Vali Derhami
Papers
10
Total Citations
123
H-Index
6
About
Vali Derhami is a robotics and artificial intelligence researcher whose work sits at the intersection of machine learning, control systems, and autonomous robot navigation. His research primarily explores how intelligent learning algorithms — including reinforcement learning, fuzzy logic, and deep learning — can be harnessed to solve complex real-world robotics challenges. Derhami's most influential contribution, "Supervised Fuzzy Reinforcement Learning for Robot Navigation" (2015), has accumulated 61 citations, establishing him as a notable voice in adaptive robot control. His work on visual servoing — developing controllers that guide robot manipulators using camera-based feedback without requiring precise pre-built models — represents a particularly practical strand of his research, addressing real-world uncertainty in robotic systems. He has further extended these ideas through adaptive and 3D trajectory-tracking frameworks using depth sensors like the Kinect camera. More recently, Derhami has investigated how recurrent neural networks and deep learning can empower robots to navigate challenging off-road environments by leveraging sequences of past states, and how feature selection can be optimized specifically for robotic control tasks. His work on humanoid robot walking using Fuzzy Sarsa Learning also demonstrates a breadth spanning both mobile and articulated robotic systems — making his research portfolio valuable reading for students working in intelligent robotics and autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1Supervised fuzzy reinforcement learning for robot navigation61 citations · 2015
- 2Visual servoing control of robot manipulator with Jacobian matrix estimation18 citations · 2014
- 3
- 4
- 5
- 6Control of humanoid robot walking by Fuzzy Sarsa Learning6 citations · 2015
- 7
- 8
- 9
- 10