Ishana Shekhawat
Papers
1
Total Citations
6
H-Index
1
About
Ishana Shekhawat’s research lies at the intersection of robotics, machine learning, and nonparametric statistics, with a particular focus on enabling machines to learn complex behaviors from human demonstrations. Her most cited work, “Imitation of Demonstrations Using Bayesian Filtering With Nonparametric Data-Driven Models” (2017, 6 citations), tackles the fundamental challenge of teaching robots to replicate dynamic tasks through observation. Shekhawat introduces a novel framework that models hybrid systems—those combining continuous and discrete dynamics—by employing Bayesian filtering alongside linear programming-based nonparametric kernel density estimation. This approach allows robots to infer and imitate nuanced motion patterns without requiring pre-specified parametric models, making learning more flexible and data-driven. Her contributions advance the field of learning from demonstration (LfD), offering a principled method for robots to adapt to new tasks in unstructured environments. While her citation count reflects the specialized nature of her work, Shekhawat’s methodology has influenced subsequent research in probabilistic imitation learning and nonparametric system identification. Her dedication to bridging statistical theory with practical robotic control underscores a career focused on creating more autonomous, adaptable machines that learn seamlessly from human guidance.
Research Focus
Key Achievements
Top Papers
- 1