Tuluhan Akbulut
Papers
1
Total Citations
4
H-Index
1
About
Tuluhan Akbulut is a robotics researcher whose work focuses on the intersection of machine learning and physical interaction, particularly in the domain of sustained-contact manipulation. His key research areas include robot learning, policy representation, and dexterous manipulation, with a major contribution being the development of Composable Interaction Primitives (CIPs). This structured policy class, introduced in his 2024 paper, is designed to efficiently learn skills such as opening drawers, pulling levers, turning wheels, and shifting gears—tasks that require continuous, stable contact with objects. By exploiting the inherent structure of these interactions, CIPs reduce the complexity of what must be learned, enabling more sample-efficient and robust skill acquisition. Though early in his career, his work has already garnered attention, with his most-cited paper accumulating 4 citations since its publication. This achievement highlights his potential to shape how robots learn complex, real-world manipulation tasks. Akbulut’s research is particularly notable for its practical focus on enabling robots to perform everyday physical tasks, bridging the gap between theoretical policy learning and real-world application.
Research Focus
Key Achievements
Top Papers
- 1