Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Alliance Grants

Queen's University

$30,000.00

Part Detection and Localization for Flexible Automation

FY 2023-24

Summary
The project objective is to integrate a set of Machine Learning-based 3D computer vision methods, collectively called RCVPose, into Bluewrist's commercial FlexiPick software. Bluewrist provides industrial automation solutions that combine 3D machine vision, automated inspection and robotic guidance technologies. They develop custom software solutions that include 3D machine vision routines for the detection and localization of parts in an automated assembly cell. To date, their software has been based on classical machine vision methods. The problem/challenge is to integrate modern Machine Learning-based methods into their product offering. RCVPose was developed in a research environment and currently exists as prototype software. While the method has been demonstrated as highly effective, modification and translation of the code base will be required, as well as the development of a novel sim2real training module, in order to successfully integrate the method into Bluewrist's code base. The deliverable/outcome of the project will be a Machine Learning-based 3D part detection and localization module fully integrated into FlexiPick, and ready for beta testing by Bluewrist's customers. The inclusion of modern Machine Learning-based vision methods will allow Bluewrist's systems to be deployed more flexibly and with higher performance, on a larger and more diverse set of applications, thereby increasing their market reach.
Program
Alliance Grants
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
581399-2023
Name nom
Greenspan, Michael MA
Department département
Electrical and Computer Engineering
Organization id
29
Institution établissement
Queen's University
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2023
Competition year année de concours
2023
Award amount
30000
Program id
ALLRP
Program name en
Alliance Grants
Program name fr
Subventions Alliance
Group en
RESEARCH PARTNERSHIPS
Group fr
PARTENARIATS DE RECHERCHE
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
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
2605
Research subject group en
Robotics
Research subject group fr
Pattern analysis and machine intelligence
Research subject en
Robotique
Research subject fr
Analyse de formes et intelligence artificielle
Application title
Part Detection and Localization for Flexible Automation
Keyword
3D sensing; computer vision; domain transfer; machine learning; neural network; object detection; pose estimation; robotic grasping; sime2real learning; simulation
Application summary
The project objective is to integrate a set of Machine Learning-based 3D computer vision methods, collectively called RCVPose, into Bluewrist's commercial FlexiPick software. Bluewrist provides industrial automation solutions that combine 3D machine vision, automated inspection and robotic guidance technologies. They develop custom software solutions that include 3D machine vision routines for the detection and localization of parts in an automated assembly cell. To date, their software has been based on classical machine vision methods. The problem/challenge is to integrate modern Machine Learning-based methods into their product offering. RCVPose was developed in a research environment and currently exists as prototype software. While the method has been demonstrated as highly effective, modification and translation of the code base will be required, as well as the development of a novel sim2real training module, in order to successfully integrate the method into Bluewrist's code base. The deliverable/outcome of the project will be a Machine Learning-based 3D part detection and localization module fully integrated into FlexiPick, and ready for beta testing by Bluewrist's customers. The inclusion of modern Machine Learning-based vision methods will allow Bluewrist's systems to be deployed more flexibly and with higher performance, on a larger and more diverse set of applications, thereby increasing their market reach.