Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Discovery Grants Program - Individual

University of Victoria

$50,000.00

Uncertainty Management Framework for Learning-based Intelligent Robotics

EF 2023-24

Résumé
Intelligent robotics is the realization of artificial intelligence in industrial applications that have impacted our quality of life and fueled significant economic growth by changing the state of practice in many sectors over the past decade. For example, intelligent industrial robots enable advanced manufacturing improving quality and efficiency of production, automated and autonomous vehicles are making roads safer and transportation more efficient, autonomous construction equipment improve safety and efficiency in mining, and agricultural robots are making a huge impact on crop yield and quality. Moreover, research on intelligent robotics has advanced autonomous processes which are the cornerstone of many innovations in the hi-tech, consumer product, retail, and health care sectors. Artificial intelligence (AI) and more recently deep networks for machine learning (ML) have introduced a modeling paradigm for intelligent robotics using data and heuristics. In turn, this has offered solutions for complex autonomous processes namely perception, planning and control whereas traditional models were inadequate or unavailable. Despite these advantages, the applicability of ML in practical use cases and real-world environments is challenged by the uncertainties that are typically associated with noisy observations as well as the absence, incompleteness, and vagueness of information in the datasets used for model training. This Discovery Grant describes the applicant's proposed research program that aims to introduce an uncertainty management framework for autonomous processes of intelligent robots with emphasis on robot perception and robot planning. The framework will encapsulate the uncertainty modelling methodologies that rely on heuristics, stochastics, and closed-form formulations. After managing uncertainties, the ML-based methods will present practical solutions for complex autonomous scenarios in real-world environments, which are deemed to be intractable by traditional methods. The framework will provide free online access to datasets and algorithms developed in this program, subsequently creating a quick and permanent forum for sharing knowledge and exchanging ideas between his HQP and the robotics research community, in addition to the HQP dissertations and publications. In this way, the proposed research program will not only accelerate and expand the scientific and technological advancement of intelligent robots for industry but also enhance the accessibility of the research outcome, diversify his HQP training within and outside his laboratory, and create a more inclusive and reputable research environment for his HQP.
Programme
Discovery Grants Program - Individual
Emplacement
British Columbia, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
RGPIN-2023-05408
Name nom
Najjaran, Homayoun
Department département
Mechanical Engineering - Mechanical Engineering
Organization id
7
Institution établissement
University of Victoria
Province en
British Columbia
Province fr
Colombie-Britannique
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2023
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
500
Area of application group en
Manufacturing processes and products
Area of application group fr
Procédés et produits industriels
Area of application en
Manufacturing processes and products
Area of application fr
Procédés et produits industriels
Research subject code
2600
Research subject group en
Robotics
Research subject group fr
Robotics
Research subject en
Robotique
Research subject fr
Robotique
Application title
Uncertainty Management Framework for Learning-based Intelligent Robotics
Keyword
Adaptive Robots; Artificial Intelligence; Autonomous Systems; Intelligent Robots; Machine Learning; Robotics; Robot Perception; Robot Planning; Uncertainty
Application summary
Intelligent robotics is the realization of artificial intelligence in industrial applications that have impacted our quality of life and fueled significant economic growth by changing the state of practice in many sectors over the past decade. For example, intelligent industrial robots enable advanced manufacturing improving quality and efficiency of production, automated and autonomous vehicles are making roads safer and transportation more efficient, autonomous construction equipment improve safety and efficiency in mining, and agricultural robots are making a huge impact on crop yield and quality. Moreover, research on intelligent robotics has advanced autonomous processes which are the cornerstone of many innovations in the hi-tech, consumer product, retail, and health care sectors. Artificial intelligence (AI) and more recently deep networks for machine learning (ML) have introduced a modeling paradigm for intelligent robotics using data and heuristics. In turn, this has offered solutions for complex autonomous processes namely perception, planning and control whereas traditional models were inadequate or unavailable. Despite these advantages, the applicability of ML in practical use cases and real-world environments is challenged by the uncertainties that are typically associated with noisy observations as well as the absence, incompleteness, and vagueness of information in the datasets used for model training. This Discovery Grant describes the applicant's proposed research program that aims to introduce an uncertainty management framework for autonomous processes of intelligent robots with emphasis on robot perception and robot planning. The framework will encapsulate the uncertainty modelling methodologies that rely on heuristics, stochastics, and closed-form formulations. After managing uncertainties, the ML-based methods will present practical solutions for complex autonomous scenarios in real-world environments, which are deemed to be intractable by traditional methods. The framework will provide free online access to datasets and algorithms developed in this program, subsequently creating a quick and permanent forum for sharing knowledge and exchanging ideas between his HQP and the robotics research community, in addition to the HQP dissertations and publications. In this way, the proposed research program will not only accelerate and expand the scientific and technological advancement of intelligent robots for industry but also enhance the accessibility of the research outcome, diversify his HQP training within and outside his laboratory, and create a more inclusive and reputable research environment for his HQP.