Gu, Y., Wei, L. and Groß, R. orcid.org/0000-0003-1826-1375 (2020) Turing learning with hybrid discriminators: combining the best of active and passive learning. In: GECCO 2020: Proceedings of the Genetic and Evolutionary Computation Conference. GECCO 2020 : Genetic and Evolutionary Computation Conference, 08-12 Jul 2020, Cancún, Mexico. ACM Digital Library , New York, NY, USA , pp. 121-122. ISBN 9781450371278
Abstract
We propose a hybrid formulation of Turing Learning and study its application in mobile robotics. Instead of using a single type of discriminator, in the hybrid formulation, both active and passive discriminators are used. Active discriminators come to their judgments while interacting with the system under investigation, which helps improve model accuracy. Passive discriminators come to their judgments while only observing the system, allowing the reuse of data samples, which for real robots would be costly to obtain. To validate these ideas, we present a case study where a simulated embodied robot is required to calibrate its distance sensor through a process of self-modeling, and without metric information of where it resides within the environment. The results show that the hybrid formulation achieves a good level of accuracy with significantly fewer data samples from the robot. The findings suggest that the self-modeling process could be realized on a mobile physical robot with a limited time and energy budget.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2020 The Authors. This is an author-produced version of a paper subsequently published in GECCO '20: Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion. Uploaded in accordance with the publisher's self-archiving policy. |
Keywords: | Turing Learning; generative adversarial networks; robotics; active learning; sensor calibration |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Automatic Control and Systems Engineering (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 27 Apr 2020 08:15 |
Last Modified: | 02 Sep 2020 15:44 |
Status: | Published |
Publisher: | ACM Digital Library |
Refereed: | Yes |
Identification Number: | 10.1145/3377929.3390051 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:159796 |