Trajectory Optimization for the Handling of Elastically Coupled Objects via Reinforcement Learning and Flatness-Based Control

Show simple item record

dc.identifier.uri http://dx.doi.org/10.15488/10390
dc.identifier.uri https://www.repo.uni-hannover.de/handle/123456789/10464
dc.contributor.author Kaczor, Daniel eng
dc.contributor.author Bensch, Martin eng
dc.contributor.author Schappler, Moritz eng
dc.contributor.author Ortmaier, Tobias eng
dc.date.accessioned 2021-02-10T12:46:37Z
dc.date.available 2021-02-10T12:46:37Z
dc.date.issued 2020-07-21
dc.identifier.citation Kaczor, Daniel; Bensch, Martin; Schappler, Moritz; Ortmaier, Tobias: Trajectory Optimization for the Handling of Elastically Coupled Objects via Reinforcement Learning and Flatness-Based Control. In: Schüppstuhl, T.; Tracht, K.; Henrich, D. (Eds.): Annals of Scientific Society for Assembly, Handling and Industrial Robotics. Berlin: Springer Vieweg, 2020, S. 319-329. DOI: https://doi.org/10.1007/978-3-662-61755-7_29 eng
dc.description.abstract Positioning objects in industrial handling applications is often compromised by elasticity-induced oscillations reducing the possible motion time and thereby the performance and profitability of the automation solution. Existing approaches for oscillation reduction mostly focus on the elasticity of the handling system itself, i.e. the robot structure. Depending on the task, elastic parts or elastic grippers like suction cups strongly influence the oscillation and prevent faster positioning. In this paper, the problem is investigated exemplarily with a typical handling robot and an additional end effector setup representing the elastic load. The handling object is modeled as a base-excited spring and mass, making the proposed approach independent from the robot structure. A model-based feed-forward control based on differential flatness and a machine-learning method are used to reduce oscillations solely with a modification of the end effector trajectory of the robot. Both methods achieve a reduction of oscillation amplitudes of 85% for the test setup, promising a significant increase in performance. Further investigations on the uncertainty of the parameterization prove the applicability of the not yet widely-used learning approach in the field of oscillation reduction. eng
dc.language.iso eng eng
dc.publisher Berlin : Springer Vieweg
dc.relation.ispartof Annals of Scientific Society for Assembly, Handling and Industrial Robotics, S. 319 - 329 eng
dc.rights CC BY 4.0 Unported eng
dc.rights.uri https://creativecommons.org/licenses/by/4.0/ eng
dc.subject flatness-based control eng
dc.subject reinforcement learning eng
dc.subject double deep Q-network eng
dc.subject trajectory optimization eng
dc.subject oscillation reduction eng
dc.subject.ddc 620 | Ingenieurwissenschaften und Maschinenbau eng
dc.title Trajectory Optimization for the Handling of Elastically Coupled Objects via Reinforcement Learning and Flatness-Based Control eng
dc.type conferenceObject eng
dc.type Text eng
dc.relation.doi 10.1007/978-3-662-61755-7_29
dc.description.version acceptedVersion eng
tib.accessRights frei zug�nglich eng


Files in this item

This item appears in the following Collection(s):

Show simple item record

 

Search the repository


Browse

My Account

Usage Statistics