Semantic 3D mapping and localization of intelligent drones in indoor environments

The objective of this project is to develop intelligent algorithms and machine learning models to enable semantic 3D mapping and localization of intelligent drones, allowing them to autonomously navigate complex indoor environments. The project will collaborate with SOTI Aerospace to establish a research and development team focused on advancing aerial technology for the next generation. The proposed solution is technologically innovative and will push the boundaries of drone performance and
applications. Unlike previous methods, this study incorporates semantic and contextual information about the surroundings and proposes the creation of a landmarks dictionary, greatly enhancing SLAM computation and obstacle estimation. Consequently, the proposed system will possess higher intelligence, offering a more efficient and reliable solution compared to previous systems. This study introduces a fresh perspective on autonomous navigation of indoor drones through the utilization of visual information.

Faculty Supervisor:

Guanghui Wang;Guangjun Liu

Student:

Partner:

SOTI Inc

Discipline:

Engineering

Sector:

Information and cultural industries; Professional, scientific and technical services

University:

Toronto Metropolitan University

Program: