Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Discovery Grants Program - Individual

University of Waterloo

$38,000.00

Methodologies and Algorithms for Robust Autonomous Vehicles

FY 2024-25

Summary
Thousands of human lives are lost in road accidents every year. The number of fatalities, serious injuries, and injuries in Canada in 2020 were 1745, 7868, and about 102 thousand, respectively. In addition, there is a driver shortage in the trucking industry. Therefore, Autonomous Vehicles (AV) are drawing considerable attention from automakers, transportation industry, and governments. The "brain" of an AV, called an Autonomous Driving System (ADS), operates in three phases: sensing, processing, and action. In sensing, AVs monitor the driving environment (DE) using a variety of onboard sensors. Data collected by the sensors are fed to an onboard processing system which recommends the appropriate actions. Finally, the recommended actions, namely, acceleration, braking, lane changing, and overtaking are executed by the AV. Several challenges need to be addressed before AV technologies are trusted by drivers and riders: unequivocal detection of objects, safety, traffic efficiency, dynamicity of DEs, hacking, legal, and ethical. For AVs to gain public trust, their posthuman ability must be robust in terms of safety, performance, and availability. Through the proposed research program, we will pursue the following objectives: (i) design methodologies, algorithms, techniques, and tools (MATTs) for accurate and fast detection of objects, namely, roads, lanes, vehicles, pedestrians, traffic signs, and obstacles, in real-time in dense and sparse DEs; (ii) design MATTs for continuous evaluation of the performance of AVs; (iii) design MATTs for prognostics and health management of AVs for preventive maintenance; and (iv) integrate drivers' preferences with the decision making process of ADS. Our methodology includes a multi-dimensional approach to environment sensing and data processing. For fast and accurate sensing, we will use roadside and aerial sensors and store attributes of roads in the cloud. For fast and accurate processing, we will: (i) adopt a human-like approach in the design of object detection, instead of pure computer vision-based techniques; (ii) use federated machine learning in cooperative driving; and (iii) design digital twins of ADS. The MATTs developed in this research program will find applications in the design of robust AVs to reduce crashes, congestion, energy consumption, and pollution. Seven graduate students and five undergraduates will be trained in the composite field of intelligent transportation systems (ITS), federated machine learning, and digital twins. Highly qualified software engineers with those and associated skills are in demand in Canada. Canadian companies in the domain of ITS can benefit from this research program by designing services and products for safer and cheaper transportation of goods and people.
Program
Discovery Grants Program - Individual
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
RGPIN-2023-04328
Name nom
Naik, Kshirasagar
Department département
Electrical and Computer Engineering
Organization id
33
Institution établissement
University of Waterloo
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2023
Award amount
38000
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
1510
Committee name en
Electrical and Computer Engineering
Committee name fr
Génie électrique et informatique
Area of application code
700
Area of application group en
Transportation systems and services
Area of application group fr
Services et systèmes de transport
Area of application en
Transportation systems and services
Area of application fr
Services et systèmes de transport
Research subject code
2709
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Other computing methods
Research subject fr
Autres méthodes informatiques
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
Methodologies and Algorithms for Robust Autonomous Vehicles
Keywords
intelligent transportation systems; robust autonomous vehicles; anomaly detection; safety, performance, and availability; machine learning; digital twins
Application summary
Thousands of human lives are lost in road accidents every year. The number of fatalities, serious injuries, and injuries in Canada in 2020 were 1745, 7868, and about 102 thousand, respectively. In addition, there is a driver shortage in the trucking industry. Therefore, Autonomous Vehicles (AV) are drawing considerable attention from automakers, transportation industry, and governments. The "brain" of an AV, called an Autonomous Driving System (ADS), operates in three phases: sensing, processing, and action. In sensing, AVs monitor the driving environment (DE) using a variety of onboard sensors. Data collected by the sensors are fed to an onboard processing system which recommends the appropriate actions. Finally, the recommended actions, namely, acceleration, braking, lane changing, and overtaking are executed by the AV. Several challenges need to be addressed before AV technologies are trusted by drivers and riders: unequivocal detection of objects, safety, traffic efficiency, dynamicity of DEs, hacking, legal, and ethical. For AVs to gain public trust, their posthuman ability must be robust in terms of safety, performance, and availability. Through the proposed research program, we will pursue the following objectives: (i) design methodologies, algorithms, techniques, and tools (MATTs) for accurate and fast detection of objects, namely, roads, lanes, vehicles, pedestrians, traffic signs, and obstacles, in real-time in dense and sparse DEs; (ii) design MATTs for continuous evaluation of the performance of AVs; (iii) design MATTs for prognostics and health management of AVs for preventive maintenance; and (iv) integrate drivers' preferences with the decision making process of ADS. Our methodology includes a multi-dimensional approach to environment sensing and data processing. For fast and accurate sensing, we will use roadside and aerial sensors and store attributes of roads in the cloud. For fast and accurate processing, we will: (i) adopt a human-like approach in the design of object detection, instead of pure computer vision-based techniques; (ii) use federated machine learning in cooperative driving; and (iii) design digital twins of ADS. The MATTs developed in this research program will find applications in the design of robust AVs to reduce crashes, congestion, energy consumption, and pollution. Seven graduate students and five undergraduates will be trained in the composite field of intelligent transportation systems (ITS), federated machine learning, and digital twins. Highly qualified software engineers with those and associated skills are in demand in Canada. Canadian companies in the domain of ITS can benefit from this research program by designing services and products for safer and cheaper transportation of goods and people.