Max Robotics — Global Service Robot Directory + US Certification

About

Michal Puheim is a researcher whose work sits at the intersection of robotics, neural control, and intelligent systems. His primary contributions focus on solving the inverse kinematic problem for humanoid robots, specifically using neural network controllers to enable precise, real-time arm movements. In his highly cited 2014 paper, Puheim explored normalization techniques for neural network inputs and outputs, achieving 23 citations for advancing the accuracy of robotic arm control. His 2013 work on forward control of a robotic arm, cited 18 times, integrated stereo-vision tracking via the Tracking-Learning-Detection (TLD) method, allowing a Nao humanoid robot to track and touch objects—a significant step in vision-guided manipulation. Beyond robotics, Puheim has contributed to the design of Intelligent Spaces for IoT applications, proposing architectures that merge distributed sensor networks with autonomous decision-making. His research demonstrates a clear trajectory from foundational neural control methods to applied, vision-based robotic systems, and onward to broader smart environments. For students and researchers, Puheim’s work offers practical insights into bridging neural computation with physical robotic action, making his papers essential reading for those interested in humanoid robotics and intelligent automation.