HyunJun Jo
Papers
10
Total Citations
40
H-Index
4
About
HyunJun Jo is a robotics researcher whose work centers on industrial and home-service robotic manipulation, with a particular focus on grasping, object recognition, and bin picking. A key contribution is his development of grasping algorithms that bypass the need for extensive deep learning training data and time—a significant practical advance. For instance, his 2020 work on a point cloud-based clustering grasping system (6 citations) and his 2017 ensemble learning approach combining simulation and real data (4 citations) directly address the data bottleneck in robotic grasping. His 2021 CAD-based view planning paper (8 citations) further advances robotic inspection through globally consistent registration. Notably, Jo’s team won the RoboCup@Home 2021 Domestic Standard Platform League (4 citations), demonstrating real-world application of his research in home service robotics. His work on automated synthetic dataset generation for bin picking (2018, 4 citations) and irregular depth tiles for grasping in dense clutter (2021, 3 citations) showcases his innovative use of synthetic data to overcome training limitations. With a total of over 40 citations, Jo’s research is steadily building impact, particularly in making robotic grasping more efficient and accessible for both industrial and domestic settings.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Object manipulation system based on image-based reinforcement learning5 citations · 2022
- 4
- 5RoboCup@Home 2021 Domestic Standard Platform League Winner4 citations · 2022
- 6
- 7
- 8
- 9Robotic Tidy-up Tasks using Point Cloud-based Pose Estimation2 citations · 2020
- 10