Reinforcement Learning for Manipulators without Direct Obstacle Perception in Physically Constrained Environments

Reinforcement Learning algorithms have the downside of potentially dangerous exploration of unknown states, which makes them largely unsuitable for the use on serial manipulators in an industrial setting. In this paper, we make use of a policy search algorithm and provide two extensions that aim to...

Full description

Saved in:
Bibliographic Details
Published in:Procedia manufacturing 2017, Vol.11, p.329-337
Main Authors: Ossenkopf, Marie, Ennen, Philipp, Vossen, Rene, Jeschke, Sabina
Format: Article
Language:English
Subjects:
Assembly Robot
Dynamic Movement Primitives
Intelligent Manufacturing
Potential Field
Relative Entropy Policy Search
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Reinforcement Learning algorithms have the downside of potentially dangerous exploration of unknown states, which makes them largely unsuitable for the use on serial manipulators in an industrial setting. In this paper, we make use of a policy search algorithm and provide two extensions that aim to make learning more applicable on robots in industrial environments without the need of complex sensors. They build upon the use of Dynamic Movement Primitives (DMPs) as policy representation. Rather than model explicitly the skills of the robot we describe actions the robot should not try to do. First, we implement potential fields into the DMPs to keep planned movements inside the robot's workspace. Second, we monitor and evaluate the deviation in the DMPs to recognize and learn from collisions. Both extensions are evaluated in a simulation
ISSN:2351-9789
2351-9789
DOI:10.1016/j.promfg.2017.07.115