Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Discovery Grants Program - Individual

Queen's University

$42,000.00

Mobile-robot navigation, control, and mapping in spatiotemporal worlds

FY 2023-24

Summary
Mobile equipment capable of autonomous or semi-autonomous operations is of relevance in remote, harsh, uncertain and dynamic environments where human presence is either not possible, hindered in some way, or highly undesirable (e.g., due to safety considerations). Something that we have come to realize in recent years is that the spatiotemporal nature of the "worlds" in which autonomous mobile robots operate has a more significant impact on performance than is generally appreciated. Vehicle navigation, control, and mapping systems often ignore spatiotemporal effects and view such time-varying characteristics as disturbances to be rejected in real-time or through post-processing. For some applications, these assumptions may be satisfactory. For others, spatiotemporal dynamics clearly play an integral role and in some cases be the very thing that we are interested in mapping. This proposed research program aims to explore the application of recent theoretical advances in spatiotemporal modelling to the problems of mobile robot navigation, control, and mapping in challenging outdoor environments. Our research will commence with the use of suitably equipped mobile robots for the purposes of learning spatiotemporal field models from data acquired during traversals in space and time. Consider, for example, the problem of estimating wave action, coastal erosion, or temperature gradients by using sensors installed on an uncrewed marine surface vessel. In this case, spatial modelling alone is not sufficient and our research will aim to develop methods based on mobile sampling to model (e.g., by using Gaussian process regression or other machine learning-based techniques) the spatiotemporal evolution of such processes by using discrete samples collected in both space and time. In the secondary stream of this research program, we plan to employ our learned spatiotemporal mapping techniques as a means to provide feedback to vehicle control systems that could be used to improve navigation and vehicle control system performance in dynamic scenarios for real-world applications. Finally, as is typical of our group's past research and inherent strengths, technical developments in both of the proposed research streams will be deployed and tested by using real hardware in representative physical environments. Trained HQP (2 PhD, 2 MASc, 5 USRA) will be part of a multi-disciplinary robotics and artificial intelligence (AI) research centre at Queen's and an NSERC Strategic Network, granting them access to state-of-the-art research space and robots. These resources include multiple Clearpath Husky A200 mobile robots, large robotic Kubota vehicles, a new Maritime Robotics Otter uncrewed surface vessel (USV), as well as a host of sensors, both proprioceptive and exteroceptive. Thus, there is a very strong case that the proposed research is not only feasible and executable, but also has the potential to find tangible impacts for both Canadian industry and society.
Program
Discovery Grants Program - Individual
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
RGPIN-2023-03404
Name nom
Marshall, Joshua
Department département
Mining Engineering - Mining 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
42000
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
204
Area of application group en
Natural resources (economic aspects)
Area of application group fr
Ressources naturelles (aspects économiques)
Area of application en
Oceans and inland waters
Area of application fr
Océans et eaux intérieures
Research subject code
2109
Research subject group en
Mechanical engineering
Research subject group fr
Mechanical systems and instrumentation
Research subject en
Génie mécanique
Research subject fr
Instrumentation et systèmes mécaniques
Application title
Mobile-robot navigation, control, and mapping in spatiotemporal worlds
Keyword
Control systems; Environmental monitoring; Field robotics; Mobile robotics; Multi-robot systems; Nonlinear systems; Remote sensing; Robot navigation; Spatiotemporal mapping; State estimation
Application summary
Mobile equipment capable of autonomous or semi-autonomous operations is of relevance in remote, harsh, uncertain and dynamic environments where human presence is either not possible, hindered in some way, or highly undesirable (e.g., due to safety considerations). Something that we have come to realize in recent years is that the spatiotemporal nature of the "worlds" in which autonomous mobile robots operate has a more significant impact on performance than is generally appreciated. Vehicle navigation, control, and mapping systems often ignore spatiotemporal effects and view such time-varying characteristics as disturbances to be rejected in real-time or through post-processing. For some applications, these assumptions may be satisfactory. For others, spatiotemporal dynamics clearly play an integral role and in some cases be the very thing that we are interested in mapping. This proposed research program aims to explore the application of recent theoretical advances in spatiotemporal modelling to the problems of mobile robot navigation, control, and mapping in challenging outdoor environments. Our research will commence with the use of suitably equipped mobile robots for the purposes of learning spatiotemporal field models from data acquired during traversals in space and time. Consider, for example, the problem of estimating wave action, coastal erosion, or temperature gradients by using sensors installed on an uncrewed marine surface vessel. In this case, spatial modelling alone is not sufficient and our research will aim to develop methods based on mobile sampling to model (e.g., by using Gaussian process regression or other machine learning-based techniques) the spatiotemporal evolution of such processes by using discrete samples collected in both space and time. In the secondary stream of this research program, we plan to employ our learned spatiotemporal mapping techniques as a means to provide feedback to vehicle control systems that could be used to improve navigation and vehicle control system performance in dynamic scenarios for real-world applications. Finally, as is typical of our group's past research and inherent strengths, technical developments in both of the proposed research streams will be deployed and tested by using real hardware in representative physical environments. Trained HQP (2 PhD, 2 MASc, 5 USRA) will be part of a multi-disciplinary robotics and artificial intelligence (AI) research centre at Queen's and an NSERC Strategic Network, granting them access to state-of-the-art research space and robots. These resources include multiple Clearpath Husky A200 mobile robots, large robotic Kubota vehicles, a new Maritime Robotics Otter uncrewed surface vessel (USV), as well as a host of sensors, both proprioceptive and exteroceptive. Thus, there is a very strong case that the proposed research is not only feasible and executable, but also has the potential to find tangible impacts for both Canadian industry and society.
Queen's University - $42,000 Grant (2023-24) | Canada Spends