Lailiang Cheng
Papers
2
Total Citations
7
H-Index
2
About
Lailiang Cheng is a leading researcher at the intersection of agricultural robotics and 3D computer vision, with a primary focus on automating precision orchard management. His work directly addresses critical labor shortages in agriculture by developing advanced perception systems for robotic pruning. Cheng’s major contributions lie in solving the fundamental challenge of incomplete and noisy 3D point cloud data captured in real-world field conditions. His highly cited work, “(Real2Sim)⁻¹: 3D Branch Point Cloud Completion for Robotic Pruning in Apple Orchards” (2024, 5 citations), pioneered a novel framework that leverages simulation to reconstruct missing branch geometry and topology, significantly improving the accuracy of autonomous pruning decisions. Building on this, his recent research on “Joint 3D Point Cloud Segmentation Using Real-Sim Loop: From Panels to Trees and Branches” (2025, 2 citations) introduces a hierarchical segmentation approach (P2TB) that efficiently parses complex orchard scenes from the panel level down to individual branches. By creating robust, real-to-sim feedback loops, Cheng’s work is establishing the perceptual foundation for the next generation of intelligent agricultural robots, moving beyond single-instance analysis to holistic, operational scene understanding.
Research Focus
Key Achievements
Top Papers
- 1
- 2