Papers
1
Total Citations
183
H-Index
1
About
Keren Gu is a researcher whose work sits at the intersection of human-robot interaction, machine learning, and collaborative autonomy. Her most notable contribution, the 2016 paper "Efficient Model Learning from Joint-Action Demonstrations for Human-Robot Collaborative Tasks," has garnered 183 citations and stands as a foundational work in the field of adaptive robotic collaboration. In this research, Gu developed a framework that enables robots to automatically learn models of human behavior from joint-action demonstrations, using unsupervised learning to cluster human action sequences into distinct behavioral types. This allows robots to compute robust, personalized policies tailored to individual human partners — a significant advancement in making robots more effective and intuitive collaborators in shared tasks. Her approach addressed a critical challenge in human-robot teaming: the need for robots to understand and anticipate the diverse ways different users interact with them, rather than relying on a one-size-fits-all model. This work has influenced subsequent research in robot planning under uncertainty, user modeling, and assistive robotics, establishing Gu as a meaningful contributor to the growing field of intelligent, human-aware robotic systems.
Research Focus
Key Achievements
Top Papers
- 1