Dongjun Gong

Papers

Total Citations

H-Index

About

Dongjun Gong is a researcher in robotics and intelligent control, with a primary focus on developing data-driven approaches for autonomous manipulation. His most notable contribution is a novel method for robot grasping based on reinforcement learning, which leverages a six-degree-of-freedom robot arm and an RGB-D camera as the primary sensing module. Unlike traditional model-based techniques, Gong’s system learns optimal grasping policies directly from sensory input, enabling more adaptive and robust performance in unstructured environments. Though his work is early-stage, with his top-cited paper accumulating 3 citations, it represents a meaningful step toward bridging reinforcement learning with practical robotic applications. Gong’s research is particularly relevant for students and engineers interested in the intersection of computer vision, deep reinforcement learning, and robotic control. His approach highlights the potential of end-to-end learning to replace hand-crafted grasping algorithms, offering a scalable pathway for robots to interact with novel objects. As the field of robotic manipulation increasingly turns to learning-based methods, Gong’s contributions provide a foundational framework for future advances in autonomous grasping and dexterous manipulation.