Imperial College London

Professor Yiannis Demiris

Faculty of EngineeringDepartment of Electrical and Electronic Engineering

Professor of Human-Centred Robotics, Head of ISN



+44 (0)20 7594 6300y.demiris Website




1014Electrical EngineeringSouth Kensington Campus






BibTex format

author = {Simmons, G and Demiris, Y},
doi = {10.1109/ICHR.2004.1442124},
pages = {215--234},
publisher = {IEEE},
title = {Imitation of human demonstration using a biologically inspired modular optimal control scheme},
url = {},
year = {2004}

RIS format (EndNote, RefMan)

AB - Download Citation Email Print Request Permissions Save to ProjectProgress in the field of humanoid robotics and the need to find simpler ways to program such robots has prompted research into computational models for robotic learning from human demonstration. To further investigate biologically inspired human-like robotic movement and imitation, we have constructed a framework based on three key features of human movement and planning: optimality, modularity and learning. In this paper we describe a computational motor system, based on the minimum variance model of human movement, that uses optimality principles to produce human-like movement in a robot arm. Within this motor system different movements are represented in a modular structure. When the system observes a demonstrated movement, the motor system uses these modules to produce motor commands which are used to update an internal state representation. This is used so that the system can recognize known movements and move the robot arm accordingly, or extract key features from the demonstrated movement and use them to learn a new module. The active involvement of the motor system in the recognition and learning of observed movements has its theoretical basis in the direct matching hypothesis and the use of a model for human-like movement allows the system to learn from human demonstration.
AU - Simmons,G
AU - Demiris,Y
DO - 10.1109/ICHR.2004.1442124
EP - 234
PY - 2004///
SP - 215
TI - Imitation of human demonstration using a biologically inspired modular optimal control scheme
UR -
ER -