Seaar Al-Dabooni
Missouri University of Science and Technology, University of Basrah
Papers
3
Total Citations
37
H-Index
3
About
Seaar Al-Dabooni is a researcher specializing in adaptive dynamic programming (ADP), reinforcement learning, and intelligent control systems for mobile robotics. His work focuses on developing novel algorithms that enable robots to learn optimal behaviors in uncertain, dynamic environments. Al-Dabooni’s most influential contribution is the introduction of a direct heuristic dynamic programming method based on Dyna planning (Dyna_HDP), which accelerates online model learning in Markov decision processes—a key advancement for mobile robot path planning. This work has garnered 21 citations, reflecting its impact on the field. He has also advanced value-gradient learning (VGL) architectures, including hybrid neuro-fuzzy systems that compute optimal torque values for nonholonomic robots under uncertainty, and has explored convergence properties of recurrent neuro-fuzzy VGL with and without an actor. His research bridges theoretical ADP algorithms with practical robotic control, offering efficient, high-performance solutions for real-world navigation and tracking tasks. Al-Dabooni’s publications demonstrate a sustained focus on improving learning speed, stability, and robustness in autonomous systems, making his work valuable for students and researchers interested in intelligent control, reinforcement learning, and robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3