Guez

About

Guez is a pioneering researcher in the intersection of neural networks and robotics, with a particular focus on solving complex kinematic problems through computational intelligence. His landmark 1988 paper, "Solution to the Inverse Kinematics Problem in Robotics by Neural Networks," garnered an impressive 167 citations and established him as an early innovator in applying neural network models to one of robotics' most computationally demanding challenges. By demonstrating that neural networks could generate accurate approximate solutions to inverse kinematics — subsequently refined through local differential methods — Guez significantly reduced the processing burden on robotic systems. Building on this foundation, his 1989 follow-up work introduced a hybrid multilayer feedforward network approach, accumulating 40 additional citations, which further accelerated convergence in iterative kinematic solutions by leveraging trained networks as intelligent starting points for optimization. Guez's contributions were remarkably ahead of their time, anticipating the deep integration of machine learning into robotics that would come to define the field decades later. His work remains essential reading for researchers exploring data-driven approaches to robotic manipulation and control.

Research Focus

Key Achievements

Top Papers

1. 1
   Solution to the inverse kinematics problem in robotics by neural networks

   167 citations · 1988
2. 2
   Accelerated convergence in the inverse kinematics via multilayer feedforward networks

   40 citations · 1989

Key Collaborators

Contact & Links