Katherine Driggs-Campbell
Papers
2
Total Citations
5
H-Index
1
About
Katherine Driggs-Campbell is a leading researcher in robotics and human-robot interaction, with a focus on enabling robots to learn complex manipulation skills through human guidance. Her work bridges the gap between human intuition and machine learning, particularly in the domains of teleoperation and bimanual coordination. In her highly cited 2025 paper, "Human-Agent Joint Learning for Efficient Robot Manipulation Skill Acquisition," she demonstrates how teleoperation systems can be leveraged to gather demonstrations for more efficient learning of high-dimensional manipulation tasks, addressing the inherent challenges of controlling dexterous robot arms and grippers. Her follow-up work, "Learning Coordinated Bimanual Manipulation Policies Using State Diffusion and Inverse Dynamics Models," tackles the difficult problem of coordinating two robot hands to manipulate deformable objects like laundry, modeling object movement and predicting future states. With a total of 5 citations across these recent papers, Driggs-Campbell is establishing herself as a rising star in the field, pushing the boundaries of what robots can learn from human demonstration and how they can achieve the fluid, coordinated actions that come naturally to humans.
Research Focus
Key Achievements
Top Papers
- 1
- 2