Max Robotics — Global Service Robot Directory + US Certification

About

Minh-Tri Le is a robotics researcher whose work focuses on the intersection of computer vision and robotic manipulation, particularly in developing efficient, lightweight grasping systems. His primary research areas include deep learning for robotic grasping, template matching algorithms, and embedded vision systems for real-time object detection and manipulation. Le's major contributions center on creating computationally efficient models that enable robots to accurately grasp objects in real-world scenarios. His most cited work, "Lightweight Robotic Grasping Model Based on Template Matching and Depth Image" (2022, 8 citations), introduces a deep neural network with just 1.5 million parameters—a significant reduction in computational requirements—that uses pairwise template matching for object localization and depth information for orientation prediction. This work, along with his subsequent "Robot arm grasping using learning-based template matching and self-rotation learning network" (2022, 7 citations), demonstrates his commitment to practical, deployable solutions. Le has also pioneered embedded-based grasping systems using NVIDIA Jetson platforms, integrating vision and control subsystems for autonomous operation. His research has important implications for industrial automation and service robotics, where efficient, real-time grasping remains a critical challenge.