Adversarial Generation of Informative Trajectories for Dynamics System Identification

Marija Jegorova, Joshua Smith, Michael Mistry, Timothy M Hospedales

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Dynamic System Identification approaches usually heavily rely on evolutionary and gradient-based optimisation techniques to produce optimal excitation trajectories for determining the physical parameters of robot platforms. Current optimisation techniques tend to generate single trajectories. This is expensive, and intractable for longer trajectories, thus limiting their efficacy for system identification. We propose to tackle this issue by using multiple shorter cyclic trajectories, which can be generated in parallel, and subsequently combined together to achieve the same effect as a longer trajectory. Crucially, we show how to scale this approach even further by increasing the generation speed and quality of the dataset through the use of generative adversarial network (GAN) based architectures to produce large databases of valid and diverse excitation trajectories. To the best of our knowledge, this is the first robotics work to explore system identification with multiple cyclic trajectories and to develop GAN-based techniques for scaleably producing excitation trajectories that are diverse in both control parameter and inertial parameter spaces. We show that our approach dramatically accelerates trajectory optimisation, while simultaneously providing more accurate system identification than the conventional approach.
Original languageEnglish
Title of host publication2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
PublisherInstitute of Electrical and Electronics Engineers
Pages7109 - 7115
Number of pages7
ISBN (Electronic)978-1-7281-6212-6
ISBN (Print)978-1-7281-6213-3
DOIs
Publication statusPublished - 10 Feb 2021
Event2020 IEEE/RSJ International Conference on Intelligent Robots and Systems - Las Vegas, United States
Duration: 25 Oct 202029 Oct 2020
https://www.iros2020.org/index.html

Publication series

Name
PublisherIEEE
ISSN (Print)2153-0858
ISSN (Electronic)2153-0866

Conference

Conference2020 IEEE/RSJ International Conference on Intelligent Robots and Systems
Abbreviated titleIROS 2020
Country/TerritoryUnited States
CityLas Vegas
Period25/10/2029/10/20
Internet address

Fingerprint

Dive into the research topics of 'Adversarial Generation of Informative Trajectories for Dynamics System Identification'. Together they form a unique fingerprint.

Cite this