Paper Info
Title
Reinforcement learning based compensation methods for robot manipulators.
Abstract
Smart robotics will be a core feature while migrating from Industry 3.0 (i.e., mass manufacturing) to Industry 4.0 (i.e., customized or social manufacturing). A key characteristic of a smart system is its ability to learn. For smart manufacturing, this means incorporating learning capabilities into the current fixed, repetitive, task-oriented industrial manipulators, thus rendering them ‘smart’. In this paper we introduce two reinforcement learning (RL) based compensation methods. The learned correction signal, which compensates for unmodeled aberrations, is added to the existing nominal input with an objective to enhance the control performance. The proposed learning algorithms are evaluated on a 6-DoF industrial robotic manipulator arm to follow different kinds of reference paths, such as square or a circular path, or to track a trajectory on a three dimensional surface. In an extensive experimental study we compare the performance of our learning-based methods with well-known tracking controllers, namely, proportional-derivative (PD), model predictive control (MPC), and iterative learning control (ILC). The experimental results show a considerable performance improvement thanks to our RL-based methods when compared to PD, MPC, and ILC.
Year
DOI
Venue
2019
10.1016/j.engappai.2018.11.006
Engineering Applications of Artificial Intelligence
Keywords
Field
DocType
Reinforcement learning,Tracking control,Robotics,Actor-critic scheme
Smart system,Computer science,Model predictive control,Control engineering,Artificial intelligence,Iterative learning control,Rendering (computer graphics),Robotics,Machine learning,Trajectory,Reinforcement learning,Performance improvement
Journal
Volume
ISSN
Citations 
78
0952-1976
4
PageRank 
References 
Authors
0.56
10
4
Name
Order
Citations
PageRank
Yudha P. Pane141.57
Subramanya P. Nageshrao2454.95
jens kober391545.54
Robert Babuska42200164.90