Doyeob Yeo
Papers
1
Total Citations
15
H-Index
1
About
Doyeob Yeo is a researcher advancing the field of agricultural robotics, with a primary focus on enhancing the perception and detection capabilities of automated harvesting systems. His most cited work, "Enhancing detection performance for robotic harvesting systems through RandAugment" (2023), introduces a novel application of data augmentation techniques—specifically RandAugment—to improve the robustness and accuracy of computer vision models in complex, real-world agricultural environments. This contribution addresses a critical bottleneck in precision agriculture: enabling robots to reliably identify and locate ripe produce under variable lighting, occlusion, and crop conditions. With 15 citations in just a short time, this paper signals growing recognition of his approach within the robotics and AI communities. Yeo’s research sits at the intersection of deep learning, data-efficient training, and field robotics, offering practical solutions that move automated harvesting from lab demonstrations toward viable commercial deployment. His work is particularly notable for its emphasis on improving detection performance without requiring extensive manual annotation, making it scalable for diverse crop types and growing conditions.
Research Focus
Key Achievements
Top Papers
- 1