Max Robotics — Global Service Robot Directory + US Certification

About

Kiru Park is a leading researcher in robotic perception and manipulation, whose work bridges computer vision, machine learning, and interactive robotics. His primary research areas include 6D object pose estimation, robotic grasping, and template matching, with a strong emphasis on enabling robots to operate robustly in unstructured, real-world environments. Park’s most influential contribution is the development of multi-task template matching for depth images, a method that simultaneously handles object detection, segmentation, and pose estimation—even under occlusion—garnering 49 citations. He further advanced the field with the DGCM-Net, a dense geometrical correspondence matching network that allows robots to learn from past grasping experiences and transfer that knowledge to novel objects, achieving 37 citations. His work on incremental experience-based grasping and object model generation from in-hand manipulation videos (10 citations) has been pivotal for autonomous robot learning. Additionally, Park’s early research on dual-layer user models for adaptive service robots (8 citations) demonstrates his long-standing interest in human-robot interaction. With over 100 total citations, Kiru Park’s research is essential reading for anyone working on perception-driven robotic manipulation and lifelong learning systems.