Practical Trajectory Learning Algorithms for Robot Manipulators
Several alternative learning control algorithms are discussed, both from an inverse dynamics and an optimization point of view. The learning laws are derived in discrete time and do not need acceleration measurements. A simple algorithm using a constant learning operator is proposed to run in additi...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Norwegian Society of Automatic Control
1990-04-01
|
| Series: | Modeling, Identification and Control |
| Online Access: | http://www.mic-journal.no/PDF/1990/MIC-1990-2-4.pdf |
| _version_ | 1818345488239296512 |
|---|---|
| author | Erling Lunde Jens G. Balchen |
| author_facet | Erling Lunde Jens G. Balchen |
| author_sort | Erling Lunde |
| collection | DOAJ |
| description | Several alternative learning control algorithms are discussed, both from an inverse dynamics and an optimization point of view. The learning laws are derived in discrete time and do not need acceleration measurements. A simple algorithm using a constant learning operator is proposed to run in addition to a simple (PD) feedback controller. Its performance is comparable to other algorithms, and it works under non-ideal conditions where the others fail. Two simulation examples on (1) learning dynamic control, and (2) learning optimal redundancy resolution, are presented. |
| first_indexed | 2024-12-13T17:03:10Z |
| format | Article |
| id | doaj.art-63cba53c4fe442dfb179b81376447cb5 |
| institution | Directory Open Access Journal |
| issn | 0332-7353 1890-1328 |
| language | English |
| last_indexed | 2024-12-13T17:03:10Z |
| publishDate | 1990-04-01 |
| publisher | Norwegian Society of Automatic Control |
| record_format | Article |
| series | Modeling, Identification and Control |
| spelling | doaj.art-63cba53c4fe442dfb179b81376447cb52022-12-21T23:37:44ZengNorwegian Society of Automatic ControlModeling, Identification and Control0332-73531890-13281990-04-0111210912110.4173/mic.1990.2.4Practical Trajectory Learning Algorithms for Robot ManipulatorsErling LundeJens G. BalchenSeveral alternative learning control algorithms are discussed, both from an inverse dynamics and an optimization point of view. The learning laws are derived in discrete time and do not need acceleration measurements. A simple algorithm using a constant learning operator is proposed to run in addition to a simple (PD) feedback controller. Its performance is comparable to other algorithms, and it works under non-ideal conditions where the others fail. Two simulation examples on (1) learning dynamic control, and (2) learning optimal redundancy resolution, are presented.http://www.mic-journal.no/PDF/1990/MIC-1990-2-4.pdf |
| spellingShingle | Erling Lunde Jens G. Balchen Practical Trajectory Learning Algorithms for Robot Manipulators Modeling, Identification and Control |
| title | Practical Trajectory Learning Algorithms for Robot Manipulators |
| title_full | Practical Trajectory Learning Algorithms for Robot Manipulators |
| title_fullStr | Practical Trajectory Learning Algorithms for Robot Manipulators |
| title_full_unstemmed | Practical Trajectory Learning Algorithms for Robot Manipulators |
| title_short | Practical Trajectory Learning Algorithms for Robot Manipulators |
| title_sort | practical trajectory learning algorithms for robot manipulators |
| url | http://www.mic-journal.no/PDF/1990/MIC-1990-2-4.pdf |
| work_keys_str_mv | AT erlinglunde practicaltrajectorylearningalgorithmsforrobotmanipulators AT jensgbalchen practicaltrajectorylearningalgorithmsforrobotmanipulators |