Zeeshan Shareef
Technische Universität Braunschweig, Paderborn University, Bielefeld University
Papers
8
Total Citations
151
H-Index
6
About
Zeeshan Shareef is a robotics researcher whose work bridges the gap between analytical models and data-driven learning for robotic control. His primary research areas include inverse dynamics modeling, trajectory optimization, and model-based robot control—with a particular focus on improving the accuracy and adaptability of robotic manipulators. Shareef's most impactful contribution is his 2017 paper on hybrid analytical and data-driven modeling for feed-forward robot control, which has garnered 81 citations and addresses the limitations of purely mechanical models by integrating learning-based approaches. He pioneered Independent Joint Learning (IJL), a modular method for refining inverse dynamics models of robots like the KUKA LWR IV+, and demonstrated its generalization to varying load conditions through regression in the model space. Shareef also advanced trajectory planning by applying Discrete Mechanics and Optimal Control (DMOC) to solve path planning and trajectory optimization simultaneously—a departure from traditional sequential approaches. His work on cooperative ball juggling with DELTA robots, which eliminates the need for visual guidance, showcases his ability to tackle complex dynamic tasks. With a citation count exceeding 150 across his key publications, Shareef's research continues to influence the development of more accurate, adaptable, and autonomous robotic systems.
Research Focus
Key Achievements
Top Papers
- 1Hybrid Analytical and Data-Driven Modeling for Feed-Forward Robot Control †81 citations · 2017
- 2
- 3
- 4
- 5
- 6
- 7
- 8Dynamical model of ball juggling Delta robots using reflection laws3 citations · 2013