Feedback
Menu

Home / Search / Record

Memorial University of Newfoundland

Autonomous Fleet Ice Management via Reinforcement Learning

A flag is a question, not a finding. It is not evidence that anything wrong happened.

CAD 105,681.00

Reported federal agreement value. An agreement can cover several years; this is not the amount paid out.

Selected because the publisher reports recipient province NL; NL Ledger has not established the work, benefit or jurisdiction from this record; source fields are available below.

This is the whole reported commitment or notice value, not the amount paid or an NL allocation.

Agreement start
Jan. 1, 2022
Program
Collaborative Science, Technology and Innovation Program - Collaborative R&D Initiatives
Record type
Federal grant or contribution

Receipt

agreement 172-2021-2022-Q3-983412, amendment 0

Open the source

Source location evidence

Location review incomplete.

Reported address: country: CA; province: NL; city: St. John's|St. John's; postal code: A1C 5S7.

How counted: latest of 1 rows (department reports running totals). Start: 2022-01-01; end: 2026-03-31; reported: not stated. Amount: published value.

    Full source fields
    _id
    493677332
    ref_number
    172-2021-2022-Q3-983412
    amendment_number
    0
    amendment_date
    agreement_type
    G
    recipient_type
    S
    recipient_business_number
    107690273
    recipient_legal_name
    Memorial University of Newfoundland
    recipient_operating_name
    research_organization_name
    recipient_country
    CA
    recipient_province
    NL
    recipient_city
    St. John's|St. John's
    recipient_postal_code
    A1C 5S7
    federal_riding_name_en
    St. John's East
    federal_riding_name_fr
    St. John's-Est
    federal_riding_number
    10006
    prog_name_en
    Collaborative Science, Technology and Innovation Program - Collaborative R&D Initiatives
    prog_name_fr
    Programme de collaboration en science, en technologie et en innovation - Initiatives de collaboration en R-D
    prog_purpose_en
    Collaborate on multiparty research and development programs to catalyze transformative, high-risk, high-reward research with the potential for game-changing scientific discoveries and technological breakthroughs in priority areas.
    prog_purpose_fr
    Collaborer à des programmes multipartites de recherche-développement dans le but de profiter de la synergie entre la recherche transformatrice à haut risque et à haut rendement et le potentiel de découvertes scientifiques et de percées technologiques révolutionnaires dans des secteurs d’intervention prioritaires.
    agreement_title_en
    Autonomous Fleet Ice Management via Reinforcement Learning
    agreement_title_fr
    Gestion autonome de la flotte de glace au moyen de l’apprentissage par renforcement
    agreement_number
    983412
    agreement_value
    105681
    foreign_currency_type
    foreign_currency_value
    agreement_start_date
    2022-01-01
    agreement_end_date
    2026-03-31
    coverage
    description_en
    The purpose of this project is to explore the idea of an autonomous fleet of vessels which increase the availability of a channel of interest by pushing ice out of the way. The project involves the hiring of one PhD student. A reinforcement learning strategy for the vessel control algorithm to capture the complex interactions with ice on water is proposed. The model test basins at NRC are proposed to be used to collect data to enhance a simulation for algorithm development that will also be demonstrated with a model test. An existing ice simulation technology developed at NRC-OCRE in combination with model-free reinforcement learning will be used to arrive at a design for the vessel controllers that maint navigability.
    description_fr
    Dans le cadre de ce projet, on explorera l’idée d’une flotte autonome de navires qui augmentent la disponibilité d’un canal d’intérêt en dégageant la glace qui s’y trouve. Le projet implique l’embauche d’un doctorant. Une stratégie d’apprentissage par renforcement pour l’algorithme de contrôle des navires afin de capturer les interactions complexes avec la glace sur l’eau est proposée. Il est proposé d’utiliser les bassins d’essai de modèles du CNRC pour recueillir des données en vue d’améliorer une simulation pour créer un algorithme qui sera également soumis à un essai de modèle. Une technologie actuelle de simulation de glace développée au Centre de recherche en génie océanique, côtier et fluvial du CNRC, combinée à l’apprentissage par renforcement sans modèle, sera utilisée pour obtenir une conception de contrôleurs de navires qui maintiennent la navigabilité.
    naics_identifier
    541710
    expected_results_en
    In the short term, anticipated outcomes will be strengthened collaborations across industry, academia, and government to support research excellence. In the medium term, anticipated outcomes will be the development of new and potentially disruptive technologies with collaborators. In the long term, find collaborative solutions to public policy challenges and create stronger innovation systems.
    expected_results_fr
    À court terme, les résultats prévus seront des collaborations renforcées entre l'industrie, le milieu universitaire et le gouvernement pour soutenir l'excellence en recherche. À moyen terme, les résultats attendus seront le développement de nouvelles technologies potentiellement perturbatrices avec des collaborateurs. À long terme, trouver des solutions collaboratives aux défis des politiques publiques et créer des systèmes d'innovation plus solides.
    additional_information_en
    additional_information_fr
    owner_org
    nrc-cnrc
    owner_org_title
    National Research Council Canada | Conseil national de recherches Canada

    Spot an error? Say so in the box below, or email corrections@nlledger.ca. What to send.

    Something missing, wrong or confusing?

    Say so here. No account is needed, and no email program. Every note is read.

    What people asked for, and what was done

    What kind of note is it? Optional

    The address of this page is sent with it, so there is no need to say where you were.

    Notes are read by the people who run the site. They are never shown on it. Privacy