Publication
Kinematic Bézier maps
Journal Article (2012)
Journal
IEEE Transactions on Systems, Man and Cybernetics: Part B
Pages
1215-1230
Volume
42
Number
4
Doc link
http://dx.doi.org/10.1109/TSMCB.2012.2188507
File
Authors
-
Ulbrich, Stefan
-
Ruiz de Angulo García, Vicente
-
Torras Genís, Carme
-
Asfour, Tamim
-
Dillman, Rudiger
Projects associated
MIPRCV: CONSOLIDER-INGENIO 2010 Multimodal interaction in pattern recognition and computer vision
SGR ROBÒTICA: Grup de recerca consolidat - Grup de Robòtica
CUIK++: An Extension of Branch-and-Prune Techniques for Motion Analysis and Synthesis of Complex Robotic Systems
IntellAct: Intelligent observation and execution of Actions and manipulations
Abstract
The kinematics of a robot with many degrees of freedom is a very complex function. Learning this function for a large workspace with a good precision requires a huge number of training samples, i.e., robot movements. In this work, we introduce the Kinematic Bézier Map (KB-Map), a parametrizable model without the generality of other systems, but whose structure readily incorporates some of the geometric constraints of a kinematic function. In this way, the number of training samples required is drastically reduced. Moreover, the simplicity of the model reduces learning to solving a linear least squares problem. Systematic experiments have been carried out showing the excellent interpolation and extrapolation capabilities of KB-Maps and their relatively low sensitivity to noise.
Categories
learning (artificial intelligence), robot kinematics, robots.
Author keywords
learning, robot kinematics, humanoid robots
Scientific reference
S. Ulbrich, V. Ruiz de Angulo, C. Torras, T. Asfour and R. Dillman. Kinematic Bézier maps. IEEE Transactions on Systems, Man and Cybernetics: Part B, 42(4): 1215-1230, 2012.
Follow us!