Steven Lu
Papers
1
Total Citations
5
H-Index
1
About
Steven Lu’s research lies at the intersection of computer vision, robotics, and human-robot interaction (HRI), with a focus on enabling machines to learn adaptively in unstructured environments. His most cited work, “Video Object Segmentation using Teacher-Student Adaptation in a Human Robot Interaction (HRI) Setting” (2019, 5 citations), introduces a novel framework where robots learn to segment objects incrementally through natural human guidance—mirroring the way children acquire knowledge. This contribution addresses a critical bottleneck in robotics: the need for continuous, real-world learning without exhaustive pre-training. By leveraging video object segmentation, Lu’s approach enhances a robot’s ability to grasp objects and understand affordances, directly impacting autonomous manipulation tasks. His work exemplifies how HRI can serve as a dynamic teaching mechanism, bridging the gap between static datasets and adaptive, lifelong learning. Though early in his career, Lu’s research has already garnered attention for its practical implications in assistive robotics and interactive AI, positioning him as a promising voice in the push toward more intuitive, human-guided machine intelligence.
Research Focus
Key Achievements
Top Papers
- 1