|M.Sc Student||Mayo Bar|
|Subject||Visual Navigation with Spatial Attention|
|Department||Department of Electrical and Computers Engineering||Supervisors||PROF. Ayellet Tal|
|ASSOCIATE PROF. Tamir Hazan|
|Full Thesis text|
This work focuses on visual navigation, aiming at finding the location of an object from a given class, where in each step the agent is provided with an egocentric RGB image of the scene. We propose to learn the agent's policy using a reinforcement learning algorithm. Our key contribution is a novel attention probability model for visual navigation tasks. This attention encodes semantic information about observed objects, as well as spatial information about their place. This combination of the "what" and the "where" allows the agent to navigate toward the sought-after object effectively.
The attention model is shown to improve the agent's policy and to achieve state-of-the-art results on commonly-used datasets.