Max Robotics — Global Service Robot Directory + US Certification

About

Micha Hersch is a robotics researcher whose work sits at the intersection of robot learning, motor control, and human-robot interaction. His research focuses primarily on programming robots by demonstration, dynamical systems-based motion learning, and the development of biologically-inspired controllers for humanoid robots. Hersch's most influential contribution — "Dynamical System Modulation for Robot Learning via Kinesthetic Demonstrations" (2008, 237 citations) — introduced a robust framework enabling robots to acquire goal-directed skills through physical guidance, reliably reproducing learned movements despite environmental perturbations and varying initial conditions. Complementing this, his work on reinforcement learning for imitation of constrained reaching movements (2007, 145 citations) addressed a fundamental challenge in programming-by-demonstration: generalizing beyond what a demonstrator explicitly shows. His broader research agenda explores how robots can develop human-like representations of their bodies and surrounding space. Notably, he developed algorithms for online body schema learning in humanoid robots, allowing them to visually acquire their own kinematics without prior knowledge. Drawing inspiration from neuroscience, Hersch also proposed biologically-grounded controllers for reaching movements, bridging theories of human motor control and robotics. His doctoral thesis synthesized these threads into a unified framework for adaptive peripersonal space representation — a compelling vision for cognitively grounded robot autonomy.