Papers
7
Total Citations
108
H-Index
5
About
Robin Strudel is a robotics and machine learning researcher whose work sits at the intersection of computer vision, robot learning, and manipulation planning. His research tackles one of the field's most persistent challenges: enabling robots to perform complex, real-world tasks by bridging the gap between simulated training environments and physical deployment. Strudel's most impactful contributions focus on sim-to-real transfer, with his work on augmenting synthetic images for policy transfer garnering 45 citations and offering practical strategies for reducing the costly reliance on real-world training data. His research on combining primitive skills for robotic manipulation (37 citations) represents a meaningful step toward versatile robots capable of multi-step tasks like assembly or meal preparation, blending the strengths of classical task planning with modern learning approaches. He has also contributed to neural motion planning and obstacle representation learning, broadening the toolkit available for dynamic, sensor-driven environments. Collectively, Strudel's portfolio reflects a coherent vision: making robotic manipulation more adaptable, data-efficient, and deployable outside controlled settings. His continued attention to visual sim-to-real robustness and assembly planning from observation signals a researcher steadily advancing the frontier of intelligent, physically grounded robot learning.
Research Focus
Key Achievements
Top Papers
- 1Learning to Augment Synthetic Images for Sim2Real Policy Transfer45 citations · 2019
- 2
- 3Learning Obstacle Representations for Neural Motion Planning12 citations · 2020
- 4
- 5Robust Visual Sim-to-Real Transfer for Robotic Manipulation5 citations · 2023
- 6Assembly Planning from Observations under Physical Constraints2 citations · 2022
- 7Learning to Augment Synthetic Images for Sim2Real Policy Transfer2 citations · 2019