Journal article 481 views 131 downloads
Novel Hybrid Adaptive Controller for Manipulation in Complex Perturbation Environments
Alex M. C. Smith,
Chenguang Yang,
Hongbin Ma,
Phil Culverhouse,
Angelo Cangelosi,
Etienne Burdet
PLOS ONE, Volume: 10, Issue: 6, Start page: e0129281
Swansea University Author: Chenguang Yang
DOI (Published version): 10.1371/journal.pone.0129281
Abstract
In this paper we present a hybrid control scheme, combining the advantages of task-spaceand joint-space control. The controller is based on a human-like adaptive design, which minimisesboth control effort and tracking error. Our novel hybrid adaptive controller has beentested in extensive simulation...
| Published in: | PLOS ONE |
|---|---|
| ISSN: | 1932-6203 |
| Published: |
2015
|
| Online Access: |
Check full text
|
| URI: | https://cronfa.swan.ac.uk/Record/cronfa27020 |
| Abstract: |
In this paper we present a hybrid control scheme, combining the advantages of task-spaceand joint-space control. The controller is based on a human-like adaptive design, which minimisesboth control effort and tracking error. Our novel hybrid adaptive controller has beentested in extensive simulations, in a scenario where a Baxter robot manipulator is affectedby external disturbances in the form of interaction with the environment and tool-like end-effectorperturbations. The results demonstrated improved performance in the hybrid controllerover both of its component parts. In addition, we introduce a novel method for onlineadaptation of learning parameters, using the fuzzy control formalism to utilise expert knowledgefrom the experimenter. This mechanism of meta-learning induces further improvementin performance and avoids the need for tuning through trial testing. |
|---|---|
| College: |
Faculty of Science and Engineering |
| Issue: |
6 |
| Start Page: |
e0129281 |