Grant: Discovery Grants Program - Individual
Queen's University
$31,000.00
Toward Resilient Multi-Robot Collaboration in Emergencies
EF 2023-24
Résumé
Disasters in Canada are increasing in frequency and severity across the country. Over a ten-year period, these disasters have resulted in tens of billions of dollars in damages and displaced hundreds of thousands of people. As a response, Public Safety Canada has proposed an "Emergency Management Strategy for Canada: Toward a Resilient 2030." In this proposed research program, we will develop capabilities for resilient multi-robot teams to enhance emergency response capacity and co-ordination, which is one of the five priority areas outlined by Public Safety Canada. Multi-robot collaboration can be leveraged to substantially improve public safety by using efficient and intelligent navigation to provide critical feedback in disasters and search-and-rescue scenarios, facilitate time-critical extraction, and enable delivery of life-saving tools. However, developing resilient multi-robot collaboration is both challenging and necessary to prevent catastrophic down-time. In this research program, we will advance resilient multi-robot navigation by efficiently adapting to robot failures and sensor disruptions. We propose leveraging robot teams comprising of aerial and ground-based robots equipped with visual and/or thermal cameras to operate in challenging densely populated and potentially low light (e.g., because of fog, dust, rain, and smoke) environments. These are frequent conditions in emergency response events. Specifically, this program supports three streams. In Stream 1, we will address real-time planning for aerial and ground-based robots in densely populated environments where dynamic uncertainty and robot failures are likely. In Stream 2, we will explore multi-robot perception using visual and thermal cameras to estimate more accurate task-specific information (e.g., depth estimation and semantic segmentation) despite image noise, occlusions, and failures. This information can then be leveraged by emergency response teams. In Stream 3, we will integrate Stream 1 and 2 and develop a framework to optimize resilient collaboration between aerial and ground-based robots equipped with visual and/or thermal cameras. This program will support the training of eight highly qualified personnel (HQP) (2 PhD, 2 master's and 4 undergraduate students) over five years. The work proposed in the program will require simulation, experimentation, and field trials. HQP will learn to work with various Application Programming Interfaces (APIs), use Robot Operating System (ROS) and implement algorithms for robotic platforms and camera sensors. They will contribute to novel research on multi-robot collaboration which they will present at international robotics conferences. They will develop engaging demos and videos showcasing our developed algorithms to the public. They will co-organize and participate in field trials to test the resiliency of the developed algorithms in challenging real-world environments.
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-2023-04526
Name nom
Greeff, Melissa
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
31000
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
1507
Committee name en
Computer Science
Committee name fr
Sciences informatiques
Area of application code
1206
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Engineering
Area of application fr
Génie
Research subject code
9999
Research subject group en
Not available
Research subject group fr
Not available
Research subject en
Non disponible
Research subject fr
Non disponible
Application title
Toward Resilient Multi-Robot Collaboration in Emergencies
Keyword
Aerial Systems Applications; Differential Flatness; Graph Neural Networks; Multi-Robot Path Planning; Multi-Robot Systems; Robotics
Application summary
Disasters in Canada are increasing in frequency and severity across the country. Over a ten-year period, these disasters have resulted in tens of billions of dollars in damages and displaced hundreds of thousands of people. As a response, Public Safety Canada has proposed an "Emergency Management Strategy for Canada: Toward a Resilient 2030." In this proposed research program, we will develop capabilities for resilient multi-robot teams to enhance emergency response capacity and co-ordination, which is one of the five priority areas outlined by Public Safety Canada. Multi-robot collaboration can be leveraged to substantially improve public safety by using efficient and intelligent navigation to provide critical feedback in disasters and search-and-rescue scenarios, facilitate time-critical extraction, and enable delivery of life-saving tools. However, developing resilient multi-robot collaboration is both challenging and necessary to prevent catastrophic down-time. In this research program, we will advance resilient multi-robot navigation by efficiently adapting to robot failures and sensor disruptions. We propose leveraging robot teams comprising of aerial and ground-based robots equipped with visual and/or thermal cameras to operate in challenging densely populated and potentially low light (e.g., because of fog, dust, rain, and smoke) environments. These are frequent conditions in emergency response events. Specifically, this program supports three streams. In Stream 1, we will address real-time planning for aerial and ground-based robots in densely populated environments where dynamic uncertainty and robot failures are likely. In Stream 2, we will explore multi-robot perception using visual and thermal cameras to estimate more accurate task-specific information (e.g., depth estimation and semantic segmentation) despite image noise, occlusions, and failures. This information can then be leveraged by emergency response teams. In Stream 3, we will integrate Stream 1 and 2 and develop a framework to optimize resilient collaboration between aerial and ground-based robots equipped with visual and/or thermal cameras. This program will support the training of eight highly qualified personnel (HQP) (2 PhD, 2 master's and 4 undergraduate students) over five years. The work proposed in the program will require simulation, experimentation, and field trials. HQP will learn to work with various Application Programming Interfaces (APIs), use Robot Operating System (ROS) and implement algorithms for robotic platforms and camera sensors. They will contribute to novel research on multi-robot collaboration which they will present at international robotics conferences. They will develop engaging demos and videos showcasing our developed algorithms to the public. They will co-organize and participate in field trials to test the resiliency of the developed algorithms in challenging real-world environments.