Grant: Discovery Grants Program - Individual
McGill University
$50,000.00
Enhanced Robustness and Performance of Navigation Solutions for Robotic Vehicles
FY 2024-25
Summary
The long-term research objective of this proposal is to enhance the robustness and performance of autonomous vehicle (AV) operation. Canada has flourishing automotive, aerospace, power generation, agriculture, forestry, and mining industries that can all benefit from more robust, reliable, performant AV operation. Superior AV operation, individually and in teams, will impact the lives of Canadians in rural, urban, and Northern regions through improved industrial efficiencies and economic competitiveness, safeguarding Canada's wildlife and natural resources, and enhancing the comfort, convenience, and safety of ground and air transport. The particular focus of this proposal is enhancing the reliability and performance of AV navigation algorithms when global positioning system measurements are unavailable or unreliable, such as indoors, underground, underwater, and in dense urban areas. Camera, LiDAR, and other time-of-flight sensors, are often used in concert with inertial measurement unit (IMU) data for AV navigation. Existing AV navigation methods work well in ideal situations but performance degrades dramatically in the presence of outliers, non-Gaussian probability distribution functions (PDFs), and when IMU data must be relied upon for long durations, a process called dead-reckoning. Thus, the short-term objectives of this proposal are improving robustness and performance of 1) outlier rejection, 2) navigation in the presence of non-Gaussian PDFs, and 3) dead-reckoning. These short-term objectives will be realized using a blend of rigorous mathematics, statistics, and machine learning tools. Although improved AV operation motivates this research, this work is more broadly applicable to any scientific, engineering, or economic problem where outliers, unexpected non-Gaussian distributions, and corrections to time-series data, are important. Two PhD students, six MSc students, and five undergraduate students will be intimately involved in both theoretical and experimental research, arming them with highly sought after skills.
Program
Discovery Grants Program - Individual
Recipient
Location
Quebec, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
RGPIN-2023-03621
Name nom
Forbes, James
Department département
Mechanical Engineering
Organization id
61
Institution établissement
McGill University
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2023
Award amount
50000
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
703
Area of application group en
Transportation systems and services
Area of application group fr
Services et systèmes de transport
Area of application en
Aerospace
Area of application fr
Aérospatial
Research subject code
2601
Research subject group en
Robotics
Research subject group fr
Robotique
Research subject en
Robotic control
Research subject fr
Systèmes de commande
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
Enhanced Robustness and Performance of Navigation Solutions for Robotic Vehicles
Keywords
navigation; state estimation; robotic systems; outlier rejection; non-gaussian distributions; inference; machine learning
Application summary
The long-term research objective of this proposal is to enhance the robustness and performance of autonomous vehicle (AV) operation. Canada has flourishing automotive, aerospace, power generation, agriculture, forestry, and mining industries that can all benefit from more robust, reliable, performant AV operation. Superior AV operation, individually and in teams, will impact the lives of Canadians in rural, urban, and Northern regions through improved industrial efficiencies and economic competitiveness, safeguarding Canada's wildlife and natural resources, and enhancing the comfort, convenience, and safety of ground and air transport. The particular focus of this proposal is enhancing the reliability and performance of AV navigation algorithms when global positioning system measurements are unavailable or unreliable, such as indoors, underground, underwater, and in dense urban areas. Camera, LiDAR, and other time-of-flight sensors, are often used in concert with inertial measurement unit (IMU) data for AV navigation. Existing AV navigation methods work well in ideal situations but performance degrades dramatically in the presence of outliers, non-Gaussian probability distribution functions (PDFs), and when IMU data must be relied upon for long durations, a process called dead-reckoning. Thus, the short-term objectives of this proposal are improving robustness and performance of 1) outlier rejection, 2) navigation in the presence of non-Gaussian PDFs, and 3) dead-reckoning. These short-term objectives will be realized using a blend of rigorous mathematics, statistics, and machine learning tools. Although improved AV operation motivates this research, this work is more broadly applicable to any scientific, engineering, or economic problem where outliers, unexpected non-Gaussian distributions, and corrections to time-series data, are important. Two PhD students, six MSc students, and five undergraduate students will be intimately involved in both theoretical and experimental research, arming them with highly sought after skills.