H. Hashempour
Papers
2
Total Citations
7
H-Index
2
About
H. Hashempour is a roboticist specializing in the intersection of deep learning and robot learning from demonstration (LfD), with a particular focus on deformable object manipulation. Their major contributions lie in developing deep-LfD frameworks that enable robots to learn complex tasks directly from high-dimensional visual sensory data, moving beyond conventional LfD approaches that struggle with real-world variability. Hashempour’s work on learning the relationship between visual inputs and robot trajectories has been foundational for automating delicate procedures such as robotic suturing and needle piercing through deformable materials. Their most cited paper, “Deep-LfD: Deep robot learning from demonstrations” (2021, 4 citations), introduces a dataset and methodology that bridges the gap between high-level task demonstrations and low-level robot control. A complementary dataset paper (2020, 3 citations) provides critical benchmarks for deformable object manipulation. Though early in their career, Hashempour’s research is paving the way for more autonomous surgical robots and adaptive manufacturing systems, demonstrating how deep learning can make LfD practical for real-world, high-precision tasks.
Research Focus
Key Achievements
Top Papers
- 1Deep-LfD: Deep robot learning from demonstrations4 citations · 2021
- 2