Congmin Guo

Papers

Total Citations

H-Index

About

Congmin Guo is a robotics researcher focused on intelligent grasping and manipulation, with a particular emphasis on agricultural and industrial applications. Their work bridges computer vision and robotic control, developing efficient neural network architectures for object detection and grasp planning. Guo’s most impactful contribution is the “End-to-End lightweight Transformer-Based neural network for grasp detection towards fruit robotic handling” (2024, 28 citations), which introduces a streamlined, attention-driven model that enables robots to identify and execute stable grasps on delicate fruit with minimal computational overhead—a critical advance for real-time harvesting systems. This work addresses the longstanding challenge of balancing speed and accuracy in robotic perception. Additionally, Guo’s “NBMOD: Find It and Grasp It in Noisy Background” (2023, 3 citations) tackles the practical problem of robust object detection in cluttered, visually noisy environments, proposing a method that enhances grasp success rates where traditional approaches fail. By focusing on lightweight, deployable solutions, Guo’s research directly supports the automation of labor-intensive tasks in agriculture and logistics, demonstrating how efficient AI can unlock new capabilities for field robots. Their work is increasingly cited by researchers developing real-world robotic systems.