Shahar Ben‐Menahem

About

Shahar Ben-Menahem is a researcher whose work lies at the intersection of robotics, neural network control, and nonlinear dynamics. His primary contributions focus on developing robust control strategies for robot manipulators, particularly by leveraging Radial Basis Function (RBF) neural networks. In his most cited work (11 citations), Ben-Menahem introduced a novel approach that eliminates the stringent Persistence of Excitation (PE) condition for desired trajectories by incorporating an error-minimizing dead-zone into the learning dynamics—a significant advancement for practical robotic applications. He further explored the reliability of such systems by analyzing the stochastic stability of neural-net robot controllers under signal-dependent noise in the learning rule (2 citations), addressing critical challenges in real-world, noisy environments. These studies underscore his dedication to bridging theoretical control theory with implementable, noise-tolerant robotic systems. Ben-Menahem’s research is particularly valuable for students and engineers seeking to understand how neural networks can be made both adaptive and stable in uncertain, real-world conditions, marking him as a thoughtful contributor to the field of intelligent robotics.

Research Focus

Key Achievements

Top Papers

1. 1
   Control of robots using radial basis function neural networks with dead‐zone

   11 citations · 2011
2. 2
   Stochastic stability of a neural‐net robot controller subject to signal‐dependent noise in the learning rule

   2 citations · 2009

Key Collaborators

Contact & Links