Ahmet E. Tekden
Papers
7
Total Citations
74
H-Index
5
About
Ahmet E. Tekden is a robotics researcher whose work sits at the intersection of robot manipulation, machine learning, and physical interaction. His research focuses on equipping robots with intelligent, adaptable skills — spanning trajectory prediction, tactile exploration, grasp transfer, and non-prehensile manipulation such as pushing. Tekden's most cited contribution, "Deep Effect Trajectory Prediction in Robot Manipulation" (2019, 29 citations), established an early foundation for learning-based approaches to predicting manipulation outcomes. Building on this, his ACNMP framework (2020, 11 citations) introduced an elegant integration of Learning from Demonstration and Reinforcement Learning through representation sharing, enabling robots to acquire and refine dexterous skills efficiently. His work on object-shape reconstruction via sliding touch with multi-fingered hands (2023, 10 citations) demonstrates a strong interest in tactile sensing as a pathway to robust perception in unstructured environments. Meanwhile, his research on push-effect prediction using object- and relation-centric representations reflects a commitment to structured, generalizable world models for scene understanding. Across his growing body of work, Tekden consistently bridges deep learning with practical robotics challenges, making his research particularly valuable for those studying embodied AI, manipulation planning, and skill transfer in autonomous robotic systems.
Research Focus
Key Achievements
Top Papers
- 1Deep effect trajectory prediction in robot manipulation29 citations · 2019
- 2
- 3
- 4Object and relation centric representations for push effect prediction9 citations · 2024
- 5
- 6Object and Relation Centric Representations for Push Effect Prediction4 citations · 2023
- 7Object and Relation Centric Representations for Push Effect Prediction3 citations · 2021