Zihong Wang
Papers
2
Total Citations
24
H-Index
2
About
Zihong Wang is a pioneering researcher in agricultural robotics, specializing in autonomous navigation systems for complex orchard environments. His work addresses critical challenges in deploying robots under GNSS-denied conditions, where traditional satellite-based positioning fails due to dense foliage and terrain irregularities. Wang's major contributions include developing deep-learning-based trunk perception systems that combine depth estimation with Dynamic Window Approach (DWA) for robust navigation, achieving 21 citations in his seminal 2023 paper. His most recent work (2025) introduces a field-validated VIO-MPC fusion framework for autonomous headland turning, solving the persistent problem of reliable robot maneuvering in GPS-denied orchards where LiDAR-based approaches struggle with sparse data. Wang's research has significant practical impact, enabling agricultural robots to operate reliably in harsh conditions including illumination variations and uneven terrain. His innovative sensor fusion techniques and perception algorithms represent important advances toward fully autonomous agricultural systems, with potential applications in precision farming and sustainable agriculture. Wang's work continues to influence the development of robust, field-ready robotic solutions for modern agriculture.
Research Focus
Key Achievements
Top Papers
- 1
- 2