Grant: Alliance Grants
University of Calgary
$50,000.00
Transforming Indoor Navigation and Support through Language and Spatial Intelligence
FY 2024-25
Summary
Traditional indoor navigation methods face significant limitations, including lack of natural language support, reliance on static maps, and inability to interpret visual cues in dynamic environments. These systems often fail to adapt to real-time changes, consider user preferences, and provide comprehensive guidance. Additionally, they lack context-aware interactions, dynamic language processing capabilities, semantic understanding of spatial relationships, and adaptive decision-making based on complex environmental factors that LLMs can offer. The objective of the proposed project is to develop an Indoor Vision-Language Navigation (IVLN) system, which will enable robots to comprehend both visual information and natural language, thus allowing them to offer personalized, real-time directions and assistance. We will combine computer vision, spatial data processing and analytics, and natural language understanding, and use advanced learning techniques to blend visual, spatial, and language data, allowing the system to navigate effectively and communicate with users in real-time. The system will be evaluated through simulated scenarios and controlled tests in healthcare, retail, and emergency service environments to ensure its feasibility for future real-world applications. The proposed IVLN system represents a groundbreaking advancement in indoor navigation technology integrated with geospatial AI methods, transforming how we navigate complex indoor spaces. By improving daily experiences and critical safety measures, IVLN has the potential to make a significant impact. It will particularly benefit seniors and individuals with disabilities by enhancing their independence and safety. In emergencies, the system will efficiently guide rescue teams through hazardous environments. The project will utilize existing expertise to train highly qualified personnel in geospatial AI, vision-language navigation, and spatial data analytics. This innovation will position Canada and Alberta at the forefront of AI and robotics, attracting investment and creating high-skilled jobs while improving accessibility and safety for all Canadians.
Program
Alliance Grants
Recipient
Location
Alberta, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
600013-2024
Name nom
Wang, Xin X
Department département
Geomatics Engineering
Organization id
11
Institution établissement
University of Calgary
Province en
Alberta
Province fr
Alberta
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2024
Award amount
50000
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
1207
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Information, computer and communication technologies
Area of application fr
Technologie de l'information, des ordinateurs et des réseaux de communications
Research subject code
4100
Research subject group en
Geographical information
Research subject group fr
Information géographique
Research subject en
Geographical information
Research subject fr
Information géographique
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
Transforming Indoor Navigation and Support through Language and Spatial Intelligence
Keywords
geospatial information; large language models; vision language navigation
Application summary
Traditional indoor navigation methods face significant limitations, including lack of natural language support, reliance on static maps, and inability to interpret visual cues in dynamic environments. These systems often fail to adapt to real-time changes, consider user preferences, and provide comprehensive guidance. Additionally, they lack context-aware interactions, dynamic language processing capabilities, semantic understanding of spatial relationships, and adaptive decision-making based on complex environmental factors that LLMs can offer. The objective of the proposed project is to develop an Indoor Vision-Language Navigation (IVLN) system, which will enable robots to comprehend both visual information and natural language, thus allowing them to offer personalized, real-time directions and assistance. We will combine computer vision, spatial data processing and analytics, and natural language understanding, and use advanced learning techniques to blend visual, spatial, and language data, allowing the system to navigate effectively and communicate with users in real-time. The system will be evaluated through simulated scenarios and controlled tests in healthcare, retail, and emergency service environments to ensure its feasibility for future real-world applications. The proposed IVLN system represents a groundbreaking advancement in indoor navigation technology integrated with geospatial AI methods, transforming how we navigate complex indoor spaces. By improving daily experiences and critical safety measures, IVLN has the potential to make a significant impact. It will particularly benefit seniors and individuals with disabilities by enhancing their independence and safety. In emergencies, the system will efficiently guide rescue teams through hazardous environments. The project will utilize existing expertise to train highly qualified personnel in geospatial AI, vision-language navigation, and spatial data analytics. This innovation will position Canada and Alberta at the forefront of AI and robotics, attracting investment and creating high-skilled jobs while improving accessibility and safety for all Canadians.