Max Robotics — Global Service Robot Directory + US Certification

About

Nicola Milano’s research career spans three decades of foundational work in robotics, from the mathematical underpinnings of manipulator control to the frontiers of evolutionary and embodied AI. His core contributions lie in solving the inverse kinematics problem—the challenge of calculating how a robot arm should move to reach a desired position—with a particular focus on handling singularities and ensuring robust, efficient computation. His most influential paper, “A fast procedure for manipulator inverse kinematics evaluation and pseudoinverse robustness” (1992, 23 citations), introduced an original scheme that leverages the Jacobian matrix norm to prevent instability, a method that became a practical reference for roboticists. He further refined this with a damped least-squares solution in 2005 (13 citations), offering a faster, more reliable approach to singularity avoidance. Milano also developed a symbolic procedure for computing a dexterity measure (1991), providing a theoretical tool for analyzing manipulator performance. More recently, his work has expanded into evolutionary robotics and embodied language learning, exploring how phenotypic complexity affects evolvability (2022) and how robots can learn language from minimal experiences (2025). This trajectory from precise kinematic algorithms to the messy realities of learning and evolution showcases a career dedicated to making robots both more capable and more adaptable.