Lifelong learning for disturbance rejection on mobile robots
David Isele, José Marcio Luna, Eric Eaton, Gabriel V. de la Cruz, James Irwin, Brandon Kallaher, Matthew E. Taylor
Abstract
No two robots are exactly the same—even for a given model of robot, different units will require slightly different controllers. Furthermore, because robots change and degrade over time, a controller will need to change over time to remain optimal. This paper leverages lifelong learning in order to learn controllers for different robots. In particular, we show that by learning a set of control policies over robots with different (unknown) motion models, we can quickly adapt to changes in the robot, or learn a controller for a new robot with a unique set of disturbances. Furthermore, the approach is completely model-free, allowing us to apply this method to robots that have not, or cannot, be fully modeled.
BibTeX
@inproceedings{iros2016_lifelonglearning,
title = {Lifelong learning for disturbance rejection on mobile robots},
author = {David Isele and José Marcio Luna and Eric Eaton and Gabriel V. de la Cruz and James Irwin and Brandon Kallaher and Matthew E. Taylor},
booktitle = {IROS 2016},
year = {2016}
}