Soheila Barzegari

About

Soheila Barzegari is a researcher whose work sits at the intersection of robotics and machine learning, with a primary focus on learning from demonstration (LfD) and robot skill acquisition. Her key research areas include dynamic movement primitives, Gaussian process regression, and handling uncertainty in task parameterization. Her most cited work, "Learning from demonstration with partially observable task parameters using dynamic movement primitives and Gaussian process regression" (2016, 11 citations), addresses a critical real-world challenge: enabling robots to learn tasks when key environmental information is incomplete or missing. This contribution is significant because it moves beyond idealized laboratory conditions toward more practical, everyday scenarios where sensors may be limited or occluded. By integrating Gaussian process regression with dynamic movement primitives, Barzegari’s approach allows robots to robustly generalize learned skills even under partial observability. While her citation count reflects a focused, emerging impact in this niche area, her work is notable for bridging probabilistic modeling and imitation learning, offering a foundation for more adaptive and resilient robotic systems. For students and researchers in robotics and machine learning, her research highlights the importance of addressing real-world uncertainty in autonomous skill acquisition.

Research Focus

Key Achievements

Top Papers

1. 1
   Learning from demonstration with partially observable task parameters using dynamic movement primitives and Gaussian process regression

   11 citations · 2016

Key Collaborators

Contact & Links