Seongwon Jang
Papers
1
Total Citations
5
H-Index
1
About
Seongwon Jang is a robotics researcher whose work focuses on the intersection of computer vision and reinforcement learning for dynamic manipulation tasks. His primary research areas include vision-based robotic control, active perception, and autonomous object grasping in unstructured environments. Jang’s most notable contribution is his 2022 paper on "Vision-based Reinforcement learning: Moving object grasping with a Single Active-view Camera," which addresses a critical limitation in traditional robotic grasping systems. While conventional methods rely on static, overhead cameras that can be obstructed by obstacles or the robot’s own body, Jang’s approach leverages an active-view camera mounted on the robot itself, combined with reinforcement learning to enable successful grasping of moving objects despite visual occlusions. This work has garnered 5 citations and demonstrates a practical solution for real-world applications where environmental constraints hinder perception. Jang’s research pushes the boundaries of how robots can interact with dynamic environments, making his contributions valuable for advancing autonomous systems in manufacturing, logistics, and service robotics.
Research Focus
Key Achievements
Top Papers
- 1