Cooperative suspended object manipulation using reinforcement learning and energy-based control

Author

Palunko, Ivana ; Donner, Philine ; Buss, Martin ; Hirche, Sandra

Author_Institution

Fac. of Electr. Eng. & Comput., Univ. of Zagreb, Zagreb, Croatia

fYear

2014

fDate

14-18 Sept. 2014

Firstpage

885

Lastpage

891

Abstract

Cooperative dynamic object manipulation can extend the manipulation capabilities of robot-robot and human-robot teams. In order to be able to inject energy into various suspended objects of unknown parameters, in this paper we propose an adaptive controller which combines reinforcement learning with energy based swing-up control. The proposed controller is successfully verified in a single robot and human-robot experimental setup for different types of suspended objects.

Keywords

adaptive control; human-robot interaction; intelligent robots; learning (artificial intelligence); manipulators; multi-robot systems; adaptive controller; cooperative dynamic object manipulation; cooperative suspended object manipulation; energy based swing-up control; energy-based control; human-robot experimental setup; human-robot team; manipulation capabilities; reinforcement learning; robot-robot team; suspended objects; Adaptation models; Approximation methods; Frequency estimation; Gold; Manipulator dynamics; Mathematical model;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Robots and Systems (IROS 2014), 2014 IEEE/RSJ International Conference on

Conference_Location

Chicago, IL

Type

conf

DOI

10.1109/IROS.2014.6942664

Filename

6942664