Omid Naghash Almasi

About

Omid Naghash Almasi is a researcher whose work sits at the intersection of robotics, control systems, and advanced computational intelligence. His primary research focus is on the dynamic modeling and identification of robotic manipulators, particularly using sophisticated machine learning techniques to overcome the challenges of non-linear system behavior. Almasi’s major contributions lie in applying Adaptive Neuro-Fuzzy Inference Systems (ANFIS) and Least-Square Support Vector Regression (LS-SVR) to accurately model complex robots, such as the Phantom Omni from SensAble Technologies. His 2014 paper on neuro-fuzzy identification for a Phantom robot (4 citations) established a foundational approach for Single-Input Single-Output (SISO) and Multiple-Input Single-Output (MISO) systems. He significantly advanced this work in his 2018 study (3 citations), where he tackled the more challenging Multiple-Input Multiple-Output (MIMO) identification of the Phantom Omni. Notably, this later work introduced a novel two-stage hybrid optimization strategy combining coupled simulated annealing with LS-SVR, demonstrating a sophisticated method for model selection that improves accuracy in non-linear robotic control. Almasi’s research provides critical pathways for enhancing the precision and reliability of robot control systems through intelligent data-driven modeling.

Research Focus

Key Achievements

Top Papers

1. 1
   Neuro–Fuzzy Based Approach for Identification of a Phantom Robot

   4 citations · 2014
2. 2
   Non‐linear MIMO identification of a Phantom Omni using LS‐SVR with a hybrid model selection

   3 citations · 2018

Key Collaborators

Contact & Links