Robot Programming by Demonstration

Couverture
EPFL Press, 24 août 2009 - 222 pages

Also referred to as learning by imitation, tutelage, or apprenticeship learning, Programming by Demonstration (PbD) develops methods by which new skills can be transmitted to a robot. This book examines methods by which robots learn new skills through human guidance. Taking a practical perspective, it covers a broad range of applications, including service robots. The text addresses the challenges involved in investigating methods by which PbD is used to provide robots with a generic and adaptive model of control. Drawing on findings from robot control, human-robot interaction, applied machine learning, artificial intelligence, and developmental and cognitive psychology, the book contains a large set of didactic and illustrative examples. Practical and comprehensive machine learning source codes are available on the book’s companion website: http://www.programming-by-demonstration.org

 

Pages sélectionnées

Table des matières

ACKNOWLEDGMENT
1
SYSTEM ARCHITECTURE
31
estimation of
64
COMPARISON AND OPTIMIZATION OF THE PARAMETERS
75
ཙཙ
89
HANDLING OF CONSTRAINTS IN JOINT SPACE
101
EXTENSION TO DYNAMICAL SYSTEM AND HANDLING
129
TRANSFERRING SKILLS THROUGH ACTIVE
147
USING SOCIAL CUES TO SPEED UP
171
DISCUSSION FUTURE WORK AND CONCLUSIONS
178
REFERENCES
201
INDEX
221
Droits d'auteur

Expressions et termes fréquents

algorithm approach automation ICRA Bayesian Information Criterion Billard Calinon Cartesian space chess piece components computed considered covariance matrices datapoints dataset Dautenhahn defined Demo Dillmann dimensionality DOFs dynamics EM algorithm encoding end-effector estimation experiment extracted framework Gaussian distributions Gaussian Mixture Regression gestures GMM parameters graph grasping Hidden Markov Models human motion human-robot interaction humanoid robot IEEE IEEE intl conf incremental learning initial positions inverse kinematics joint angle trajectories joint space keypoints kinesthetic kinesthetic teaching latent space machine learning matrix method mirror neuron Mixture Model motion sensors motor Nehaniv neural number of Gaussians object observed optimal presented in Section probabilistic Proc proposed representation represented reproduce the skill reproduction attempt retrieval robotics and automation Schaal segmentation sequence signals social cues solution space of motion statistical task constraints task space temporal tion trajectories variables various velocity हुर

Informations bibliographiques

TitreRobot Programming by Demonstration
Engineering sciences
Engineering sciences: Microtechnology
AuteurSylvain Calinon
Éditionillustrée
ÉditeurEPFL Press, 2009
ISBN1439808678, 9781439808672
Longueur222 pages
  
Exporter la citationBiBTeX EndNote RefMan