Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Discovery Grants Program - Individual

University of Guelph

$46,000.00

Robotic grasping and manipulation for application in uncertain and cluttered environments

EF 2024-25

Résumé
A recent report by the Federation of Robotics, an industry trade group, shows that industrial robot installations skyrocketed to a new record level of 517,385 units in 2021. This represented a growth rate of 31% over 2020. Beyond the traditional automotive and electronics industries, robots are now the backbone of the electronic commerce logistics hubs enabling the same-day shipping of items ordered early in the day. What is fuelling this significant expansion of robotics applications? There are several factors. The cost of labour is rising worldwide, particularly in areas where demographics negatively impact the labour market, like Europe and Japan. At the same time, the advancement of technology in terms of software and hardware is making robots cheaper and more capable. For example, all major robotics manufacturers now offer collaborative robots designed to allow close collaboration with human workers. The same trend is happening in machine vision and machine learning. The huge expansion in electronic commerce is now fuelling interest in warehouse robots that can save time and money and make fewer mistakes. The pandemic also accelerated the demand for automation in other sectors, like healthcare and agriculture, where the difficulty in recruiting foreign workers had a significant impact. However, several significant challenges still need to be addressed before robots can be fully integrated into uncertain, unstructured environments like hospitals and farms. A key challenge is grasping and manipulation. The general problem is difficult since objects come in different shapes, mass, surface friction, fragility, and functionality. These characteristics are only known in well-structured industrial environments. Compounding the problem is that obstacles may render one grasping configuration not reachable, and the overall task may also require other grasping configurations beyond what is obvious. Therefore, grasping is fundamentally a many-to-many mapping. Another challenge is how to acquire and encode grasping knowledge. The traditional hard-coded, top-down approach fails to react to new events or unforeseen environmental changes. Mastering grasping and manipulation skills will be a game-changer in the robotics field. This proposal addresses this challenge by proposing an integrated system that perceives objects under uncertainty, plans grasping configuration, executes the grasp and maintains its stability, and learns from the experience how to grasp other objects under other conditions, with a total focus on sensory feedback. The system will be tested in an experimental robotics cell that mimics a real industrial task. Five HQPs will gain expertise in robotics and AI, fields in high demand. This work will significantly impact many applications ranging from manufacturing to precision agriculture to personal robots.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
RGPIN-2024-05549
Name nom
Moussa, Medhat
Department département
School of Engineering
Organization id
24
Institution établissement
University of Guelph
Province en
Ontario
Province fr
Ontario
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
1510
Committee name en
Electrical and Computer Engineering
Committee name fr
Génie électrique et informatique
Area of application code
1200
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Advancement of knowledge
Area of application fr
Avancement des connaissances
Research subject code
2600
Research subject group en
Robotics
Research subject group fr
Robotique
Research subject en
Robotics
Research subject fr
Robotique
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
Robotic grasping and manipulation for application in uncertain and cluttered environments
Keywords
robotics; machine learning; grasping and manipulation
Application summary
A recent report by the Federation of Robotics, an industry trade group, shows that industrial robot installations skyrocketed to a new record level of 517,385 units in 2021. This represented a growth rate of 31% over 2020. Beyond the traditional automotive and electronics industries, robots are now the backbone of the electronic commerce logistics hubs enabling the same-day shipping of items ordered early in the day. What is fuelling this significant expansion of robotics applications? There are several factors. The cost of labour is rising worldwide, particularly in areas where demographics negatively impact the labour market, like Europe and Japan. At the same time, the advancement of technology in terms of software and hardware is making robots cheaper and more capable. For example, all major robotics manufacturers now offer collaborative robots designed to allow close collaboration with human workers. The same trend is happening in machine vision and machine learning. The huge expansion in electronic commerce is now fuelling interest in warehouse robots that can save time and money and make fewer mistakes. The pandemic also accelerated the demand for automation in other sectors, like healthcare and agriculture, where the difficulty in recruiting foreign workers had a significant impact. However, several significant challenges still need to be addressed before robots can be fully integrated into uncertain, unstructured environments like hospitals and farms. A key challenge is grasping and manipulation. The general problem is difficult since objects come in different shapes, mass, surface friction, fragility, and functionality. These characteristics are only known in well-structured industrial environments. Compounding the problem is that obstacles may render one grasping configuration not reachable, and the overall task may also require other grasping configurations beyond what is obvious. Therefore, grasping is fundamentally a many-to-many mapping. Another challenge is how to acquire and encode grasping knowledge. The traditional hard-coded, top-down approach fails to react to new events or unforeseen environmental changes. Mastering grasping and manipulation skills will be a game-changer in the robotics field. This proposal addresses this challenge by proposing an integrated system that perceives objects under uncertainty, plans grasping configuration, executes the grasp and maintains its stability, and learns from the experience how to grasp other objects under other conditions, with a total focus on sensory feedback. The system will be tested in an experimental robotics cell that mimics a real industrial task. Five HQPs will gain expertise in robotics and AI, fields in high demand. This work will significantly impact many applications ranging from manufacturing to precision agriculture to personal robots.