Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Discovery Grants Program - Individual

Dalhousie University

$46,000.00

Underwater Navigation with Anomalous Bathymetric Landmark Identification and Evaluation

FY 2024-25

Summary
Underwater navigation and localization is used by autonomous underwater vehicles to find objects on the seabed (e.g.., mines, sunken wrecks, downed aircraft).  Underwater is a difficult environment to operate, sense, and localize in.  The latter is especially true since underwater robots cannot access the Global Position System for position, navigation and timing.   A method that has been emerging over the last decade is to assist navigation systems is to use underwater environment features like bathymetry (underwater topography) and gravitational and magnetic fields. Given the underwater environment is harsh and the sensors are limited, the challenge is to identify environment features that are distinctive enough that they are navigation grade.   The research here attempts to find a way to identify then evaluate how distinctive the detected environmental features are.  Traditional methods are used and novel methods are proposed and pursued.  Machine learning will be applied to labelled bathymetric measurements to see if it is possible to obtain an classifier that quantitatively describes how distinctive environment features are. As well, saliency detection models will be created for bathymetry and gravitational and magnetic fields. Finally, these capabilities will be deployed on autonomous underwater vehicles for in-water verification. The desired outcome is a method to evaluate whether environment features are distinctive enough to be landmarks and if so, how distinctive are they.  The outcome of this work is extended ranges that underwater navigation and localization can be performed over with acceptable accuracy.  The best use case for the methods developed is to autonomously map the bathymetry under-ice in the Canadian Arctic as only 20% is mapped.  Mapping the underwater / under-ice portions of the Arctic is a goal for Canada.  The techniques developed will also contribute to the commercial sector for offshore wind farms and oil rigs.  The methodologies will benefit Canada's ocean sector on multiple fronts.
Program
Discovery Grants Program - Individual
Location
Nova Scotia, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
RGPIN-2024-06577
Name nom
Seto, Mae
Department département
Mechanical Engineering
Organization id
79
Institution établissement
Dalhousie University
Province en
Nova Scotia
Province fr
Nouvelle-Écosse
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2024
Award amount
46000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1512
Committee name en
Mechanical Engineering
Committee name fr
Génie mécanique
Area of application code
1002
Area of application group en
Northern development
Area of application group fr
Développement du nord
Area of application en
Environment
Area of application fr
Environnement
Research subject code
2100
Research subject group en
Mechanical engineering
Research subject group fr
Génie mécanique
Research subject en
Mechanical engineering
Research subject fr
Génie mécanique
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Underwater Navigation with Anomalous Bathymetric Landmark Identification and Evaluation
Keywords
underwater navigation; localization; underwater mapping; bathymetry; slam; simultaneous localization and mapping; marine robotics; underwater surveys
Application summary
Underwater navigation and localization is used by autonomous underwater vehicles to find objects on the seabed (e.g.., mines, sunken wrecks, downed aircraft).  Underwater is a difficult environment to operate, sense, and localize in.  The latter is especially true since underwater robots cannot access the Global Position System for position, navigation and timing.   A method that has been emerging over the last decade is to assist navigation systems is to use underwater environment features like bathymetry (underwater topography) and gravitational and magnetic fields. Given the underwater environment is harsh and the sensors are limited, the challenge is to identify environment features that are distinctive enough that they are navigation grade.   The research here attempts to find a way to identify then evaluate how distinctive the detected environmental features are.  Traditional methods are used and novel methods are proposed and pursued.  Machine learning will be applied to labelled bathymetric measurements to see if it is possible to obtain an classifier that quantitatively describes how distinctive environment features are. As well, saliency detection models will be created for bathymetry and gravitational and magnetic fields. Finally, these capabilities will be deployed on autonomous underwater vehicles for in-water verification. The desired outcome is a method to evaluate whether environment features are distinctive enough to be landmarks and if so, how distinctive are they.  The outcome of this work is extended ranges that underwater navigation and localization can be performed over with acceptable accuracy.  The best use case for the methods developed is to autonomously map the bathymetry under-ice in the Canadian Arctic as only 20% is mapped.  Mapping the underwater / under-ice portions of the Arctic is a goal for Canada.  The techniques developed will also contribute to the commercial sector for offshore wind farms and oil rigs.  The methodologies will benefit Canada's ocean sector on multiple fronts.