Grant: Alliance Grants
The University of Western Ontario
$40,000.00
Computer vision system for construction of lunar structures using in situ materials
FY 2024-25
Summary
There has been renewed interest this decade in a return to, and permanent settlement on, the moon. One necessary technology to enabling a long-term lunar presence is the ability to exploit lunar resources, rather than needing to transport everything from Earth. Artificial intelligence and automation are a key component of lunar resource exploitation, since the hazardous environment of the moon means that human presence in the open should be minimized. This project fits into a larger initiative, led by the industrial partner, to develop a fully automated construction capability on the moon. Our long-term vision for the solution is to develop an autonomous robotic system to build lunar structures using sandbags filled with lunar regolith. In this project, we focus on the problem of manipulating and grasping lunar sandbags. We have identified three key milestones as necessary building blocks towards the larger goal. First we will develop the capability to model the behavior of lunar sandbags that takes into account the unusual physics caused by vacuum and low gravity. Next we will develop an AI-based system using a simulated training data set to train an automatic system capable of recognizing and locating a sandbag, including the problem of identifying one sandbag out of many. Finally, we will develop a strategy for grasping and manipulating the sandbags.
Program
Alliance Grants
Recipient
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
592529-2023
Name nom
McIsaac, Kenneth KA
Department département
Electrical and Computer Engineering
Organization id
36
Institution établissement
The University of Western Ontario
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
40000
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
1204
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Space and astronomy
Area of application fr
Sciences spatiales et astronomie
Research subject code
2603
Research subject group en
Robotics
Research subject group fr
Robotique
Research subject en
Computer vision
Research subject fr
Vision artificielle
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
Computer vision system for construction of lunar structures using in situ materials
Keywords
computer vision; deep learning; grasping; lunar resources; robotic manipulation
Application summary
There has been renewed interest this decade in a return to, and permanent settlement on, the moon. One necessary technology to enabling a long-term lunar presence is the ability to exploit lunar resources, rather than needing to transport everything from Earth. Artificial intelligence and automation are a key component of lunar resource exploitation, since the hazardous environment of the moon means that human presence in the open should be minimized. This project fits into a larger initiative, led by the industrial partner, to develop a fully automated construction capability on the moon. Our long-term vision for the solution is to develop an autonomous robotic system to build lunar structures using sandbags filled with lunar regolith. In this project, we focus on the problem of manipulating and grasping lunar sandbags. We have identified three key milestones as necessary building blocks towards the larger goal. First we will develop the capability to model the behavior of lunar sandbags that takes into account the unusual physics caused by vacuum and low gravity. Next we will develop an AI-based system using a simulated training data set to train an automatic system capable of recognizing and locating a sandbag, including the problem of identifying one sandbag out of many. Finally, we will develop a strategy for grasping and manipulating the sandbags.