Visual Navigation with Spatial Attention
This work addresses navigation for agents in visual environments, but it appears incremental as it builds on existing reinforcement learning methods with a new attention mechanism.
The paper tackles object goal visual navigation by proposing a novel attention probability model that combines semantic and spatial information, achieving state-of-the-art results on common datasets.
This work focuses on object goal 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.