TU Darmstadt / ULB / TUprints

Intelligent Real-Time Control of a Multifingered Robot Gripper by Learning Incremental Actions

Kleinmann, Karl ; Hormel, Michael ; Paetsch, Wolfgang (2023)
Intelligent Real-Time Control of a Multifingered Robot Gripper by Learning Incremental Actions.
In: IFAC Proceedings Volumes, 1992, 25 (10)
doi: 10.26083/tuprints-00023371
Article, Secondary publication, Publisher's Version

[img] Text
1-s2.0-S1474667017508381-main.pdf
Copyright Information: CC BY-NC-ND 4.0 International - Creative Commons, Attribution NonCommercial, NoDerivs.

Download (1MB)
Item Type: Article
Type of entry: Secondary publication
Title: Intelligent Real-Time Control of a Multifingered Robot Gripper by Learning Incremental Actions
Language: English
Date: 2023
Place of Publication: Darmstadt
Year of primary publication: 1992
Publisher: IFAC - International Federation of Automatic Control
Journal or Publication Title: IFAC Proceedings Volumes
Volume of the journal: 25
Issue Number: 10
DOI: 10.26083/tuprints-00023371
Corresponding Links:
Origin: Secondary publication service
Abstract:

Learning control systems are expected to have several advantages over conventional approaches when dealing with complex, high-dimensional processes. One example is the task of controlling grasping operations of a multifingered, multijoined robot gripper, which has been designed and implemented at our robotics lab (the Darmstadt-Hand). The Advanced Gripper Control with Learning Algorithms -AGRICOLA- presented in this paper is able to maintain a stable grasp even if disturbances are applied. Also it works for objects of different sizes for which the grasping has not been learned. Compared to the conventional stiffness approach the performance of the learning system is equal but the design is much easier, since less knowledge about the gripper-hardware has to be taken into account. The main part of the learning control loop is an associative memory storing the grasping behaviour as determined by the choice of an objective function.

Uncontrolled Keywords: high-dimensional nonlinear process, stable grasp, object manipulation, associative memories, learning control loop
Status: Publisher's Version
URN: urn:nbn:de:tuda-tuprints-233712
Additional Information:

Zugl. Konferenzveröffentlichung: IFAC Symposium on Artificial Intelligence in Real Time Control, 16.-18.06.1992, Delft, Netherlands

Classification DDC: 600 Technology, medicine, applied sciences > 620 Engineering and machine engineering
Divisions: 18 Department of Electrical Engineering and Information Technology > Institut für Automatisierungstechnik und Mechatronik > Control Methods and Intelligent Systems
Date Deposited: 14 Mar 2023 10:49
Last Modified: 13 Jul 2023 14:36
URI: https://tuprints.ulb.tu-darmstadt.de/id/eprint/23371
PPN: 50961941X
Export:
Actions (login required)
View Item View Item