DeepKoCo

Efficient latent planning with a task-relevant Koopman representation

Conference Paper (2021)
Author(s)

Bas van der Heijden (TU Delft - Learning & Autonomous Control)

Laura Ferranti (TU Delft - Learning & Autonomous Control)

Jens Kober (TU Delft - Learning & Autonomous Control)

Robert Babuska (TU Delft - Learning & Autonomous Control)

Research Group
Learning & Autonomous Control
DOI related publication
https://doi.org/10.1109/IROS51168.2021.9636408
More Info
expand_more
Publication Year
2021
Language
English
Research Group
Learning & Autonomous Control
Bibliographical Note
Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.@en
Pages (from-to)
183-189
ISBN (print)
978-1-6654-1715-0
ISBN (electronic)
978-1-6654-1714-3
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

This paper presents DeepKoCo, a novel modelbased agent that learns a latent Koopman representation from images. This representation allows DeepKoCo to plan efficiently using linear control methods, such as linear model predictive control. Compared to traditional agents, DeepKoCo learns taskrelevant dynamics, thanks to the use of a tailored lossy autoencoder network that allows DeepKoCo to learn latent dynamics that reconstruct and predict only observed costs, rather than all observed dynamics. As our results show, DeepKoCo achieves a similar final performance as traditional model-free methods on complex control tasks, while being considerably more robust to distractor dynamics, making the proposed agent more amenable for real-life applications.

Files

DeepKoCo_Efficient_latent_plan... (pdf)
(pdf | 1.97 Mb)
- Embargo expired in 16-06-2022
License info not available