Semantic Visual Navigation by Watching YouTube Videos
This addresses the challenge of efficient semantic navigation for robots or agents in real-world settings, though it is incremental as it builds on existing Q-learning and hierarchical methods.
The paper tackles the problem of learning semantic cues for navigation in novel environments by watching YouTube videos, which lack action or goal labels, and demonstrates that using these cues in a hierarchical policy improves efficiency on the ObjectGoal task with a 15-83% relative improvement over baseline methods.
Semantic cues and statistical regularities in real-world environment layouts can improve efficiency for navigation in novel environments. This paper learns and leverages such semantic cues for navigating to objects of interest in novel environments, by simply watching YouTube videos. This is challenging because YouTube videos don't come with labels for actions or goals, and may not even showcase optimal behavior. Our method tackles these challenges through the use of Q-learning on pseudo-labeled transition quadruples (image, action, next image, reward). We show that such off-policy Q-learning from passive data is able to learn meaningful semantic cues for navigation. These cues, when used in a hierarchical navigation policy, lead to improved efficiency at the ObjectGoal task in visually realistic simulations. We observe a relative improvement of 15-83% over end-to-end RL, behavior cloning, and classical methods, while using minimal direct interaction.