Deep Network Uncertainty Maps for Indoor Navigation

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Abstract

Most mobile robots for indoor use rely on 2D laser scanners for localization, mapping and navigation. These sensors, however, cannot detect transparent surfaces or measure the full occupancy of complex objects such as tables. Deep Neural Networks have recently been proposed to overcome this limitation by learning to estimate object occupancy. These estimates are nevertheless subject to uncertainty, making the evaluation of their confidence an important issue for these measures to be useful for autonomous navigation and mapping. In this work we approach the problem from two sides. First we discuss uncertainty estimation in deep models, proposing a solution based on a fully convolutional neural network. The proposed architecture is not restricted by the assumption that the uncertainty follows a Gaussian model, as in the case of many popular solutions for deep model uncertainty estimation, such as Monte-Carlo Dropout. We present results showing that uncertainty over obstacle distances is actually better modeled with a Laplace distribution. Then, we propose a novel approach to build maps based on Deep Neural Network uncertainty models. In particular, we present an algorithm to build a map that includes information over obstacle distance estimates while taking into account the level of uncertainty in each estimate. We show how the constructed map can be used to increase global navigation safety by planning trajectories which avoid areas of high uncertainty, enabling higher autonomy for mobile robots in indoor settings.
Original languageEnglish
Title of host publicationProceedings of the 2019 IEEE-RAS International Conference on Humanoid Robots, Humanoids 2019
PublisherIEEE
Pages112-119
Number of pages8
ISBN (Electronic)978-1-5386-7630-1
DOIs
Publication statusPublished - 16 Mar 2020
MoE publication typeA4 Article in a conference publication
EventIEEE-RAS International Conference on Humanoid Robots - Hotel Hilton Toronto, Toronto, Canada
Duration: 15 Oct 201917 Oct 2019
http://humanoids2019.loria.fr/

Publication series

NameIEEE-RAS International Conference on Humanoid Robots
PublisherIEEE
ISSN (Print)2164-0572
ISSN (Electronic)2164-0580

Conference

ConferenceIEEE-RAS International Conference on Humanoid Robots
Abbreviated titleHumanoids
CountryCanada
CityToronto
Period15/10/201917/10/2019
Internet address

Fingerprint Dive into the research topics of 'Deep Network Uncertainty Maps for Indoor Navigation'. Together they form a unique fingerprint.

  • Projects

    ROSE: Robots and the Future of Welfare Services

    Lundell, J., Brander, T., Kyrki, V., Racca, M. & Verdoja, F.

    01/01/201831/12/2021

    Project: Academy of Finland: Strategic research funding

    Cite this

    Verdoja, F., Lundell, J., & Kyrki, V. (2020). Deep Network Uncertainty Maps for Indoor Navigation. In Proceedings of the 2019 IEEE-RAS International Conference on Humanoid Robots, Humanoids 2019 (pp. 112-119). (IEEE-RAS International Conference on Humanoid Robots). IEEE. https://doi.org/10.1109/Humanoids43949.2019.9035016