Max Robotics — Global Service Robot Directory + US Certification

About

Jenn-Jier James Lien is a leading researcher in the intersection of computer vision and robotic manipulation, with a focus on developing efficient, learning-based systems for industrial automation. His core contributions lie in creating lightweight deep neural network architectures for robotic grasping, notably a model with just 1.5 million parameters that achieves robust performance through innovative template matching and depth image analysis. Lien’s work addresses critical challenges in real-world automation, such as occluded target motion estimation and high-precision grasping of rotated objects, as demonstrated in his 2015 study on adaptive robotic interceptions. His most cited paper (8 citations) proposes a lightweight DNN model that estimates object location via pairwise template matching and orientation via depth data, significantly reducing computational overhead. Lien has also advanced self-supervised learning techniques to overcome the need for massive labeled datasets, and his multi-task Faster R-CNN framework (6 citations) enables simultaneous object detection and grasp planning. Through embedded systems integration—including Nvidia Jetson TX2 implementations—his research bridges the gap between high-performance algorithms and practical, real-time robotic control, making him a key figure in the push toward smarter, more adaptable industrial robots.