Learning from demonstration in the wild

Conference Paper (2019)
Author(s)

Feryal Behbahani (Latent Logic)

Kyriacos Shiarlis (Latent Logic)

Xi Chen (Latent Logic)

Vitaly Kurin (University of Oxford, Latent Logic)

Sudhanshu Kasewa (Latent Logic, University of Oxford)

Ciprian Stirbu (University of Oxford, Latent Logic)

Joao Gomes (Latent Logic)

Supratik Paul (Latent Logic, University of Oxford)

Frans A. Oliehoek (TU Delft - Interactive Intelligence, Latent Logic)

undefined More Authors (External organisation)

Research Group
Interactive Intelligence
DOI related publication
https://doi.org/10.1109/ICRA.2019.8794412
More Info
expand_more
Publication Year
2019
Language
English
Research Group
Interactive Intelligence
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.
Article number
8794412
Pages (from-to)
775-781
ISBN (print)
978-1-5386-8176-3
ISBN (electronic)
978-1-5386-6027-0
Event
2019 International Conference on Robotics and Automation, ICRA 2019 (2019-05-20 - 2019-05-24), Montreal, Canada
Downloads counter
375
Collections
Institutional Repository
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

Learning from demonstration (LfD) is useful in settings where hand-coding behaviour or a reward function is impractical. It has succeeded in a wide range of problems but typically relies on manually generated demonstrations or specially deployed sensors and has not generally been able to leverage the copious demonstrations available in the wild: those that capture behaviours that were occurring anyway using sensors that were already deployed for another purpose, e.g., traffic camera footage capturing demonstrations of natural behaviour of vehicles, cyclists, and pedestrians. We propose video to behaviour (ViBe), a new approach to learn models of behaviour from unlabelled raw video data of a traffic scene collected from a single, monocular, initially uncalibrated camera with ordinary resolution. Our approach calibrates the camera, detects relevant objects, tracks them through time, and uses the resulting trajectories to perform LfD, yielding models of naturalistic behaviour. We apply ViBe to raw videos of a traffic intersection and show that it can learn purely from videos, without additional expert knowledge.

Files

08794412.pdf
(pdf | 4.1 Mb)
- Embargo expired in 12-02-2020
License info not available