Papers
2
Total Citations
50
H-Index
2
About
Jiale Li is a researcher at the intersection of agricultural robotics and intelligent machine learning, with a primary focus on real-time perception systems for precision agriculture. Their most impactful work, published in 2024, introduces a lightweight YOLO-based convolutional neural network for simultaneous lettuce-weed localization and weed severity classification, enabling intelligent intra-row weed control. This paper has already garnered 46 citations, reflecting its timely relevance to sustainable farming and embedded AI. Li has also contributed to foundational challenges in robot learning, notably through their work on general robot dynamics learning and the Gen2Real framework. This research addresses a critical bottleneck in robotics: the need for efficient, transferable dynamics models that can adapt across different robotic platforms without retraining from scratch. By proposing a method that bypasses traditional dynamics randomization and simulation-data regeneration, Li’s work advances the goal of more generalizable and practical robot learning. Their contributions bridge computer vision, deep learning, and robotics, offering scalable solutions for both agricultural automation and adaptive robot control.
Research Focus
Key Achievements
Top Papers
- 1
- 2General Robot Dynamics Learning and Gen2Real4 citations · 2021