, underscoring its broad influence in the field. Building on this foundation, he developed AHPPEBot, an autonomous harvesting robot integrating crop phenotyping and pose estimation to improve operational precision and reduce crop damage. His continued refinement of perception systems is evident in his 2025 work introducing a top-down fusion network for tomato truss harvesting under limited data conditions. Across his publications, Li consistently addresses the gap between laboratory-stage robotics and practical agricultural deployment. His multi-task detection frameworks and innovative robot designs represent meaningful advances toward fully autonomous, reliable agricultural systems — making his research highly relevant for students and engineers working on smart farming and robotics solutions.

Research Focus

Key Achievements

3
H-Index
4
Papers
132
Total Citations
33
Avg Citations/Paper
🏆 Most Cited Paper
MTD-YOLO: Multi-task deep convolutional neural network for cherry tomato fruit bunch maturity detection
108 citations · 2023
📈 Most Prolific Year: 2023 (2 Papers)
🤝 Key Collaborators: 11
🏛 Institutions: Beijing University of Technology, Beijing Information Science & Technology University

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 14 days ago