Papers
38
Total Citations
543
H-Index
13
About
Mahmoud Tarokh is a robotics and intelligent systems researcher whose work spans robot kinematics, motion planning, autonomous navigation, and intelligent control. His research has made significant contributions to solving some of the most computationally challenging problems in robotics, particularly in kinematics and path planning for complex robotic systems. Tarokh's most influential work applies machine learning and decomposition techniques to robot kinematics. His 2013 paper on using Support Vector Regression to solve forward kinematics in parallel robots has garnered 68 citations, while his 2007 work on inverse kinematics decomposition for 7-DOF robots — enabling extremely fast computation suitable for real-time manipulation and animation — has accumulated 39 citations. His 2001 manipulator path planning decomposition algorithm further cemented his reputation in this domain. Beyond manipulation, Tarokh has contributed substantially to autonomous rover navigation in rough terrain, with notable work on hybrid intelligent path planning and high-mobility rover kinematics accumulating nearly 100 combined citations. His research also extends to intelligent control systems, including adaptive fuzzy force control, decoupled nonlinear trajectory tracking controllers, and multi-robot security systems. His consistent application of AI techniques — fuzzy logic, genetic algorithms, and machine learning — to real-world robotics challenges reflects a career dedicated to bridging theoretical rigor with practical innovation.
Research Focus
Key Achievements
Top Papers
- 1
- 2Hybrid intelligent path planning for articulated rovers in rough terrain57 citations · 2008
- 3
- 4
- 5Manipulator path planning by decomposition: algorithm and analysis30 citations · 2001
- 6
- 7Decoupled nonlinear three-term controllers for robot trajectory tracking24 citations · 1999
- 8
- 9
- 10Fuzzy logic decision making for multi-robot security systems17 citations · 2010