Max Robotics — Global Service Robot Directory + US Certification

About

Zengzhi Zhao is a leading researcher in robotic grasping and manipulation, with a focus on enabling robots to handle unknown and novel objects with human-like dexterity. His core contributions lie in the development of novel multilevel convolutional neural networks (CNNs) that bridge the gap between simple parallel grippers and complex multifingered dexterous hands. Zhao’s landmark 2020 paper, “Robotic Grasping of Unknown Objects Using Novel Multilevel Convolutional Neural Networks: From Parallel Gripper to Dexterous Hand,” has garnered 56 citations, establishing a foundational framework for adaptive grasping. His subsequent work on deep learning methods for dexterous hand grasping (35 citations) further advanced the field by modeling how humans select finger postures based on object parts. Earlier research (2018) on extracting optimal grasping rectangles from RGB-D images laid the groundwork for these innovations. Collectively, Zhao’s work has significantly improved robotic autonomy in unstructured environments, with his citation record reflecting growing influence in robotics and artificial intelligence. His achievements are particularly notable for translating biological grasping strategies into scalable neural architectures, offering a pathway toward more capable and versatile robotic systems.