The calibration of serial manipulators with high numbers of degrees of freedom by means of machine learning is a complex and time-consuming task. With the help of a simple strategy, this complexity can be drastically reduced and the speed of the learning procedure can be increased: When the robot is virtually divided into shorter kinematic chains, these subchains can be learned separately and, hence, much more efficiently than the complete kinematics. Such decompositions, however, require either the possibility to capture the poses of all end- effectors of all subchains at the same time, or they are limited to robots that fulfill special constraints. In this work, an alternative decomposition is presented that does not suffer from these limitations. An offline training algorithm is provided in which the composite subchains are learned sequentially with dedicated movements. A second training scheme is provided to train composite chains simultaneously and online. Both schemes can be used together with many machine learning algorithms. In the simulations, an algorithm using Parameterized Self-Organizing Maps (PSOM) modified for online learning and Gaussian Mixture Models (GMM) were chosen to show the correctness of the approach. The experimental results show that, using a two-fold decomposition, the number of samples required to reach a given precision is reduced to twice the square root of the original number. ; The work described in this paper was partially conducted within the EU Cognitive Systems projects Xperience (FP-7-270273) and GARNICS (FP-7-247947) funded by the European Commission, and the Generalitat de Catalunya through the Robotics group (SGR2009-00155). V. Ruiz de Angulo acknowledges support from Spanish Ministry of Science and Education, under the project DPI2010-18449. C. Torras acknowledges support from the Consolider project MIPRCV (CSD2007-00018). ; Peer Reviewed
General robot kinematics decomposition without intermediate markers
2012-01-01
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
DDC: | 629 |
Springer Verlag | 2021
|Advances in Robot Kinematics 2024
Springer Verlag | 2024
|Advances in robot kinematics 2022
TIBKAT | 2022
|Advances in robot kinematics 2020
TIBKAT | 2020
|