Use of Learning Methods to Improve Kinematic Models
Kinematic model is the basic aspect in robot design and motion planning. Kinematic models are idealized, however there exist certain specific aspects of particular robot or environment, so that during navigation, the robot can significantly deviate from the planned trajectory. To increase the accura...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2013-06-01
|
| Series: | Applied Computer Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.2478/acss-2013-0009 |
| _version_ | 1818586810869088256 |
|---|---|
| author | Priedniece Kintija Nikitenko Agris Liekna Aleksis Kulikovskis Guntis |
| author_facet | Priedniece Kintija Nikitenko Agris Liekna Aleksis Kulikovskis Guntis |
| author_sort | Priedniece Kintija |
| collection | DOAJ |
| description | Kinematic model is the basic aspect in robot design and motion planning. Kinematic models are idealized, however there exist certain specific aspects of particular robot or environment, so that during navigation, the robot can significantly deviate from the planned trajectory. To increase the accuracy of motions, kinematic model can be improved and to achieve that the artificial intelligence methods can be used. In case of fixed base robots different approaches are used to train kinematics, at the same time, for the mobile base robots it proves to be a more complicated task. The reason is that a mobile robot can move unbound with respect to environment thus it is difficult to control the platform without deviation from the target position, which leads to inaccuracy in the position estimate. This paper presents the method meant for improvement of the accuracy of motion of differential drive platform. Genetic programming is used to obtain the wheel velocity function, from which the coefficient, which describes different factor influence on motion, is obtained. As a result, the kinematic model of a particular platform for a particular task is obtained. This method is effective because the developed kinematic model is more specific than the general one. |
| first_indexed | 2024-12-16T08:58:53Z |
| format | Article |
| id | doaj.art-aa7bdaa6b2da4f22aab069e70d9085bc |
| institution | Directory Open Access Journal |
| issn | 2255-8691 |
| language | English |
| last_indexed | 2024-12-16T08:58:53Z |
| publishDate | 2013-06-01 |
| publisher | Sciendo |
| record_format | Article |
| series | Applied Computer Systems |
| spelling | doaj.art-aa7bdaa6b2da4f22aab069e70d9085bc2022-12-21T22:37:13ZengSciendoApplied Computer Systems2255-86912013-06-01141737910.2478/acss-2013-0009Use of Learning Methods to Improve Kinematic ModelsPriedniece Kintija0Nikitenko Agris1Liekna Aleksis2Kulikovskis Guntis3Riga Technical University, Faculty of Computer Science and Information Technology, Institute of Applied Computer SystemsRiga Technical University, Faculty of Computer Science and Information Technology, Institute of Applied Computer SystemsRiga Technical University, Faculty of Computer Science and Information Technology, Institute of Applied Computer SystemsRiga Technical University, Faculty of Computer Science and Information Technology, Institute of Applied Computer SystemsKinematic model is the basic aspect in robot design and motion planning. Kinematic models are idealized, however there exist certain specific aspects of particular robot or environment, so that during navigation, the robot can significantly deviate from the planned trajectory. To increase the accuracy of motions, kinematic model can be improved and to achieve that the artificial intelligence methods can be used. In case of fixed base robots different approaches are used to train kinematics, at the same time, for the mobile base robots it proves to be a more complicated task. The reason is that a mobile robot can move unbound with respect to environment thus it is difficult to control the platform without deviation from the target position, which leads to inaccuracy in the position estimate. This paper presents the method meant for improvement of the accuracy of motion of differential drive platform. Genetic programming is used to obtain the wheel velocity function, from which the coefficient, which describes different factor influence on motion, is obtained. As a result, the kinematic model of a particular platform for a particular task is obtained. This method is effective because the developed kinematic model is more specific than the general one.https://doi.org/10.2478/acss-2013-0009genetic programminglearning kinematicmobile platforms |
| spellingShingle | Priedniece Kintija Nikitenko Agris Liekna Aleksis Kulikovskis Guntis Use of Learning Methods to Improve Kinematic Models Applied Computer Systems genetic programming learning kinematic mobile platforms |
| title | Use of Learning Methods to Improve Kinematic Models |
| title_full | Use of Learning Methods to Improve Kinematic Models |
| title_fullStr | Use of Learning Methods to Improve Kinematic Models |
| title_full_unstemmed | Use of Learning Methods to Improve Kinematic Models |
| title_short | Use of Learning Methods to Improve Kinematic Models |
| title_sort | use of learning methods to improve kinematic models |
| topic | genetic programming learning kinematic mobile platforms |
| url | https://doi.org/10.2478/acss-2013-0009 |
| work_keys_str_mv | AT priedniecekintija useoflearningmethodstoimprovekinematicmodels AT nikitenkoagris useoflearningmethodstoimprovekinematicmodels AT lieknaaleksis useoflearningmethodstoimprovekinematicmodels AT kulikovskisguntis useoflearningmethodstoimprovekinematicmodels |