Indoor Localization

My project is related to machine learning and robotics. A brief description of my project is the following: a robot comes into a room and takes snapshots of this room. Then the algorithm will make different digital representations of the room and store them in the database. After that, the robot can make photos of the room once again and compare the representation of the room to the representations stored in the database. Based on the most similar representations, a robot will classify the type of room it is in. A practical application of this research may be smart vacuum cleaners, that can switch to different cleaning modes based on the type of room it is in or check whether a robot has already cleaned a specific room.
For this research project, I apply convolutional neural networks, which are mostly used in Computer Vision tasks, specifically, NetVLAD and Deep Graph Convolutional Neural Network.

Faculty Supervisor:

Igor Gilitschenski

Student:

Partner:

Taras Shevchenko National University of Kyiv

Discipline:

Computer science

Sector:

Artificial Intelligence; Technology; Other

University:

University of Toronto

Program: