Papers
2
Total Citations
57
H-Index
2
About
Siwen Chen is a robotics researcher whose work centers on enabling mobile robots to perceive, navigate, and interact with unknown, dynamic environments. Chen’s most impactful contribution is the development of a YOLO-GGCNN-based grasping framework (2023, 52 citations), which integrates real-time object detection with generative grasping convolutional neural networks. This framework allows mobile robots to autonomously identify and grasp objects in cluttered, unfamiliar settings—a critical step toward practical service and industrial robotics. More recently, Chen has advanced visual SLAM (Simultaneous Localization and Mapping) with an inpainting-based approach (2025) that detects and recovers regions corrupted by dynamic objects. This work directly challenges the static-scene assumption that limits many state-of-the-art SLAM systems, offering a robust solution for robots operating in human-filled environments. By tackling both manipulation and perception in real-world conditions, Chen’s research bridges key gaps between computer vision, deep learning, and autonomous robotics. With a growing citation footprint and a focus on practical, deployable systems, Chen is establishing a reputation for solving foundational problems that stand between today’s robots and truly autonomous operation in unstructured spaces.
Research Focus
Key Achievements
Top Papers
- 1
- 2