Papers
24
Total Citations
292
H-Index
10
About
Mohammad Farrokhi is a prominent robotics and control systems researcher whose work spans intelligent control, robot manipulation, and autonomous locomotion. His research sits at the intersection of advanced control theory and artificial intelligence, with particular expertise in neuro-fuzzy systems, nonlinear model predictive control (NMPC), and adaptive learning methods applied to complex robotic platforms. Farrokhi's most celebrated contribution, garnering 80 citations, introduced a Lyapunov-stable neural network and quadratic programming framework for real-time inverse kinematics of redundant manipulators — a foundational problem in robotics that his approach solved with unprecedented computational efficiency. His early work on adaptive neuro-fuzzy hybrid position/force control (2006, 32 citations) established robust strategies for manipulators interacting with uncertain environments, while his series of NMPC-based papers demonstrated elegant solutions to obstacle avoidance and path tracking without requiring pre-planned trajectories. Farrokhi has also made meaningful strides in legged robotics, developing predictive control architectures for both biped and quadruped robots that enable stable, adaptive walking over challenging terrain. His 2016 work on biped gait generation with adaptive NMPC reflects 26 citations and underscores his sustained relevance in the field. Collectively, his body of work represents a rigorous and practically impactful contribution to intelligent robotics control.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5A new fuzzy adaptive control for a Quadrotor flying robot15 citations · 2013
- 6
- 7
- 8
- 9Fuzzy-backstepping control of quadruped robots11 citations · 2020
- 10Dynamic walking of biped robots with obstacles using predictive controller11 citations · 2011