Neural Topological SLAM for Visual Navigation
This addresses navigation challenges for robots or agents in novel settings, with incremental improvements in representation and learning.
The paper tackles the problem of image-goal navigation in unseen environments by designing topological representations that leverage semantics and coarse geometry, resulting in a relative improvement of over 50% over existing methods.
This paper studies the problem of image-goal navigation which involves navigating to the location indicated by a goal image in a novel previously unseen environment. To tackle this problem, we design topological representations for space that effectively leverage semantics and afford approximate geometric reasoning. At the heart of our representations are nodes with associated semantic features, that are interconnected using coarse geometric information. We describe supervised learning-based algorithms that can build, maintain and use such representations under noisy actuation. Experimental study in visually and physically realistic simulation suggests that our method builds effective representations that capture structural regularities and efficiently solve long-horizon navigation problems. We observe a relative improvement of more than 50% over existing methods that study this task.