Yan Zheng
Papers
2
Total Citations
89
H-Index
2
About
Yan Zheng is a researcher whose work spans the intersection of computer vision, artificial intelligence, and intelligent systems, with particular emphasis on deep learning applications in agriculture and reinforcement learning for complex decision-making environments. His most widely recognized contribution involves advancing fruit detection technology through a novel integration of binocular stereo vision with an improved YOLOv3 model, enabling accurate pineapple detection and localization in unstructured natural settings — a breakthrough that has garnered 79 citations and holds significant promise for automating agricultural harvesting processes. Beyond agricultural AI, Zheng has made meaningful strides in reinforcement learning, notably through his work on HyAR (Hybrid Action Representation), which addresses the underexplored but practically critical challenge of discrete-continuous hybrid action spaces in domains such as robot control and game AI. This research tackles a fundamental limitation in existing RL frameworks, which have traditionally excelled in either discrete or continuous action settings but rarely both simultaneously. Together, these contributions position Zheng as a versatile researcher bridging real-world robotic applications with foundational advances in machine learning, making his work relevant to students and practitioners in agricultural robotics, computer vision, and autonomous systems alike.
Research Focus
Key Achievements
Top Papers
- 1
- 2