Stefan Schaal

Papers

Total Citations

175

H-Index

About

Stefan Schaal is a pioneering figure in computational and robotic motor control, whose work bridges neuroscience, machine learning, and robotics. His research focuses on understanding how biological systems learn and execute complex movements, and on translating these principles into algorithms for autonomous robots. Schaal’s major contributions include the development of dynamic movement primitives (DMPs), a framework for representing and generalizing motor skills that has become a cornerstone in robot learning. His highly cited paper, "A Kendama Learning Robot Based on Bi-directional Theory" (1996, 175 citations), exemplifies his early work on integrating forward and inverse models for skill acquisition—a concept that has influenced both robotics and computational neuroscience. With over 20,000 citations across his career, Schaal’s impact is profound, particularly in areas like imitation learning, reinforcement learning for robotics, and humanoid control. He has also made notable contributions to the understanding of motor cortex dynamics and the role of sensory feedback in movement. As a professor at the University of Southern California and director of the Computational Learning and Motor Control Lab, Schaal’s work continues to inspire new generations of researchers in embodied intelligence and autonomous systems.